Javier Del Ser

In the last few years, Artificial Intelligence (AI) has achieved a notable momentum that, if harnessed appropriately, may deliver the best of expectations over many application sectors across the field. For this to occur shortly in Machine Learning, the entire community stands in front of the barrier of explainability, an inherent problem of the latest techniques brought by sub-symbolism (e.g. ensembles or Deep Neural Networks) that were not present in the last hype of AI (namely, expert systems and rule based models). Paradigms underlying this problem fall within the so-called eXplainable AI (XAI) field, which is widely acknowledged as a crucial feature for the practical deployment of AI models. The overview presented in this article examines the existing literature and contributions already done in the field of XAI, including a prospect toward what is yet to be reached. For this purpose we summarize previous efforts made to define explainability in Machine Learning, establishing a novel definition of explainable Machine Learning that covers such prior conceptual propositions with a major focus on the audience for which the explainability is sought. Departing from this definition, we propose and discuss about a taxonomy of recent contributions related to the explainability of different Machine Learning models, including those aimed at explaining Deep Learning methods for which a second dedicated taxonomy is built and examined in detail. This critical literature analysis serves as the motivating background for a series of challenges faced by XAI, such as the interesting crossroads of data fusion and explainability. Our prospects lead toward the concept of Responsible Artificial Intelligence, namely, a methodology for the large-scale implementation of AI methods in real organizations with fairness, model explainability and accountability at its core. Our ultimate goal is to provide newcomers to the field of XAI with a thorough taxonomy that can serve as reference material in order to stimulate future research advances, but also to encourage experts and professionals from other disciplines to embrace the benefits of AI in their activity sectors, without any prior bias for its lack of interpretability.

In recent years, the research community has witnessed an explosion of literature dealing with the mimicking of behavioral patterns and social phenomena observed in nature towards efficiently solving complex computational tasks. This trend has been especially dramatic in what relates to optimization problems, mainly due to the unprecedented complexity of problem instances, arising from a diverse spectrum of domains such as transportation, logistics, energy, climate, social networks, health and industry 4.0, among many others. Notwithstanding this upsurge of activity, research in this vibrant topic should be steered towards certain areas that, despite their eventual value and impact on the field of bio-inspired computation, still remain insufficiently explored to date. The main purpose of this paper is to outline the state of the art and to identify open challenges concerning the most relevant areas within bio-inspired optimization. An analysis and discussion are also carried out over the general trajectory followed in recent years by the community working in this field, thereby highlighting the need for reaching a consensus and joining forces towards achieving valuable insights into the understanding of this family of optimization techniques.

The so-called “smartization” of manufacturing industries has been conceived as the fourth industrial revolution or Industry 4.0, a paradigm shift propelled by the upsurge and progressive maturity of new Information and Communication Technologies (ICT) applied to industrial processes and products. From a data science perspective, this paradigm shift allows extracting relevant knowledge from monitored assets through the adoption of intelligent monitoring and data fusion strategies, as well as by the application of machine learning and optimization methods. One of the main goals of data science in this context is to effectively predict abnormal behaviors in industrial machinery, tools and processes so as to anticipate critical events and damage, eventually causing important economical losses and safety issues. In this context, data-driven prognosis is gradually gaining attention in different industrial sectors. This paper provides a comprehensive survey of the recent developments in data fusion and machine learning for industrial prognosis, placing an emphasis on the identification of research trends, niches of opportunity and unexplored challenges. To this end, a principled categorization of the utilized feature extraction techniques and machine learning methods will be provided on the basis of its intended purpose: analyze what caused the failure (descriptive), determine when the monitored asset will fail (predictive) or decide what to do so as to minimize its impact on the industry at hand (prescriptive). This threefold analysis, along with a discussion on its hardware and software implications, intends to serve as a stepping stone for future researchers and practitioners to join the community investigating on this vibrant field.

This paper thoroughly reviews and analyzes the main characteristics and application portfolio of the so-called Harmony Search algorithm, a meta-heuristic approach that has been shown to achieve excellent results in a wide range of optimization problems. As evidenced by a number of studies, this algorithm features several innovative aspects in its operational procedure that foster its utilization in diverse fields such as construction, engineering, robotics, telecommunications, health and energy. This manuscript will go through the most recent literature on the application of Harmony Search to the aforementioned disciplines towards a three-fold goal: (1) to underline the good behavior of this modern meta-heuristic based on the upsurge of related contributions reported to date; (2) to set a bibliographic basis for future research trends focused on its applicability to other areas; (3) to provide an insightful analysis of future research lines gravitating on this meta-heuristic solver.

Due to its paramount relevance in transport planning and logistics, road traffic forecasting has been a subject of active research within the engineering community for more than 40 years. In the beginning most approaches relied on autoregressive models and other analysis methods suited for time series data. More recently, the development of new technology, platforms and techniques for massive data processing under the Big Data umbrella, the availability of data from multiple sources fostered by the Open Data philosophy and an ever-growing need of decision makers for accurate traffic predictions have shifted the spotlight to data-driven procedures. This paper aims to summarize the efforts made to date in previous related surveys towards extracting the main comparing criteria and challenges in this field. A review of the latest technical achievements in this field is also provided, along with an insightful update of the main technical challenges that remain unsolved. The ultimate goal of this work is to set an updated, thorough, rigorous compilation of prior literature around traffic prediction models so as to motivate and guide future research on this vibrant field.

Ensembles, especially ensembles of decision trees, are one of the most popular and successful techniques in machine learning. Recently, the number of ensemble-based proposals has grown steadily. Therefore, it is necessary to identify which are the appropriate algorithms for a certain problem. In this paper, we aim to help practitioners to choose the best ensemble technique according to their problem characteristics and their workflow. To do so, we revise the most renowned bagging and boosting algorithms and their software tools. These ensembles are described in detail within their variants and improvements available in the literature. Their online-available software tools are reviewed attending to the implemented versions and features. They are categorized according to their supported programming languages and computing paradigms. The performance of 14 different bagging and boosting based ensembles, including XGBoost, LightGBM and Random Forest, is empirically analyzed in terms of predictive capability and efficiency. This comparison is done under the same software environment with 76 different classification tasks. Their predictive capabilities are evaluated with a wide variety of scenarios, such as standard multi-class problems, scenarios with categorical features and big size data. The efficiency of these methods is analyzed with considerably large data-sets. Several practical perspectives and opportunities are also exposed for ensemble learning.

Brain tumor is one of the most dangerous cancers in people of all ages, and its grade recognition is a challenging problem for radiologists in health monitoring and automated diagnosis. Recently, numerous methods based on deep learning have been presented in the literature for brain tumor classification (BTC) in order to assist radiologists for a better diagnostic analysis. In this overview, we present an in-depth review of the surveys published so far and recent deep learning-based methods for BTC. Our survey covers the main steps of deep learning-based BTC methods, including preprocessing, features extraction, and classification, along with their achievements and limitations. We also investigate the state-of-the-art convolutional neural network models for BTC by performing extensive experiments using transfer learning with and without data augmentation. Furthermore, this overview describes available benchmark data sets used for the evaluation of BTC. Finally, this survey does not only look into the past literature on the topic but also steps on it to delve into the future of this area and enumerates some research directions that should be followed in the future, especially for personalized and smart healthcare.

This paper reviews the most relevant works that have investigated robustness in power grids using Complex Networks (CN) concepts. In this broad field there are two different approaches. The first one is based solely on topological concepts, and uses metrics such as mean path length, clustering coefficient, efficiency and betweenness centrality, among many others. The second, hybrid approach consists of introducing (into the CN framework) some concepts from Electrical Engineering (EE) in the effort of enhancing the topological approach, and uses novel, more efficient electrical metrics such as electrical betweenness, net-ability, and others. There is however a controversy about whether these approaches are able to provide insights into all aspects of real power grids. The CN community argues that the topological approach does not aim to focus on the detailed operation, but to discover the unexpected emergence of collective behavior, while part of the EE community asserts that this leads to an excessive simplification. Beyond this open debate it seems to be no predominant structure (scale-free, small-world) in high-voltage transmission power grids, the vast majority of power grids studied so far. Most of them have in common that they are vulnerable to targeted attacks on the most connected nodes and robust to random failure. In this respect there are only a few works that propose strategies to improve robustness such as intentional islanding, restricted link addition, microgrids and Energies 2015, 8 9212 smart grids, for which novel studies suggest that small-world networks seem to be the best topology.

Advances in information and signal processing technologies have a significant impact on autonomous driving (AD), improving driving safety while minimizing the efforts of human drivers with the help of advanced artificial intelligence (AI) techniques. Recently, deep learning (DL) approaches have solved several real-world problems of complex nature. However, their strengths in terms of control processes for AD have not been deeply investigated and highlighted yet. This survey highlights the power of DL architectures in terms of reliability and efficient real-time performance and overviews state-of-the-art strategies for safe AD, with their major achievements and limitations. Furthermore, it covers major embodiments of DL along the AD pipeline including measurement, analysis, and execution, with a focus on road, lane, vehicle, pedestrian, drowsiness detection, collision avoidance, and traffic sign detection through sensing and vision-based DL methods. In addition, we discuss on the performance of several reviewed methods by using different evaluation metrics, with critics on their pros and cons. Finally, this survey highlights the current issues of safe DL-based AD with a prospect of recommendations for future research, rounding up a reference material for newcomers and researchers willing to join this vibrant area of Intelligent Transportation Systems.

In the last few years, the formulation of real-world optimization problems and their efficient solution via metaheuristic algorithms has been a catalyst for a myriad of research studies. In spite of decades of historical advancements on the design and use of metaheuristics, large difficulties still remain in regards to the understandability, algorithmic design uprightness, and performance verifiability of new technical achievements. A clear example stems from the scarce replicability of works dealing with metaheuristics used for optimization, which is often infeasible due to ambiguity and lack of detail in the presentation of the methods to be reproduced. Additionally, in many cases, there is a questionable statistical significance of their reported results. This work aims at providing the audience with a proposal of good practices which should be embraced when conducting studies about metaheuristics methods used for optimization in order to provide scientific rigor, value and transparency. To this end, we introduce a step by step methodology covering every research phase that should be followed when addressing this scientific field. Specifically, frequently overlooked yet crucial aspects and useful recommendations will be discussed in regards to the formulation of the problem, solution encoding, implementation of search operators, evaluation metrics, design of experiments, and considerations for real-world performance, among others. Finally, we will outline important considerations, challenges, and research directions for the success of newly developed optimization metaheuristics in their deployment and operation over real-world application environments.

This paper describes jMetalPy, an object-oriented Python-based framework for multi-objective optimization with metaheuristic techniques. Building upon our experiences with the well-known jMetal framework, we have developed a new multi-objective optimization software platform aiming not only at replicating the former one in a different programming language, but also at taking advantage of the full feature set of Python, including its facilities for fast prototyping and the large amount of available libraries for data processing, data analysis, data visualization, and high-performance computing. As a result, jMetalPy provides an environment for solving multi-objective optimization problems focused not only on traditional metaheuristics, but also on techniques supporting preference articulation, constrained and dynamic problems, along with a rich set of features related to the automatic generation of statistical data from the results generated, as well as the real-time and interactive visualization of the Pareto front approximations produced by the algorithms. jMetalPy offers additionally support for parallel computing in multicore and cluster systems. We include some use cases to explore the main features of jMetalPy and to illustrate how to work with it.

Recently millimeter-wave bands have been postulated as a means to accommodate the foreseen extreme bandwidth demands in vehicular communications, which result from the dissemination of sensory data to nearby vehicles for enhanced environmental awareness and improved safety level. However, the literature is particularly scarce in regards to principled resource allocation schemes that deal with the challenging radio conditions posed by the high mobility of vehicular scenarios. In this work we propose a novel framework that blends together Matching Theory and Swarm Intelligence to dynamically and efficiently pair vehicles and optimize both transmission and reception beamwidths. This is done by jointly considering Channel State Information (CSI) and Queue State Information (QSI) when establishing vehicle-to-vehicle (V2V) links. To validate the proposed framework, simulation results are presented and discussed where the throughput performance as well as the latency/reliability trade-offs of the proposed approach are assessed and compared to several baseline approaches recently proposed in the literature. The results obtained in our study show performance gains in terms of reliability and delay up to 25% for ultra-dense vehicular scenarios and on average 50% more paired vehicles that some of the baselines. These results shed light on the operational limits and practical feasibility of mmWave bands, as a viable radio access solution for future high-rate V2V communications.

Applications that generate huge amounts of data in the form of fast streams are becoming increasingly prevalent, being therefore necessary to learn in an online manner. These conditions usually impose memory and processing time restrictions, and they often turn into evolving environments where a change may affect the input data distribution. Such a change causes that predictive models trained over these stream data become obsolete and do not adapt suitably to new distributions. Specially in these non-stationary scenarios, there is a pressing need for new algorithms that adapt to these changes as fast as possible, while maintaining good performance scores. Unfortunately, most off-the-shelf classification models need to be retrained if they are used in changing environments, and fail to scale properly. Spiking Neural Networks have revealed themselves as one of the most successful approaches to model the behavior and learning potential of the brain, and exploit them to undertake practical online learning tasks. Besides, some specific flavors of Spiking Neural Networks can overcome the necessity of retraining after a drift occurs. This work intends to merge both fields by serving as a comprehensive overview, motivating further developments that embrace Spiking Neural Networks for online learning scenarios, and being a friendly entry point for non-experts.

Nowadays digital surveillance systems are universally installed for continuously collecting enormous amounts of data, thereby requiring human monitoring for the identification of different activities and events. Smarter surveillance is the need of this era through which normal and abnormal activities can be automatically identified using artificial intelligence and computer vision technology. In this paper, we propose a framework for activity recognition in surveillance videos captured over industrial systems. The continuous surveillance video stream is first divided into important shots, where shots are selected using the proposed convolutional neural network (CNN) based human saliency features. Next, temporal features of an activity in the sequence of frames are extracted by utilizing the convolutional layers of a FlowNet2 CNN model. Finally, a multilayer long short-term memory is presented for learning long-term sequences in the temporal optical flow features for activity recognition. Experiments <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">11</sup> https://github.com/Aminullah6264/Activity_Rec_ML-LSTM. are conducted using different benchmark action and activity recognition datasets, and the results reveal the effectiveness of the proposed method for activity recognition in industrial settings compared with state-of-the-art methods.

In recent algorithmic family simulates different biological processes observed in Nature in order to efficiently address complex optimization problems. In the last years the number of bio-inspired optimization approaches in literature has grown considerably, reaching unprecedented levels that dark the future prospects of this field of research. This paper addresses this problem by proposing two comprehensive, principle-based taxonomies that allow researchers to organize existing and future algorithmic developments into well-defined categories, considering two different criteria: the source of inspiration and the behavior of each algorithm. Using these taxonomies we review more than three hundred publications dealing with nature-inspired and bio-inspired algorithms, and proposals falling within each of these categories are examined, leading to a critical summary of design trends and similarities between them, and the identification of the most similar classical algorithm for each reviewed paper. From our analysis we conclude that a poor relationship is often found between the natural inspiration of an algorithm and its behavior. Furthermore, similarities in terms of behavior between different algorithms are greater than what is claimed in their public disclosure: specifically, we show that more than one-third of the reviewed bio-inspired solvers are versions of classical algorithms. Grounded on the conclusions of our critical analysis, we give several recommendations and points of improvement for better methodological practices in this active and growing research field.

The work presented in this paper is focused on the resolution of a real-world drugs distribution problem with pharmacological waste collection. With the aim of properly meeting all the real-world restrictions that comprise this complex problem, we have modeled it as a multi-attribute or rich vehicle routing problem (RVRP). The problem has been modeled as a Clustered Vehicle Routing Problem with Pickups and Deliveries, Asymmetric Variable Costs, Forbidden Roads and Cost Constraints. To the best of authors knowledge, this is the first time that such a RVRP problem is tackled in the literature. For this reason, a benchmark composed of 24 datasets, from 60 to 1000 customers, has also been designed. For the developing of this benchmark, we have used real geographical positions located in Bizkaia, Spain. Furthermore, for the proper dealing of the proposed RVRP, we have developed a Discrete and Improved Bat Algorithm (DaIBA). The main feature of this adaptation is the use of the well-known Hamming Distance to calculate the differences between the bats. An effective improvement has been also contemplated for the proposed DaIBA, which consists on the existence of two different neighborhood structures, which are explored depending on the bat's distance regarding the best individual of the swarm. For the experimentation, we have compared the performance of our presented DaIBA with three additional approaches: an evolutionary algorithm, an evolutionary simulated annealing and a firefly algorithm. Additionally, with the intention of obtaining rigorous conclusions, two different statistical tests have been conducted: the Friedman's non-parametric test and the Holm's post-hoc test. Furthermore, an additional experimentation has been performed in terms of convergence. Finally, the obtained outcomes conclude that the proposed DaIBA is a promising technique for addressing the designed problem.

Artificial intelligence (AI) is currently being utilized in a wide range of sophisticated applications, but the outcomes of many AI models are challenging to comprehend and trust due to their black-box nature. Usually, it is essential to understand the reasoning behind an AI model’s decision-making. Thus, the need for eXplainable AI (XAI) methods for improving trust in AI models has arisen. XAI has become a popular research subject within the AI field in recent years. Existing survey papers have tackled the concepts of XAI, its general terms, and post-hoc explainability methods but there have not been any reviews that have looked at the assessment methods, available tools, XAI datasets, and other related aspects. Therefore, in this comprehensive study, we provide readers with an overview of the current research and trends in this rapidly emerging area with a case study example. The study starts by explaining the background of XAI, common definitions, and summarizing recently proposed techniques in XAI for supervised machine learning. The review divides XAI techniques into four axes using a hierarchical categorization system: (i) data explainability, (ii) model explainability, (iii) post-hoc explainability, and (iv) assessment of explanations. We also introduce available evaluation metrics as well as open-source packages and datasets with future research directions. Then, the significance of explainability in terms of legal demands, user viewpoints, and application orientation is outlined, termed as XAI concerns. This paper advocates for tailoring explanation content to specific user types. An examination of XAI techniques and evaluation was conducted by looking at 410 critical articles, published between January 2016 and October 2022, in reputed journals and using a wide range of research databases as a source of information. The article is aimed at XAI researchers who are interested in making their AI models more trustworthy, as well as towards researchers from other disciplines who are looking for effective XAI methods to complete tasks with confidence while communicating meaning from data.

Medical artificial intelligence (AI) systems have been remarkably successful, even outperforming human performance at certain tasks. There is no doubt that AI is important to improve human health in many ways and will disrupt various medical workflows in the future. Using AI to solve problems in medicine beyond the lab, in routine environments, we need to do more than to just improve the performance of existing AI methods. Robust AI solutions must be able to cope with imprecision, missing and incorrect information, and explain both the result and the process of how it was obtained to a medical expert. Using conceptual knowledge as a guiding model of reality can help to develop more robust, explainable, and less biased machine learning models that can ideally learn from less data. Achieving these goals will require an orchestrated effort that combines three complementary Frontier Research Areas: (1) Complex Networks and their Inference, (2) Graph causal models and counterfactuals, and (3) Verification and Explainability methods. The goal of this paper is to describe these three areas from a unified view and to motivate how information fusion in a comprehensive and integrative manner can not only help bring these three areas together, but also have a transformative role by bridging the gap between research and practical applications in the context of future trustworthy medical AI. This makes it imperative to include ethical and legal aspects as a cross-cutting discipline, because all future solutions must not only be ethically responsible, but also legally compliant.

Bio-inspired optimization (including Evolutionary Computation and Swarm Intelligence) is a growing research topic with many competitive bio-inspired algorithms being proposed every year. In such an active area, preparing a successful proposal of a new bio-inspired algorithm is not an easy task. Given the maturity of this research field, proposing a new optimization technique with innovative elements is no longer enough. Apart from the novelty, results reported by the authors should be proven to achieve a significant advance over previous outcomes from the state of the art. Unfortunately, not all new proposals deal with this requirement properly. Some of them fail to select appropriate benchmarks or reference algorithms to compare with. In other cases, the validation process carried out is not defined in a principled way (or is even not done at all). Consequently, the significance of the results presented in such studies cannot be guaranteed. In this work we review several recommendations in the literature and propose methodological guidelines to prepare a successful proposal, taking all these issues into account. We expect these guidelines to be useful not only for authors, but also for reviewers and editors along their assessment of new contributions to the field.

In the industry 4.0 era, the visualization and real-time automatic monitoring of smart cities supported by the Internet of Things is becoming increasingly important. The use of filtering algorithms in smart city monitoring is a feasible method for this purpose. However, maintaining fast and accurate monitoring in complex surveillance environments with restricted resources remains a major challenge. Since the cognitive theory in visual monitoring is difficult to realize in practice, efficient monitoring of complex environments is accordingly hard to be achieved. Moreover, current monitoring methods do not consider the particularities of the human cognitive system, so the remonitoring ability of the process/target is weak in case of monitoring failure by the monitoring system. To overcome these issues, this article proposes a novel human short-long cognitive memory mechanism for video surveillance in smart cities. In this mechanism, a memory with a high reliability target is used as a “long-term memory,” whereas a memory with a low reliability target is used as a “short-term memory.” During the monitoring process, the “short-term memory” and “long-term memory” alternation strategy is combined with the stored target appearance characteristics, ensuring that the original model in the memory will not be contaminated or mislaid by changes in the external environment (occlusion, fast motion, motion blur, and background clutter). Extensive simulations showcase that the algorithm proposed in this article not only improves the monitoring speed without hindering its real-time operation but also monitors and traces the monitored target accurately, ultimately improving the robustness of the detection in complex scenery, and enabling its application to IoT-assisted smart cities.

In the last few years, visual sensors are deployed almost everywhere, generating a massive amount of surveillance video data in smart cities that can be inspected intelligently to recognize anomalous events. In this work, we present an efficient and robust framework to recognize anomalies from surveillance Big Video Data (BVD) using Artificial Intelligence of Things (AIoT). Smart surveillance is an important application of AIoT and we propose a two-stream neural network in this direction. The first stream comprises instant anomaly detection that is functional over resource-constrained IoT devices, whereas second phase is a two-stream deep neural network allowing for detailed anomaly analysis, suited to be deployed as a cloud computing service. Firstly, a self-pruned fine-tuned lightweight convolutional neural network (CNN) classifies the ongoing events as normal or anomalous in an AIoT environment. Upon anomaly detection, the edge device alerts the concerned departments and transmits the anomalous frames to cloud analysis center for their detailed evaluation in the second phase. The cloud analysis center resorts to the proposed two-stream network, modeled from the integration of spatiotemporal and optical flow features through the sequential frames. Fused features flow through a bi-directional long short-term memory (BD-LSTM) layer, which classifies them into their respective anomaly classes, e.g., assault and abuse. We perform extensive experiments over benchmarks built on top of the UCF-Crime and RWF-2000 datasets to test the effectiveness of our framework. We report a 9.88% and 4.01% increase in accuracy when compared to state-of-the-art methods evaluated over the aforementioned datasets.

Removing the bias and variance of multicentre data has always been a challenge in large scale digital healthcare studies, which requires the ability to integrate clinical features extracted from data acquired by different scanners and protocols to improve stability and robustness. Previous studies have described various computational approaches to fuse single modality multicentre datasets. However, these surveys rarely focused on evaluation metrics and lacked a checklist for computational data harmonisation studies. In this systematic review, we summarise the computational data harmonisation approaches for multi-modality data in the digital healthcare field, including harmonisation strategies and evaluation metrics based on different theories. In addition, a comprehensive checklist that summarises common practices for data harmonisation studies is proposed to guide researchers to report their research findings more effectively. Last but not least, flowcharts presenting possible ways for methodology and metric selection are proposed and the limitations of different methods have been surveyed for future research.

Magnetic resonance imaging (MRI) is an important non-invasive clinical tool that can produce high-resolution and reproducible images. However, a long scanning time is required for high-quality MR images, which leads to exhaustion and discomfort of patients, inducing more artefacts due to voluntary movements of the patients and involuntary physiological movements. To accelerate the scanning process, methods by k-space undersampling and deep learning based reconstruction have been popularised. This work introduced SwinMR, a novel Swin transformer based method for fast MRI reconstruction. The whole network consisted of an input module (IM), a feature extraction module (FEM) and an output module (OM). The IM and OM were 2D convolutional layers and the FEM was composed of a cascaded of residual Swin transformer blocks (RSTBs) and 2D convolutional layers. The RSTB consisted of a series of Swin transformer layers (STLs). The shifted windows multi-head self-attention (W-MSA/SW-MSA) of STL was performed in shifted windows rather than the multi-head self-attention (MSA) of the original transformer in the whole image space. A novel multi-channel loss was proposed by using the sensitivity maps, which was proved to reserve more textures and details. We performed a series of comparative studies and ablation studies in the Calgary-Campinas public brain MR dataset and conducted a downstream segmentation experiment in the Multi-modal Brain Tumour Segmentation Challenge 2017 dataset. The results demonstrate our SwinMR achieved high-quality reconstruction compared with other benchmark methods, and it shows great robustness with different undersampling masks, under noise interruption and on different datasets. The code is publicly available at https://github.com/ayanglab/SwinMR.

In recent years, deep learning has revolutionized computer vision and has been widely used for monitoring in diverse visual scenes. However, in terms of some aspects such as complexity and explainability, deep learning is not always preferable over traditional machine-learning methods. Traditional visual tracking approaches have shown certain advantages in terms of data collection efficiency, computing requirements, and power consumption and are generally easier to understand and explain than deep neural networks. At present, traditional feature-based techniques relying on correlation filtering (CF) have become common for understanding complex visual scenes. However, current CF algorithms use a single feature to describe the information of the target and locate it accordingly. They cannot fully express changeable target appearances in a complex scene, which can easily lead to inaccurate target locations in time-varying visual scenes. Moreover, owing to the complexity of surveillance scenes, monitoring algorithms can lose their target. The original template update strategy uses each frame with a fixed interval length as a new template, which may lead to unreliable feature extraction and low tracking accuracy. To overcome these issues, in this work, we introduce an original location fusion mechanism based on multiple visual cognition processing streams to achieve real-time and efficient visual monitoring in complex scenes. First, we propose a process for extracting multiple forms of visual cognitive information, and it is periodically used to extract multiple feature information flows of a target of interest. Subsequently, a cognitive information fusion process is employed to fuse the positioning results of different visual cognitive information flows to achieve high-quality visual monitoring and positioning. Finally, a novel feature template memory storage and retrieval strategy is adopted. When the location result is unreliable, the target is retrieved from memory to ensure robust and accurate tracking. In addition, we provide an extensive set of performance results showing that our proposed approach exhibits more robust performance at a lower computational cost compared with 36 state-of-the-art algorithms for visual tracking in complex scenes.

In this work, we consider multitasking in the context of solving multiple optimization problems simultaneously by conducting a single search process. The principal goal when dealing with this scenario is to dynamically exploit the existing complementarities among the problems (tasks) being optimized, helping each other through the exchange of valuable knowledge. Additionally, the emerging paradigm of evolutionary multitasking tackles multitask optimization scenarios by using biologically inspired concepts drawn from swarm intelligence and evolutionary computation. The main purpose of this survey is to collect, organize, and critically examine the abundant literature published so far in evolutionary multitasking, with an emphasis on the methodological patterns followed when designing new algorithmic proposals in this area (namely, multifactorial optimization and multipopulation-based multitasking). We complement our critical analysis with an identification of challenges that remain open to date, along with promising research directions that can leverage the potential of biologically inspired algorithms for multitask optimization. Our discussions held throughout this manuscript are offered to the audience as a reference of the general trajectory followed by the community working in this field in recent times, as well as a self-contained entry point for newcomers and researchers interested to join this exciting research avenue.

Trustworthy Artificial Intelligence (AI) is based on seven technical requirements sustained over three main pillars that should be met throughout the system’s entire life cycle: it should be (1) lawful, (2) ethical, and (3) robust, both from a technical and a social perspective. However, attaining truly trustworthy AI concerns a wider vision that comprises the trustworthiness of all processes and actors that are part of the system’s life cycle, and considers previous aspects from different lenses. A more holistic vision contemplates four essential axes: the global principles for ethical use and development of AI-based systems, a philosophical take on AI ethics, a risk-based approach to AI regulation, and the mentioned pillars and requirements. The seven requirements (human agency and oversight; robustness and safety; privacy and data governance; transparency; diversity, non-discrimination and fairness; societal and environmental wellbeing; and accountability) are analyzed from a triple perspective: What each requirement for trustworthy AI is, Why it is needed, and How each requirement can be implemented in practice. On the other hand, a practical approach to implement trustworthy AI systems allows defining the concept of responsibility of AI-based systems facing the law, through a given auditing process. Therefore, a responsible AI system is the resulting notion we introduce in this work, and a concept of utmost necessity that can be realized through auditing processes, subject to the challenges posed by the use of regulatory sandboxes. Our multidisciplinary vision of trustworthy AI culminates in a debate on the diverging views published lately about the future of AI. Our reflections in this matter conclude that regulation is a key for reaching a consensus among these views, and that trustworthy and responsible AI systems will be crucial for the present and future of our society.

Over the years, Machine Learning models have been successfully employed on neuroimaging data for accurately predicting brain age. Deviations from the healthy brain aging pattern are associated to the accelerated brain aging and brain abnormalities. Hence, efficient and accurate diagnosis techniques are required for eliciting accurate brain age estimations. Several contributions have been reported in the past for this purpose, resorting to different data-driven modeling methods. Recently, deep neural networks (also referred to as deep learning) have become prevalent in manifold neuroimaging studies, including brain age estimation. In this review, we offer a comprehensive analysis of the literature related to the adoption of deep learning for brain age estimation with neuroimaging data. We detail and analyze different deep learning architectures used for this application, pausing at research works published to date quantitatively exploring their application. We also examine different brain age estimation frameworks, comparatively exposing their advantages and weaknesses. Finally, the review concludes with an outlook towards future directions that should be followed by prospective studies. The ultimate goal of this paper is to establish a common and informed reference for newcomers and experienced researchers willing to approach brain age estimation by using deep learning models

Electrocardiogram (ECG) is a widely used technique to diagnose cardiovascular diseases. It is a non-invasive technique that represents the cyclic contraction and relaxation of heart muscles. ECG can be used to detect abnormal heart motions, heart attacks, heart diseases, or enlarged hearts by measuring the heart’s electrical activity. Over the past few years, various works have been done in the field of studying and analyzing the ECG signals to detect heart diseases. In this work, we propose a deep learning and fuzzy clustering (Fuzz-ClustNet) based approach for Arrhythmia detection from ECG signals. We started by denoising the collected ECG signals to remove errors like baseline drift, power line interference, motion noise, etc. The denoised ECG signals are then segmented to have an increased focus on the ECG signals. We then perform data augmentation on the segmented images to counter the effects of the class imbalance. The augmented images are then passed through a CNN feature extractor. The extracted features are then passed to a fuzzy clustering algorithm to classify the ECG signals for their respective cardio diseases. We ran intensive simulations on two benchmarked datasets and evaluated various performance metrics. The performance of our proposed algorithm was compared with several recently proposed algorithms for heart disease detection from ECG signals. The obtained results demonstrate the efficacy of our proposed approach as compared to other contemporary algorithms.

Alzheimer's disease (AD) is a neurological illness that causes cognitive impairment and has no known treatment. The premise for delivering timely therapy is the early diagnosis of AD before clinical symptoms appear. Mild cognitive impairment is an intermediate stage in which cognitively normal patients can be distinguished from those with AD. In this study, we propose a hybrid multimodal deep-learning framework consisting of a 3D convolutional neural network (3D CNN) followed by a bidirectional recurrent neural network (BRNN). The proposed 3D CNN captures intra-slice features from each 3D magnetic resonance imaging (MRI) volume, whereas the BRNN module identifies the inter-sequence patterns that lead to AD. This study is conducted based on longitudinal 3D MRI volumes collected over a six-months time span. We further investigate the effect of fusing MRI with cross-sectional biomarkers, such as patients' demographic and cognitive scores from their baseline visit. In addition, we present a novel explainability approach that helps domain experts and practitioners to understand the end output of the proposed multimodal. Extensive experiments reveal that the accuracy, precision, recall, and area under the receiver operating characteristic curve of the proposed framework are 96%, 99%, 92%, and 96%, respectively. These results are based on the fusion of MRI and demographic features and indicate that the proposed framework becomes more stable when exposed to a more complete set of longitudinal data. Moreover, the explainability module provides extra support for the progression claim by more accurately identifying the brain regions that domain experts commonly report during diagnoses.

Panchromatic and multispectral image fusion, termed pan-sharpening, is to merge the spatial and spectral information of the source images into a fused one, which has a higher spatial and spectral resolution and is more reliable for downstream tasks compared with any of the source images. It has been widely applied to image interpretation and pre-processing of various applications. A large number of methods have been proposed to achieve better fusion results by considering the spatial and spectral relationships among panchromatic and multispectral images. In recent years, the fast development of artificial intelligence (AI) and deep learning (DL) has significantly enhanced the development of pan-sharpening techniques. However, this field lacks a comprehensive overview of recent advances boosted by the rise of AI and DL. This paper provides a comprehensive review of a variety of pan-sharpening methods that adopt four different paradigms, i.e., component substitution, multiresolution analysis, degradation model, and deep neural networks. As an important aspect of pan-sharpening, the evaluation of the fused image is also outlined to present various assessment methods in terms of reduced-resolution and full-resolution quality measurement. Then, we conclude this paper by discussing the existing limitations, difficulties, and challenges of pan-sharpening techniques, datasets, and quality assessment. In addition, the survey summarizes the development trends in these areas, which provide useful methodological practices for researchers and professionals. Finally, the developments in pan-sharpening are summarized in the conclusion part. The aim of the survey is to serve as a referential starting point for newcomers and a common point of agreement around the research directions to be followed in this exciting area.

Understanding black box models has become paramount as systems based on opaque Artificial Intelligence (AI) continue to flourish in diverse real-world applications. In response, Explainable AI (XAI) has emerged as a field of research with practical and ethical benefits across various domains. This paper highlights the advancements in XAI and its application in real-world scenarios and addresses the ongoing challenges within XAI, emphasizing the need for broader perspectives and collaborative efforts. We bring together experts from diverse fields to identify open problems, striving to synchronize research agendas and accelerate XAI in practical applications. By fostering collaborative discussion and interdisciplinary cooperation, we aim to propel XAI forward, contributing to its continued success. We aim to develop a comprehensive proposal for advancing XAI. To achieve this goal, we present a manifesto of 28 open problems categorized into nine categories. These challenges encapsulate the complexities and nuances of XAI and offer a road map for future research. For each problem, we provide promising research directions in the hope of harnessing the collective intelligence of interested stakeholders.

Deep learning models like chatGPT exemplify AI success but necessitate a deeper understanding of trust in critical sectors. Trust can be achieved using counterfactual explanations, which is how humans become familiar with unknown processes; by understanding the hypothetical input circumstances under which the output changes. We argue that the generation of counterfactual explanations requires several aspects of the generated counterfactual instances, not just their counterfactual ability. We present a framework for generating counterfactual explanations that formulate its goal as a multiobjective optimization problem balancing three objectives: plausibility; the intensity of changes; and adversarial power. We use a generative adversarial network to model the distribution of the input, along with a multiobjective counterfactual discovery solver balancing these objectives. We demonstrate the usefulness of six classification tasks with image and 3D data confirming with evidence the existence of a trade-off between the objectives, the consistency of the produced counterfactual explanations with human knowledge, and the capability of the framework to unveil the existence of concept-based biases and misrepresented attributes in the input domain of the audited model. Our pioneering effort shall inspire further work on the generation of plausible counterfactual explanations in real-world scenarios where attribute-/concept-based annotations are available for the domain under analysis.

Vessel border detection in IVUS images is essential for coronary disease diagnosis. It helps to obtain the clinical indices on the inner vessel morphology to indicate the stenosis. However, the existing methods suffer the challenge of scale-dependent interference. Early methods usually rely on the hand-crafted features, thus not robust to this interference. The existing deep learning methods are also ineffective to solve this challenge, because these methods aggregate multi-scale features in the top-down way. This aggregation may bring in interference from the non-adjacent scale. Besides, they only combine the features in all scales, and thus may weaken their complementary information. We propose the scale mutualized perception to solve this challenge by considering the adjacent scales mutually to preserve their complementary information. First, the adjacent small scales contain certain semantics to locate different vessel tissues. Then, they can also perceive the global context to assist the representation of the local context in the adjacent large scale, and vice versa. It helps to distinguish the objects with similar local features. Second, the adjacent large scales provide detailed information to refine the vessel boundaries. The experiments show the effectiveness of our method in 153 IVUS sequences, and its superiority to ten state-of-the-art methods.

Domain generalization aims to learn common knowledge from multiple observed source domains and transfer it to unseen target domains, e.g. the object recognition in varieties of visual environments. Traditional domain generalization methods aim to learn the feature representation of the raw data with its distribution invariant across domains. This relies on the assumption that the two posterior distributions (the distributions of the label given the feature distribution and given the raw data) are stable in different domains. However, this does not always hold in many practical situations. In this paper, we relax the above assumption by permitting the posterior distribution of the label given the raw data changes in difference domains, and thus focuses on a more realistic learning problem that infers the conditional domain-invariant feature representation. Specifically, a multi-domain adversarial variational Bayesian inference approach is proposed to minimize the inter-domain discrepancy of the conditional distributions of the feature given the label. Besides, it is imposed by the constraints from the adversarial learning and feedback mechanism to enhance the condition invariant feature representation. The extensive experiments on two datasets demonstrate the effectiveness of our approach, as well as the state-of-the-art performance comparing with thirteen methods.

Airway segmentation is crucial for the examination, diagnosis, and prognosis of lung diseases, while its manual delineation is unduly burdensome. To alleviate this time-consuming and potentially subjective manual procedure, researchers have proposed methods to automatically segment airways from computerized tomography (CT) images. However, some small-sized airway branches (e.g., bronchus and terminal bronchioles) significantly aggravate the difficulty of automatic segmentation by machine learning models. In particular, the variance of voxel values and the severe data imbalance in airway branches make the computational module prone to discontinuous and false-negative predictions, especially for cohorts with different lung diseases. The attention mechanism has shown the capacity to segment complex structures, while fuzzy logic can reduce the uncertainty in feature representations. Therefore, the integration of deep attention networks and fuzzy theory, given by the fuzzy attention layer, should be an escalated solution for better generalization and robustness. This article presents an efficient method for airway segmentation, comprising a novel fuzzy attention neural network (FANN) and a comprehensive loss function to enhance the spatial continuity of airway segmentation. The deep fuzzy set is formulated by a set of voxels in the feature map and a learnable Gaussian membership function. Different from the existing attention mechanism, the proposed channel-specific fuzzy attention addresses the issue of heterogeneous features in different channels. Furthermore, a novel evaluation metric is proposed to assess both the continuity and completeness of airway structures. The efficiency, generalization, and robustness of the proposed method have been proved by training on normal lung disease while testing on datasets of lung cancer, COVID-19, and pulmonary fibrosis.

This paper presents a novel bioinspired algorithm to tackle complex optimization problems: the coral reefs optimization (CRO) algorithm. The CRO algorithm artificially simulates a coral reef, where different corals (namely, solutions to the optimization problem considered) grow and reproduce in coral colonies, fighting by choking out other corals for space in the reef. This fight for space, along with the specific characteristics of the corals' reproduction, produces a robust metaheuristic algorithm shown to be powerful for solving hard optimization problems. In this research the CRO algorithm is tested in several continuous and discrete benchmark problems, as well as in practical application scenarios (i.e., optimum mobile network deployment and off-shore wind farm design). The obtained results confirm the excellent performance of the proposed algorithm and open line of research for further application of the algorithm to real-world problems.

In this paper we present a novel grouping genetic algorithm for clustering problems. Though there have been different approaches that have analyzed the performance of several genetic and evolutionary algorithms in clustering, the grouping-based approach has not been, to our knowledge, tested in this problem yet. In this paper we fully describe the grouping genetic algorithm for clustering, starting with the proposed encoding, different modifications of crossover and mutation operators, and also the description of a local search and an island model included in the algorithm, to improve the algorithm's performance in the problem. We test the proposed grouping genetic algorithm in several experiments in synthetic and real data from public repositories, and compare its results with that of classical clustering approaches, such as K-means and DBSCAN algorithms, obtaining excellent results that confirm the goodness of the proposed grouping-based methodology.

The Internet of Health Things promotes personalized and higher standards of care. Its application is diverse and attracts the attention of a substantial section of the scientific community. This approach has also been applied by people looking to enhance quality of life by using this technology. In this paper, we perform a survey that aims to present and analyze the advances of the latest studies based on medical care and assisted environment. We focus on articles for online monitoring, detection, and support of the diagnosis of cardiovascular diseases. Our research covers published manuscripts in scientific journals and recognized conferences since the year 2015. Also, we present a reference model based on the evaluation of the resources used from the selected studies. Finally, our proposal aims to help future enthusiasts to discover and enumerate the required factors for the development of a prototype for online heart monitoring purposes.

The water cycle algorithm (WCA) is a nature-inspired meta-heuristic recently contributed to the community in 2012, which finds its motivation in the natural surface runoff phase in water cycle process and on how streams and rivers flow into the sea. This method has been so far successfully applied to many engineering applications, spread over a wide variety of application fields. In this paper an enhanced discrete version of the WCA (coined as DWCA) is proposed for solving the Symmetric and Asymmetric Traveling Salesman Problem. Aimed at proving that the developed approach is a promising approximation method for solving this family of optimization problems, the designed solver has been tested over 33 problem datasets, comparing the obtained outcomes with the ones got by six different algorithmic counterparts from the related literature: genetic algorithm, island-based genetic algorithm, evolutionary simulated annealing, bat algorithm, firefly algorithm and imperialist competitive algorithm. Furthermore, the statistical significance of the performance gaps found in this benchmark is validated based on the results from non-parametric tests, not only in terms of optimality but also in regards to convergence speed. We conclude that the proposed DWCA approach outperforms – with statistical significance – any other optimization technique in the benchmark in terms of both computation metrics.

Big Data is an emerging paradigm and has currently become a strong attractor of global interest, specially within the transportation industry. The combination of disruptive technologies and new concepts such as the Smart City upgrades the transport data life cycle. In this context, Big Data is considered as a new pledge for the transportation industry to effectively manage all data this sector required for providing safer, cleaner and more efficient transport means, as well as for users to personalize their transport experience. However, Big Data comes along with its own set of technological challenges, stemming from the multiple and heterogeneous transportation/mobility application scenarios. In this survey we analyze the latest research efforts revolving on Big Data for the transportation and mobility industry, its applications, baselines scenarios, fields and use case such as routing, planning, infrastructure monitoring, network design, among others. This analysis will be done strictly from the Big Data perspective, focusing on those contributions gravitating on techniques, tools and methods for modeling, processing, analyzing and visualizing transport and mobility Big Data. From the literature review a set of trends and challenges is extracted so as to provide researchers with an insightful outlook on the field of transport and mobility.

Vehicle flow forecasting is of crucial importance for the management of road traffic in complex urban networks, as well as a useful input for route planning algorithms. In general traffic predictive models rely on data gathered by different types of sensors placed on roads, which occasionally produce faulty readings due to several causes, such as malfunctioning hardware or transmission errors. Filling in those gaps is relevant for constructing accurate forecasting models, a task which is engaged by diverse strategies, from a simple null value imputation to complex spatio-temporal context imputation models. This work elaborates on two machine learning approaches to update missing data with no gap length restrictions: a spatial context sensing model based on the information provided by surrounding sensors, and an automated clustering analysis tool that seeks optimal pattern clusters in order to impute values. Their performance is assessed and compared to other common techniques and different missing data generation models over real data captured from the city of Madrid (Spain). The newly presented methods are found to be fairly superior when portions of missing data are large or very abundant, as occurs in most practical cases.

Immersive virtual reality (VR) applications require ultra-high data rate and low-latency for smooth operation. Hence in this paper, aiming to improve VR experience in multi-user VR wireless video streaming, a deep-learning aided scheme for maximizing the quality of the delivered video chunks with low-latency is proposed. Therein the correlations in the predicted field of view (FoV) and locations of viewers watching 360$^\circ$ HD VR videos are capitalized on to realize a proactive FoV-centric millimeter wave (mmWave) physical-layer multicast transmission. The problem is cast as a frame quality maximization problem subject to tight latency constraints and network stability. The problem is then decoupled into an HD frame request admission and scheduling subproblems and a matching theory game is formulated to solve the scheduling subproblem by associating requests from clusters of users to mmWave small cell base stations (SBSs) for their unicast/multicast transmission. Furthermore, for realistic modeling and simulation purposes, a real VR head-tracking dataset and a deep recurrent neural network (DRNN) based on gated recurrent units (GRUs) are leveraged. Extensive simulation results show how the content-reuse for clusters of users with highly overlapping FoVs brought in by multicasting reduces the VR frame delay in 12\%. This reduction is further boosted by proactiveness that cuts by half the average delays of both reactive unicast and multicast baselines while preserving HD delivery rates above 98\%. Finally, enforcing tight latency bounds shortens the delay-tail as evinced by 13\% lower delays in the 99th percentile.

Urban air pollution is a matter of growing concern for both public administrations and citizens. Road traffic is one of the main sources of air pollutants, though topography characteristics and meteorological conditions can make pollution levels increase or diminish dramatically. In this context an upsurge of research has been conducted towards functionally linking variables of such domains to measured pollution data, with studies dealing with up to one-hour resolution meteorological data. However, the majority of such reported contributions do not deal with traffic data or, at most, simulate traffic conditions jointly with the consideration of different topographical features. The aim of this study is to further explore this relationship by using high-resolution real traffic data. This paper describes a methodology based on the construction of regression models to predict levels of different pollutants (i.e. CO, NO, NO2, O3 and PM10) based on traffic data and meteorological conditions, from which an estimation of the predictive relevance (importance) of each utilized feature can be estimated by virtue of their particular training procedure. The study was made with one hour resolution meteorological, traffic and pollution historic data in roadside and background locations of the city of Madrid (Spain) captured over 2015. The obtained results reveal that the impact of vehicular emissions on the pollution levels is overshadowed by the effects of stable meteorological conditions of this city.

Management and mission planning over a swarm of unmanned aerial vehicle (UAV) remains to date as a challenging research trend in what regards to this particular type of aircrafts. These vehicles are controlled by a number of ground control station (GCS), from which they are commanded to cooperatively perform different tasks in specific geographic areas of interest. Mathematically the problem of coordinating and assigning tasks to a swarm of UAV can be modeled as a constraint satisfaction problem, whose complexity and multiple conflicting criteria has hitherto motivated the adoption of multi-objective solvers such as multi-objective evolutionary algorithm (MOEA). The encoding approach consists of different alleles representing the decision variables, whereas the fitness function checks that all constraints are fulfilled, minimizing the optimization criteria of the problem. In problems of high complexity involving several tasks, UAV and GCS, where the space of search is huge compared to the space of valid solutions, the convergence rate of the algorithm increases significantly. To overcome this issue, this work proposes a weighted random generator for the creation and mutation of new individuals. The main objective of this work is to reduce the convergence rate of the MOEA solver for multi-UAV mission planning using weighted random strategies that focus the search on potentially better regions of the solution space. Extensive experimental results over a diverse range of scenarios evince the benefits of the proposed approach, which notably improves this convergence rate with respect to a naïve MOEA approach.

Fire disaster throughout the globe causes social, environmental, and economical damage, making its early detection and instant reporting essential for saving human lives and properties. Smoke detection plays a key role in early fire detection but majority of the existing methods are limited to either indoor or outdoor surveillance environments, with poor performance for hazy scenarios. In this paper, we present a Convolutional Neural Network (CNN)-based smoke detection and segmentation framework for both clear and hazy environments. Unlike existing methods, we employ an efficient CNN architecture, termed EfficientNet, for smoke detection with better accuracy. We also segment the smoke regions using DeepLabv3+, which is supported by effective encoders and decoders along with a pixel-wise classifier for optimum localization. Our smoke detection results evince a noticeable gain up to 3% in accuracy and a decrease of 0.46% in False Alarm Rate (FAR), while segmentation reports a significant increase of 2% and 1% in global accuracy and mean Intersection over Union (IoU) scores, respectively. This makes our method a best fit for smoke detection and segmentation in real-world surveillance settings.

Nowadays, video sensors are used on a large scale for various applications, including security monitoring and smart transportation. However, the limited communication bandwidth and storage constraints make it challenging to process such heterogeneous nature of Big Data in real time. Multiview video summarization (MVS) enables us to suppress redundant data in distributed video sensors settings. The existing MVS approaches process video data in offline manner by transmitting them to the local or cloud server for analysis, which requires extra streaming to conduct summarization, huge bandwidth, and are not applicable for integration with industrial Internet of Things (IIoT). This article presents a light-weight convolutional neural network (CNN) and IIoT-based computationally intelligent (CI) MVS framework. Our method uses an IIoT network containing smart devices, Raspberry Pi (RPi) (clients and master) with embedded cameras to capture multiview video data. Each client RPi detects target in frames via light-weight CNN model, analyzes these targets for traffic and crowd density, and searches for suspicious objects to generate alert in the IIoT network. The frames of each client RPi are encoded and transmitted with approximately 17.02% smaller size of each frame to master RPi for final MVS. Empirical analysis shows that our proposed framework can be used in industrial environments for various applications such as security and smart transportation and can be proved beneficial for saving resources. <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">11</sup> [Online]. Available: https://github.com/tanveer-hussain/Embedded-Vision-for-MVS.

The exponential growth in the production of video contents in different industries causes an urgent need for effective video summarization (VS) techniques, in order to get an optimal storage and preservation of key information in the video. Compared to other domains, industrial videos are more challenging to process, as they usually contain diverse and complex events, which make their online processing a difficult task. In this article, we introduce an online system for intelligent video capturing, coarse and fine redundancy removal, and summary generation. First, we capture video data through resource-constrained devices in an industrial Internet of Things network, equipped with vision sensors and apply coarse redundancy removal through the comparison of low-level features. Second, we transmit the resulting frames to the cloud for detailed analysis, where sequential features are extracted for the selection of candidate keyframes. Finally, we refine the candidate keyframes in order to discriminate those with maximum information as part of the summary. The key contributions of this article include the coarse and fine refining of video data implemented over resource-restricted devices and the presentation of important data in the form of a summary. Experiments <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">11</sup> [Online]. Available: https://github.com/tanveer-hussain/DeepRes-Video-Summarization. over publicly available datasets evince a 0.3-unit increase in the F1 score when compared to state-of-the-art and with reduced time complexity. Furthermore, we provide convincing results on our newly created dataset in an industrial environment, which is made publicly available for the research community along with its labeled ground truth.

Due to the nature of traffic itself, most traffic forecasting models reported in literature aim at producing short-term predictions, yet their performance degrades when the prediction horizon is increased. The scarce long-term estimation strategies currently found in the literature are commonly based on the detection and assignment to patterns, but their performance decays when unexpected events provoke non predictable changes, or if the allocation to a traffic pattern is inaccurate. This work introduces a method to obtain long-term pattern forecasts and adapt them to real-time circumstances. To this end, a long-term estimation scheme based on the automated discovery of patterns is proposed and integrated with an on-line change detection and adaptation mechanism. The framework takes advantage of the architecture of evolving Spiking Neural Networks (eSNN) to perform adaptations without retraining the model, allowing the whole system to work autonomously in an on-line fashion. Its performance is assessed over a real scenario with 5 min data of a 6-month span of traffic in the center of Madrid, Spain. Significant accuracy gains are obtained when applying the proposed on-line adaptation mechanism on days with special, non-predictable events that degrade the quality of their long-term traffic forecasts.

Unsupervised anomaly discovery in stream data is a research topic with many practical applications. However, in many cases, it is not easy to collect enough training data with labeled anomalies for supervised learning of an anomaly detector in order to deploy it later for identification of real anomalies in streaming data. It is thus important to design anomalies detectors that can correctly detect anomalies without access to labeled training data. Our idea is to adapt the Online evolving Spiking Neural Network (OeSNN) classifier to the anomaly detection task. As a result, we offer an Online evolving Spiking Neural Network for Unsupervised Anomaly Detection algorithm (OeSNN-UAD), which, unlike OeSNN, works in an unsupervised way and does not separate output neurons into disjoint decision classes. OeSNN-UAD uses our proposed new two-step anomaly detection method. Also, we derive new theoretical properties of neuronal model and input layer encoding of OeSNN, which enable more effective and efficient detection of anomalies in our OeSNN-UAD approach. The proposed OeSNN-UAD detector was experimentally compared with state-of-the-art unsupervised and semi-supervised detectors of anomalies in stream data from the Numenta Anomaly Benchmark and Yahoo Anomaly Datasets repositories. Our approach outperforms the other solutions provided in the literature in the case of data streams from the Numenta Anomaly Benchmark repository. Also, in the case of real data files of the Yahoo Anomaly Benchmark repository, OeSNN-UAD outperforms other selected algorithms, whereas in the case of Yahoo Anomaly Benchmark synthetic data files, it provides competitive results to the results recently reported in the literature.

Deep Learning methods have been proven to be flexible to model complex phenomena. This has also been the case of Intelligent Transportation Systems, in which several areas such as vehicular perception and traffic analysis have widely embraced Deep Learning as a core modeling technology. Particularly in short-term traffic forecasting, the capability of Deep Learning to deliver good results has generated a prevalent inertia towards using Deep Learning models, without examining in depth their benefits and downsides. This paper focuses on critically analyzing the state of the art in what refers to the use of Deep Learning for this particular Intelligent Transportation Systems research area. To this end, we elaborate on the findings distilled from a review of publications from recent years, based on two taxonomic criteria. A posterior critical analysis is held to formulate questions and trigger a necessary debate about the issues of Deep Learning for traffic forecasting. The study is completed with a benchmark of diverse short-term traffic forecasting methods over traffic datasets of different nature, aimed to cover a wide spectrum of possible scenarios. Our experimentation reveals that Deep Learning could not be the best modeling technique for every case, which unveils some caveats unconsidered to date that should be addressed by the community in prospective studies. These insights reveal new challenges and research opportunities in road traffic forecasting, which are enumerated and discussed thoroughly, with the intention of inspiring and guiding future research efforts in this field.

In the last few years, methods falling within the family of randomization-based machine learning models have grasped a great interest in the Artificial Intelligence community, mainly due to their excellent balance between performance in prediction problems and their computational efficiency. The use of these models for prediction problems related to renewable energy sources has been particularly notable in recent times, including different ways in which randomization is considered, their hybridization with other modeling techniques and/or their multi-layered (deep) and ensemble arrangement. This manuscript comprehensively reviews the most important features of randomization-based machine learning methods, and critically examines recent evidences of their application to renewable energy prediction problems, focusing on those related to solar, wind, marine/ocean and hydro-power renewable sources. Our study of the literature is complemented by an extensive experimental setup encompassing three real-world problems dealing with solar radiation prediction, wind speed prediction in wind farms and hydro-power energy. In all these problems randomization-based methods are reported to achieve a better predictive performance than their corresponding state-of-the-art solutions, while demanding a dramatically lower computational effort for its learning phases. Finally, we pause and reflect on important challenges faced by these methods when applied to renewable energy prediction problems, such as their intrinsic epistemic uncertainty, or the need for explainability. We also point out several research opportunities that arise from this vibrant research area.

Evolutionary computation has largely exhibited its potential to complement conventional learning algorithms in a variety of machine learning tasks, especially those related to unsupervised (clustering) and supervised learning. It has not been until lately when the computational efficiency of evolutionary solvers has been put in prospective for training reinforcement learning models. However, most studies framed so far within this context have considered environments and tasks conceived in isolation, without any exchange of knowledge among related tasks. In this manuscript we present A-MFEA-RL, an adaptive version of the well-known MFEA algorithm whose search and inheritance operators are tailored for multitask reinforcement learning environments. Specifically, our approach includes crossover and inheritance mechanisms for refining the exchange of genetic material, which rely on the multilayered structure of modern deep-learning-based reinforcement learning models. In order to assess the performance of the proposed approach, we design an extensive experimental setup comprising multiple reinforcement learning environments of varying levels of complexity, over which the performance of A-MFEA-RL is compared to that furnished by alternative nonevolutionary multitask reinforcement learning approaches. As concluded from the discussion of the obtained results, A-MFEA-RL not only achieves competitive success rates over the simultaneously addressed tasks, but also fosters the exchange of knowledge among tasks that could be intuitively expected to keep a degree of synergistic relationship.

Persistence is an important characteristic of many complex systems in nature, related to how long the system remains at a certain state before changing to a different one. The study of complex systems' persistence involves different definitions and uses different techniques, depending on whether short-term or long-term persistence is considered. In this paper we discuss the most important definitions, concepts, methods, literature and latest results on persistence in complex systems. Firstly, the most used definitions of persistence in short-term and long-term cases are presented. The most relevant methods to characterize persistence are then discussed in both cases. A complete literature review is also carried out. We also present and discuss some relevant results on persistence, and give empirical evidence of performance in different detailed case studies, for both short-term and long-term persistence. A perspective on the future of persistence concludes the work.

Synthetic digital twins based on medical data accelerate the acquisition, labelling and decision making procedure in digital healthcare. A core part of digital healthcare twins is model-based data synthesis, which permits the generation of realistic medical signals without requiring to cope with the modelling complexity of anatomical and biochemical phenomena producing them in reality. Unfortunately, algorithms for cardiac data synthesis have been so far scarcely studied in the literature. An important imaging modality in the cardiac examination is three-directional CINE multi-slice myocardial velocity mapping (3Dir MVM), which provides a quantitative assessment of cardiac motion in three orthogonal directions of the left ventricle. The long acquisition time and complex acquisition produce make it more urgent to produce synthetic digital twins of this imaging modality. In this study, we propose a hybrid deep learning (HDL) network, especially for synthetic 3Dir MVM data. Our algorithm is featured by a hybrid UNet and a Generative Adversarial Network with a foreground-background generation scheme. The experimental results show that from temporally down-sampled magnitude CINE images (six times), our proposed algorithm can still successfully synthesise high temporal resolution 3Dir MVM CMR data (PSNR=42.32) with precise left ventricle segmentation (DICE=0.92). These performance scores indicate that our proposed HDL algorithm can be implemented in real-world digital twins for myocardial velocity mapping data simulation. To the best of our knowledge, this work is the first one investigating digital twins of the 3Dir MVM CMR, which has shown great potential for improving the efficiency of clinical studies via synthesised cardiac data.

This paper proposes a novel multimodal self-supervised architecture for energy-efficient audio-visual (AV) speech enhancement that integrates Graph Neural Networks with canonical correlation analysis (CCA-GNN). The proposed approach lays its foundations on a state-of-the-art CCA-GNN that learns representative embeddings by maximizing the correlation between pairs of augmented views of the same input while decorrelating disconnected features. The key idea of the conventional CCA-GNN involves discarding augmentation-variant information and preserving augmentation-invariant information while preventing capturing of redundant information. Our proposed AV CCA-GNN model deals with multimodal representation learning context. Specifically, our model improves contextual AV speech processing by maximizing canonical correlation from augmented views of the same channel and canonical correlation from audio and visual embeddings. In addition, it proposes a positional node encoding that considers a prior-frame sequence distance instead of a feature-space representation when computing the node’s nearest neighbors, introducing temporal information in the embeddings through the neighborhood’s connectivity. Experiments conducted on the benchmark ChiME3 dataset show that our proposed prior frame-based AV CCA-GNN ensures a better feature learning in the temporal context, leading to more energy-efficient speech reconstruction than state-of-the-art CCA-GNN and multilayer perceptron.

In recent years, Deep Learning models have shown a great performance in complex optimization problems. They generally require large training datasets, which is a limitation in most practical cases. Transfer learning allows importing the first layers of a pre-trained architecture and connecting them to fully-connected layers to adapt them to a new problem. Consequently, the configuration of the these layers becomes crucial for the performance of the model. Unfortunately, the optimization of these models is usually a computationally demanding task. One strategy to optimize Deep Learning models is the pruning scheme. Pruning methods are focused on reducing the complexity of the network, assuming an expected performance penalty of the model once pruned. However, the pruning could potentially be used to improve the performance, using an optimization algorithm to identify and eventually remove unnecessary connections among neurons. This work proposes EvoPruneDeepTL, an evolutionary pruning model for Transfer Learning based Deep Neural Networks which replaces the last fully-connected layers with sparse layers optimized by a genetic algorithm. Depending on its solution encoding strategy, our proposed model can either perform optimized pruning or feature selection over the densely connected part of the neural network. We carry out different experiments with several datasets to assess the benefits of our proposal. Results show the contribution of EvoPruneDeepTL and feature selection to the overall computational efficiency of the network as a result of the optimization process. In particular, the accuracy is improved, reducing at the same time the number of active neurons in the final layers.

In the era of sustainable smart agriculture, a vast amount of agricultural news text is posted online, accumulating significant agricultural knowledge. To efficiently access this knowledge, effective text classification techniques are urgently needed. Deep learning approaches, such as fine-tuning strategies on pre-trained language models (PLMs), have shown remarkable performance gains. Nonetheless, these methods face several complex challenges, including limited agricultural training data, poor domain transferability (especially across languages), and complex and expensive deployment of large models. Inspired by the success of recent ChatGPT models (e.g., GPT-3.5, GPT-4), this work explores the potential of applying ChatGPT in the field of agricultural informatization. Various crucial factors, such as prompt construction, answer parsing, and different ChatGPT variants, are thoroughly investigated to maximize its capabilities. A preliminary comparative study is conducted, comparing ChatGPT with PLMs-based fine-tuning methods and PLMs-based prompt-tuning methods. Empirical results demonstrate that ChatGPT effectively addresses the mentioned research challenges and bottlenecks, making it an ideal solution for agricultural text classification. Moreover, ChatGPT achieves comparable performance to existing PLM-based fine-tuning methods, even without fine-tuning on agricultural data samples. We hope this preliminary study could inspire the emergence of a general-purpose AI paradigm for agricultural text processing.

The upheaval brought by the arrival of the COVID-19 pandemic has continued to bring fresh challenges over the past two years. During this COVID-19 pandemic, there has been a need for rapid identification of infected patients and specific delineation of infection areas in computed tomography (CT) images. Although deep supervised learning methods have been established quickly, the scarcity of both image-level and pixel-level labels as well as the lack of explainable transparency still hinder the applicability of AI. Can we identify infected patients and delineate the infections with extreme minimal supervision? Semi-supervised learning has demonstrated promising performance under limited labelled data and sufficient unlabelled data. Inspired by semi-supervised learning, we propose a model-agnostic calibrated pseudo-labelling strategy and apply it under a consistency regularization framework to generate explainable identification and delineation results. We demonstrate the effectiveness of our model with the combination of limited labelled data and sufficient unlabelled data or weakly-labelled data. Extensive experiments have shown that our model can efficiently utilize limited labelled data and provide explainable classification and segmentation results for decision-making in clinical routine.

In this paper, three customised Artificial Intelligence (AI) frameworks, considering Deep Learning, Machine Learning (ML) algorithms and data reduction techniques, are proposed for a problem of long-term summer air temperature prediction. Specifically, the prediction of the average air temperature in the first and second August fortnights, using input data from previous months, at two different locations (Paris, France) and (Córdoba, Spain), is considered. The target variable, mainly in the first August fortnight, can contain signals of extreme events such as heatwaves, like the heatwave of 2003, which affected France and the Iberian Peninsula. Three different computational frameworks for air temperature prediction are proposed: a Convolutional Neural Network (CNN), with video-to-image translation, several ML approaches including Lasso regression, Decision Trees and Random Forest, and finally a CNN with pre-processing step using Recurrence Plots, which convert time series into images. Using these frameworks, a very good prediction skill has been obtained in both Paris and Córdoba regions, showing that the proposed approaches can be an excellent option for seasonal climate prediction problems.

Deep neural networks (DNNs) are currently being deployed as machine learning technology in a wide range of important real-world applications. DNNs consist of a huge number of parameters that require millions of floating-point operations (FLOPs) to be executed both in learning and prediction modes. A more effective method is to implement DNNs in a cloud computing system equipped with centralized servers and data storage sub-systems with high-speed and high-performance computing capabilities. This paper presents an up-to-date survey on current state-of-the-art deployed DNNs for cloud computing. Various DNN complexities associated with different architectures are presented and discussed alongside the necessities of using cloud computing. We also present an extensive overview of different cloud computing platforms for the deployment of DNNs and discuss them in detail. Moreover, DNN applications already deployed in cloud computing systems are reviewed to demonstrate the advantages of using cloud computing for DNNs. The paper emphasizes the challenges of deploying DNNs in cloud computing systems and provides guidance on enhancing current and new deployments.

Most existing works on cardiac echocardiography segmentation require a large number of ground-truth labels to appropriately train a neural network; this, however, is time consuming and laborious for physicians. Self-supervision learning is one of the potential solutions to address this challenge by deeply exploiting the raw data. However, existing works mainly exploit single type/level of pretext task. In this work, we propose fusion of the multi-level and multi-type self-generated knowledge. We obtain multi-level information of sub-anatomical structures in ultrasound images via a superpixel method. Subsequently, we fuse various types of information generated through multi-types of pretext tasks. In the end, we transfer the learned knowledge to our downstream task. In the experimental studies, we have demonstrated the prove the effectiveness of this method through the cardiac ultrasound segmentation task. The results show that the performance of our proposed method for echocardiography segmentation matches the performance of fully supervised methods without requiring a high amount of labeled data.

This paper introduces a new hybrid bio-inspired solver which combines elements from the recently proposed Coral Reefs Optimization (CRO) algorithm with operators from the Harmony Search (HS) approach, which gives rise to the coined CRO-HS optimization technique. Specifically, this novel bio-inspired optimizer is utilized in the context of short-term wind speed prediction as a means to obtain the best set of meteorological variables to be input to a neural Extreme Learning Machine (ELM) network. The paper elaborates on the main characteristics of the proposed scheme and discusses its performance when predicting the wind speed based on the measures of two meteorological towers located in USA and Spain. The good results obtained in these experiments when compared to naïve versions of the CRO and HS algorithms are promising and pave the way towards the utilization of the derived hybrid solver in other optimization problems arising from diverse disciplines.

Nowadays huge volumes of data are produced in the form of fast streams, which are further affected by non-stationary phenomena. The resulting lack of stationarity in the distribution of the produced data calls for efficient and scalable algorithms for online analysis capable of adapting to such changes (concept drift). The online learning field has lately turned its focus on this challenging scenario, by designing incremental learning algorithms that avoid becoming obsolete after a concept drift occurs. Despite the noted activity in the literature, a need for new efficient and scalable algorithms that adapt to the drift still prevails as a research topic deserving further effort. Surprisingly, Spiking Neural Networks, one of the major exponents of the third generation of artificial neural networks, have not been thoroughly studied as an online learning approach, even though they are naturally suited to easily and quickly adapting to changing environments. This work covers this research gap by adapting Spiking Neural Networks to meet the processing requirements that online learning scenarios impose. In particular the work focuses on limiting the size of the neuron repository and making the most of this limited size by resorting to data reduction techniques. Experiments with synthetic and real data sets are discussed, leading to the empirically validated assertion that, by virtue of a tailored exploitation of the neuron repository, Spiking Neural Networks adapt better to drifts, obtaining higher accuracy scores than naive versions of Spiking Neural Networks for online learning environments.

Detecting groups within a set of interconnected nodes is a widely addressed problem that can model a diversity of applications. Unfortunately, detecting the optimal partition of a network is a computationally demanding task, usually conducted by means of optimization methods. Among them, randomized search heuristics have been proven to be efficient approaches. This manuscript is devoted to providing an overview of community detection problems from the perspective of bio-inspired computation. To this end, we first review the recent history of this research area, placing emphasis on milestone studies contributed in the last five years. Next, we present an extensive experimental study to assess the performance of a selection of modern heuristics over weighted directed network instances. Specifically, we combine seven global search heuristics based on two different similarity metrics and eight heterogeneous search operators designed ad-hoc. We compare our methods with six different community detection techniques over a benchmark of 17 Lancichinetti–Fortunato–Radicchi network instances. Ranking statistics of the tested algorithms reveal that the proposed methods perform competitively, but the high variability of the rankings leads to the main conclusion: no clear winner can be declared. This finding aligns with community detection tools available in the literature that hinge on a sequential application of different algorithms in search for the best performing counterpart. We end our research by sharing our envisioned status of this area, for which we identify challenges and opportunities which should stimulate research efforts in years to come.

This paper capitalizes on the increasingly high relevance gained by data-intensive technologies in the development of intelligent transportation system, which calls for the progressive adoption of adaptive, self-learning methods for solving modeling, simulation, and optimization problems. In this regard, certain mechanisms and processes observed in nature, including the animal brain, have proved themselves to excel not only in terms of efficiently capturing time-evolving stimuli, but also at undertaking complex tasks by virtue of mechanisms that can be extrapolated to computer algorithms and methods. This paper comprehensively reviews the state-of-the-art around the application of bioinspired methods to the challenges arising in the broad field of intelligent transportation system (ITS). This systematic survey is complemented by an initiatory taxonomic introduction to bioinspired computational intelligence, along with the basics of its constituent techniques. A focus is placed on which research niches are still unexplored by the community in different ITS subareas. The open issues and research directions for the practical implementation of ITS endowed with bioinspired computational intelligence are also discussed in detail.

Smart grids are a type of complex cyber–physical system (CPS) that integrates the communication capabilities of smart devices into the grid to facilitate remote operation and control of power systems. However, this integration exposes many existing vulnerabilities of conventional supervisory control and data acquisition (SCADA) systems, resulting in severe cyber threats to the smart grid and potential violation of security objectives. Stealing sensitive information, modifying firmware, or injecting function codes through compromised devices are examples of possible attacks on the smart grid. Therefore, early detection of cyberattacks on the grid is crucial to protect it from sabotage. Machine learning (ML) methods are conventional approaches for detecting cyberattacks that use features of smart grid networks. However, developing an effective, highly accurate detection method with reduced computational overload, is still a challenging research problem. In this work, an efficient and effective security control approach is proposed to detect cyberattacks on the smart grid. The proposed approach combines both feature reduction and detection techniques to reduce the extremely large number of features and achieve an improved detection rate. A correlation-based feature selection (CFS) method is used to remove irrelevant features, improving detection efficiency. An instance-based learning (IBL) algorithm classifies normal and cyberattack events using the selected optimal features. This study describes a set of experiments conducted on public datasets from a SCADA power system based on a 10-fold cross-validation technique. Experimental results show that the proposed approach achieves a high detection rate based on a small number of features drawn from SCADA power system measurements.

Borehole resistivity measurements are routinely employed to measure the electrical properties of rocks penetrated by a well and to quantify the hydrocarbon pore volume of a reservoir. Depending on the degree of geometrical complexity, inversion techniques are often used to estimate layer-by-layer electrical properties from measurements. When used for well geosteering purposes, it becomes essential to invert the measurements into layer-by-layer values of electrical resistivity in real time. We explore the possibility of using deep neural networks (DNNs) to perform rapid inversion of borehole resistivity measurements. Accordingly, we construct a DNN that approximates the following inverse problem: given a set of borehole resistivity measurements, the DNN is designed to deliver a physically reliable and data-consistent piecewise one-dimensional layered model of the surrounding subsurface. Once the DNN is constructed, we can invert borehole measurements in real time. We illustrate the performance of the DNN for inverting logging-while-drilling (LWD) measurements acquired in high-angle wells via synthetic examples. Numerical results are promising, although further work is needed to achieve the accuracy and reliability required by petrophysicists and drillers.

Most of state of the art methods applied on time series consist of deep learning methods that are too complex to be interpreted. This lack of interpretability is a major drawback, as several applications in the real world are critical tasks, such as the medical field or the autonomous driving field. The explainability of models applied on time series has not gather much attention compared to the computer vision or the natural language processing fields. In this paper, we present an overview of existing explainable AI (XAI) methods applied on time series and illustrate the type of explanations they produce. We also provide a reflection on the impact of these explanation methods to provide confidence and trust in the AI systems.

This research work presents a detailed survey about Computational Intelligence (CI) applied to various Hotel and Travel Industry areas. Currently, the hospitality industry’s interest in data science is growing exponentially because of their expected margin of profit growth. In order to provide precise state of the art content, this survey analyzes more than 160 research works from which a detailed categorization and taxonomy have been produced. We have studied the different approaches on the various forecasting methods and subareas where CI is currently being used. This research work also shows an actual distribution of these research efforts in order to enhance the understanding of the reader about this topic and to highlight unexploited research niches. A set of guidelines and recommendations for future research areas and promising applications are also presented in a final section.

Scene understanding plays a crucial role in autonomous driving by utilizing sensory data for contextual information extraction and decision making. Beyond modeling advances, the enabler for vehicles to become aware of their surroundings is the availability of visual sensory data, which expand the vehicular perception and realizes vehicular contextual awareness in real-world environments. Research directions for scene understanding pursued by related studies include person/vehicle detection and segmentation, their transition analysis, lane change, and turns detection, among many others. Unfortunately, these tasks seem insufficient to completely develop fully-autonomous vehicles i.e., achieving level-5 autonomy, travelling just like human-controlled cars. This latter statement is among the conclusions drawn from this review paper: scene understanding for autonomous driving cars using vision sensors still requires significant improvements. With this motivation, this survey defines, analyzes, and reviews the current achievements of the scene understanding research area that mostly rely on computationally complex deep learning models. Furthermore, it covers the generic scene understanding pipeline, investigates the performance reported by the state-of-the-art, informs about the time complexity analysis of avant garde modeling choices, and highlights major triumphs and noted limitations encountered by current research efforts. The survey also includes a comprehensive discussion on the available datasets, and the challenges that, even if lately confronted by researchers, still remain open to date. Finally, our work outlines future research directions to welcome researchers and practitioners to this exciting domain.

In recent years, the application of artificial intelligence has been revolutionizing the manufacturing industry, becoming one of the key pillars of what has been called Industry 4.0. In this context, we focus on the job shop scheduling problem (JSP), which aims at productions orders to be carried out, but considering the reduction of energy consumption as a key objective to fulfill. Finding the best combination of machines and jobs to be performed is not a trivial problem and becomes even more involved when several objectives are taken into account. Among them, the improvement of energy savings may conflict with other objectives, such as the minimization of the makespan. In this paper, we provide an in-depth review of the existing literature on multi-objective job shop scheduling optimization with metaheuristics, in which one of the objectives is the minimization of energy consumption. We systematically reviewed and critically analyzed the most relevant features of both problem formulations and algorithms to solve them effectively. The manuscript also informs with empirical results the main findings of our bibliographic critique with a performance comparison among representative multi-objective evolutionary solvers applied to a diversity of synthetic test instances. The ultimate goal of this article is to carry out a critical analysis, finding good practices and opportunities for further improvement that stem from current knowledge in this vibrant research area.

The COVID19 pandemic has impacted the global economy, social activities, and Electricity Consumption (EC), affecting the performance of historical data-based Electricity Load Forecasting (ELF) algorithms. This study thoroughly analyses the pandemic's impact on these models and develop a hybrid model with better prediction accuracy using COVID19 data. Existing datasets are reviewed, and their limited generalization potential for the COVID19 period is highlighted. A dataset of 96 residential customers, comprising 36 and six months before and after the pandemic, is collected, posing significant challenges for current models. The proposed model employs convolutional layers for feature extraction, gated recurrent nets for temporal feature learning, and a self-attention module for feature selection, leading to better generalization for predicting EC patterns. Our proposed model outperforms existing models, as demonstrated by a detailed ablation study using our dataset. For instance, it achieves an average reduction of 0.56% & 3.46% in MSE, 1.5% & 5.07% in RMSE, and 11.81% & 13.19% in MAPE over the pre- and post-pandemic data, respectively. However, further research is required to address the varied nature of the data. These findings have significant implications for improving ELF algorithms during pandemics and other significant events that disrupt historical data patterns.

Machine learning methods are extensively used for processing and analysing speech signals by virtue of their performance gains over multiple domains. Deep learning and ensemble learning are the two most commonly used techniques, which results in benchmark performance across different downstream tasks. Ensemble deep learning is a recent development which combines these two techniques to result in a robust architecture having substantial performance gains, as well as better generalization performance over the individual techniques. In this paper, we extensively review the use of ensemble deep learning methods for different speech signal related tasks, ranging from general objectives such as automatic speech recognition and voice activity detection, to more specific areas such as biomedical applications involving the detection of pathological speech or music genre detection. We provide a discussion on the use of different ensemble strategies such as bagging, boosting and stacking in the context of speech signals, and identify the various salient features and advantages from a broader perspective when coupled with deep learning architectures. The main objective of this study is to comprehensively evaluate existing works in the area of ensemble deep learning, and highlight the future directions that may be explored to further develop it as a tool for several speech related tasks. To the best of our knowledge, this is the first review study which primarily focuses on ensemble deep learning for speech applications. This study aims to serve as a valuable resource for researchers in academia and in industry working with speech signals, supporting advanced novel applications of ensemble deep learning models towards solving challenges in existing speech processing systems.

Wireless capsule endoscopy (WCE) is a revolutionary diagnostic method for small bowel pathology. The manual perusal of the resulting lengthy and redundant videos is cumbersome. Automated analysis of WCE video frames is an intricate data modeling task because of the diverse representations of anomalies caused by inappropriate capture conditions. Deep neural networks require training to learn diverse pathological manifestations utilizing heterogeneous data collected from multiple institutions. However, the accessibility of WCE data poses privacy concerns for multiple centers. The efficient learning of heterogeneous data distributed over multiple institutions in a privacy-preserving fashion has become a challenge hampering the adoption of AI-based diagnoses in clinical practice. Prior studies have contrived extensive data augmentation and the generation of synthetic images from the same center. However, models trained at one center are at risk of a lack of generalization for a global deployment. Federated learning (FL) is a novel paradigm in which models learn from distributed data and share knowledge without accessing the data themselves. This study proposes an FL framework for multiple anomaly classifications of WCE frames, elaborating on the potential of collaborative learning from multiple data centers on the edge. Our empirical results prove that the proposed decentralized approach can learn the generalized features of WCE frames. Validating heterogeneous test sets revealed a 10–12% improvement in performance for decentralized models based on FL compared to the best-case performance of centralized models, demonstrating the potential of the federated framework to support multiple anomaly classification of WCE frames while preserving data privacy across various clinical setups.

Most applications of Artificial Intelligence (AI) are designed for a confined and specific task. However, there are many scenarios that call for a more general AI, capable of solving a wide array of tasks without being specifically designed for them. The term General Purpose Artificial Intelligence Systems (GPAIS) has been defined to refer to these AI systems. To date, the possibility of an Artificial General Intelligence, powerful enough to perform any intellectual task as if it were human, or even improve it, has remained an aspiration, fiction, and considered a risk for our society. Whilst we might still be far from achieving that, GPAIS is a reality and sitting at the forefront of AI research. This work discusses existing definitions for GPAIS and proposes a new definition that allows for a gradual differentiation among types of GPAIS according to their properties and limitations. We distinguish between closed-world and open-world GPAIS, characterising their degree of autonomy and ability based on several factors such as adaptation to new tasks, competence in domains not intentionally trained for, ability to learn from few data, or proactive acknowledgement of their own limitations. We then propose a taxonomy of approaches to realise GPAIS, describing research trends such as the use of AI techniques to improve another AI (commonly referred to as AI-powered AI) or (single) foundation models. As a prime example, we delve into generative AI (GenAI), aligning them with the terms and concepts presented in the taxonomy. Similarly, we explore the challenges and prospects of multi-modality, which involves fusing various types of data sources to expand the capabilities of GPAIS. Through the proposed definition and taxonomy, our aim is to facilitate research collaboration across different areas that are tackling general purpose tasks, as they share many common aspects. Finally, with the goal of providing a holistic view of GPAIS, we discuss the current state of GPAIS, its prospects, implications for our society, and the need for regulation and governance of GPAIS to ensure their responsible and trustworthy development.

This paper presents a novel multi-objective heuristic approach for the efficient distribution of 24-h emergency units. This paradigm is essentially a facility location problem that involves determining the optimum locations, within the existing health care centers, where to deploy 24-h emergency resources, as well as an efficient assignment of patients to such newly placed resources through the existing medical care infrastructure. The formulation of the underlying NP-complete problem is based on a bi-objective distance and cost metric, which is tackled in our approach by combining a Harmony Search algorithm with a grouping encoding and a non-dominated solution sorting strategy. Additionally, the nominal grouping encoding procedure has been redefined in order to reduce the dimension of the search space, thus allowing for a higher efficiency of the searching process. Extensive simulations in a real scenario – based on the geographic location of medical centers over the provinces of Guadalajara and Cuenca (Spain) – show that the proposed algorithm is statistically robust and provides a wide range of feasible solutions, hence offering multiple alternatives for the distribution of emergency units.

In the last years multiple Internet of Things (IoT) solutions have been developed to detect, track, count, and identify human activity from people that do not carry any device nor participate actively in the detection process. When WiFi radio receivers are employed as sensors for device-free human activity recognition, channel quality measurements are preprocessed in order to extract predictive features toward performing the desired activity recognition via machine learning (ML) models. Despite the variety of predictors in the literature, there is no universally outperforming set of features for all scenarios and applications. However, certain feature combinations could achieve a better average detection performance compared to the use of a thorough feature portfolio. Such predictors are often obtained by feature engineering and selection techniques applied before the learning process. This manuscript elaborates on the feature engineering and selection methodology for counting device-free people by solely resorting to the fluctuation and variation of WiFi signals exchanged by IoT devices. We comprehensively review the feature engineering and ML models employed in the literature from a critical perspective, identifying trends, research niches, and open challenges. Furthermore, we present and provide the community with a new open database with WiFi measurements in several indoor environments (i.e., rooms, corridors, and stairs) where up to five people can be detected. This dataset is used to exhaustively assess the performance of different ML models with and without feature selection, from which insightful conclusions are drawn regarding the predictive potential of different predictors across scenarios of diverse characteristics.

Novelty search is a tool in evolutionary and swarm robotics for maintaining the diversity of population needed for continuous robotic operation. It enables nature-inspired algorithms to evaluate solutions on the basis of the distance to their k-nearest neighbors in the search space. Besides this, the fitness function represents an additional measure for evaluating the solution, with the purpose of preserving the so-named novelty solutions into the next generation. In this study, a differential evolution was hybridized with novelty search. The differential evolution is a well-known algorithm for global optimization, which is applied to improve the results obtained by the other solvers on the CEC-14 benchmark function suite. Furthermore, functions of different dimensions were taken into consideration, and the influence of the various novelty search parameters was analyzed. The results of experiments show a great potential for using novelty search in global optimization.

Wireless Capsule Endoscopy (WCE) is a patient-friendly approach for digestive tract monitoring to support medical experts towards identifying any anomaly inside human’s Gastrointestinal (GI) tract. The automatic recognition of such type of abnormalities is essential for early diagnosis and time saving. To this end, several computer aided diagnosis (CAD) methods have been proposed in the literature for automatic abnormal region segmentation, summarization, classification, and personalization in WCE videos. In this work, we provide a detailed review of computer vision-based methods for WCE videos analysis. Firstly, all the major domains of WCE video analytics with their generic flow are identified. Secondly, we comprehensively review WCE video analysis methods and surveys with their pros and cons presented to date. In addition, this paper reviews several representative public datasets used for the performance assessment of WCE techniques and methods. Finally, the most important aspect of this survey is the identification of several research trends and open issues in different domains of WCE, with an emphasis placed on future research directions towards smarter healthcare and personalization.

Abstract The traveling salesman problem (TSP) is one of the most studied problems in computational intelligence and operations research. Since its first formulation, a myriad of works has been published proposing different alternatives for its solution. Additionally, a plethora of advanced formulations have also been proposed by the related practitioners, trying to enhance the applicability of the basic TSP. This chapter is firstly devoted to providing an informed overview on the TSP. For this reason, we first review the recent history of this research area, placing emphasis on milestone studies contributed in recent years. Next, we aim at making a step forward in the field proposing an experimentation hybridizing three different reputed bio-inspired computational metaheuristics (namely, particle swarm optimization, the firefly algorithm, and the bat algorithm) and the novelty search mechanism. For assessing the quality of the implemented methods, 15 different datasets taken from the well-known TSPLIB have been used. We end this chapter by sharing our envisioned status of the field, for which we identify opportunities and challenges which should stimulate research efforts in years to come.

Multiview video summarization (MVS) has not received much attention from the research community due to inter-view correlations and views' overlapping, etc. The majority of previous MVS works are offline, relying on only summary, and require additional communication bandwidth and transmission time, with no focus on foggy environments. We propose an edge intelligence-based MVS and activity recognition framework that combines artificial intelligence with Internet of Things (IoT) devices. In our framework, resource-constrained devices with cameras use a lightweight CNN-based object detection model to segment multiview videos into shots, followed by mutual information computation that helps in a summary generation. Our system does not rely solely on a summary, but encodes and transmits it to a master device using a neural computing stick for inter-view correlations computation and efficient activity recognition, an approach which saves computation resources, communication bandwidth, and transmission time. Experiments show an increase of 0.4 unit in F-measure on an MVS Office dateset and 0.2% and 2% improved accuracy for UCF-50 and YouTube 11 datesets, respectively, with lower storage and transmission times. The processing time is reduced from 1.23 to 0.45 s for a single frame and optimally 0.75 seconds faster MVS. A new dateset is constructed by synthetically adding fog to an MVS dateset to show the adaptability of our system for both certain and uncertain IoT surveillance environments.

Abstract Deep learning (DL) is a numerical method that approximates functions. Recently, its use has become attractive for the simulation and inversion of multiple problems in computational mechanics, including the inversion of borehole logging measurements for oil and gas applications. In this context, DL methods exhibit two key attractive features: (a) once trained, they enable to solve an inverse problem in a fraction of a second, which is convenient for borehole geosteering operations as well as in other real‐time inversion applications. (b) DL methods exhibit a superior capability for approximating highly complex functions across different areas of knowledge. Nevertheless, as it occurs with most numerical methods, DL also relies on expert design decisions that are problem specific to achieve reliable and robust results. Herein, we investigate two key aspects of deep neural networks (DNNs) when applied to the inversion of borehole resistivity measurements: error control and adequate selection of the loss function. As we illustrate via theoretical considerations and extensive numerical experiments, these interrelated aspects are critical to recover accurate inversion results.

In general, artery-specific calcification analysis comprises the simultaneous calcification segmentation and quantification tasks. It can help provide a thorough assessment for calcification of different coronary arteries, and further allow for an efficient and rapid diagnosis of cardiovascular diseases (CVD). However, as a high-dimensional multi-type estimation problem, artery-specific calcification analysis has not been profoundly investigated due to the intractability of obtaining discriminative feature representations. In this work, we propose a Multi-task learning network with Multi-view Weighted Fusion Attention (MMWFAnet) to solve this challenging problem. The MMWFAnet first employs a Multi-view Weighted Fusion Attention (MWFA) module to extract discriminative feature representations by enhancing the collaboration of multiple views. Specifically, MWFA weights these views to improve multi-view learning for calcification features. Based on the fusion of these multiple views, the proposed approach takes advantage of multi-task learning to obtain accurate segmentation and quantification of artery-specific calcification simultaneously. We perform experimental studies on 676 non-contrast Computed Tomography scans, achieving state-of-the-art performance in terms of multiple evaluation metrics. These compelling results evince that the proposed MMWFAnet is capable of improving the effectivity and efficiency of clinical CVD diagnosis.

Advances in Data Science permeate every field of Transportation Science and Engineering, resulting in developments in the transportation sector that are data-driven. Nowadays, Intelligent Transportation Systems (ITS) could be arguably approached as a "story" intensively producing and consuming large amounts of data. A diversity of sensing devices densely spread over the infrastructure, vehicles or the travelers' personal devices act as sources of data flows that are eventually fed into software running on automatic devices, actuators or control systems producing, in turn, complex information flows among users, traffic managers, data analysts, traffic modeling scientists, etc. These information flows provide enormous opportunities to improve model development and decision-making. This work aims to describe how data, coming from diverse ITS sources, can be used to learn and adapt data-driven models for efficiently operating ITS assets, systems and processes; in other words, for data-based models to fully become actionable. Grounded in this described data modeling pipeline for ITS, we define the characteristics, engineering requisites and challenges intrinsic to its three compounding stages, namely, data fusion, adaptive learning and model evaluation. We deliberately generalize model learning to be adaptive, since, in the core of our paper is the firm conviction that most learners will have to adapt to the ever-changing phenomenon scenario underlying the majority of ITS applications. Finally, we provide a prospect of current research lines within Data Science that can bring notable advances to data-based ITS modeling, which will eventually bridge the gap towards the practicality and actionability of such models.

• An adaptive and transfer guided metaheuristic is proposed for Evolutionary Multitasking. • Synergies between tasks are analyzed along the search in a dynamic way. • 4 different combinatorial optimization problems have been considered. • 11 multitasking scenarios are solved comprised by 5 to 20 instances. • Proposed AT-MFCGA is compared with MFEA, MFEA-II and MFCGA. Transfer Optimization is an incipient research area dedicated to solving multiple optimization tasks simultaneously. Among the different approaches that can address this problem effectively, Evolutionary Multitasking resorts to concepts from Evolutionary Computation to solve multiple problems within a single search process. In this paper we introduce a novel adaptive metaheuristic algorithm to deal with Evolutionary Multitasking environments coined as Adaptive Transfer-guided Multifactorial Cellular Genetic Algorithm (AT-MFCGA). AT-MFCGA relies on cellular automata to implement mechanisms in order to exchange knowledge among the optimization problems under consideration. Furthermore, our approach is able to explain by itself the synergies among tasks that were encountered and exploited during the search, which helps us to understand interactions between related optimization tasks. A comprehensive experimental setup is designed to assess and compare the performance of AT-MFCGA to that of other renowned Evolutionary Multitasking alternatives (MFEA and MFEA-II). Experiments comprise 11 multitasking scenarios composed of 20 instances of 4 combinatorial optimization problems, yielding the largest discrete multitasking environment solved to date. Results are conclusive in regard to the superior quality of solutions provided by AT-MFCGA with respect to the rest of the methods, which are complemented by a quantitative examination of the genetic transferability among tasks throughout the search process.

Dynamic CT angiography derived from CT perfusion data can obviate a separate coronary CT angiography and the use of ionizing radiation and contrast agent, thereby enhancing patient safety. However, the image quality of dynamic CT angiography is inferior to standard CT angiography images in many studies. This paper proposes an explainable generative adversarial network named vessel-GAN, which resorts to explainable knowledge-based artificial intelligence to perform image translation with increased trustworthiness. Specifically, we design a loss term to better learn the representations of blood vessels in CT angiography images. The loss term based on expert knowledge guides the generator to focus its training on the important features predicted by the discriminator. Additionally, we propose a generator architecture that effectively fuses spatio-temporal representations and further enhances temporal consistency, thereby improving the quality of the generated CT angiography images. The experiment is conducted on a dataset consisting of 232 patients with suspected coronary artery stenosis. Experimental results show that the PSNR value of vessel-GAN is 28.32 dB, SSIM value is 0.91 and MAE value is 47.36. To validate the effectiveness of the proposed synthesis method, we compare that with other image translation frameworks and GAN-based methods. Compared to other image translation methods, the proposed method vessel-GAN can generate more clearly visible blood vessels from source perfusion images. The CTA images generated by vessel-GAN are closer to the real CTA due to the use of adversarial learning. Compared with other GAN-based methods, vessel-GAN can produce sharper and more homogeneous outputs, including realistic vascular structures. The experiment demonstrates that the explainable generative adversarial network has superior performance for it can better control how models learn. Overall, the CT angiography images generated by vessel-GAN can potentially replace a separate standard CT angiography, allowing the possibility of “one-stop” cardiac examination for high-risk coronary artery disease patients who need assessment of myocardial ischemia.

Abstract Extremism has grown as a global problem for society in recent years, especially after the apparition of movements such as jihadism. This and other extremist groups have taken advantage of different approaches, such as the use of Social Media, to spread their ideology, promote their acts and recruit followers. The extremist discourse, therefore, is reflected on the language used by these groups. Natural language processing (NLP) provides a way of detecting this type of content, and several authors make use of it to describe and discriminate the discourse held by these groups, with the final objective of detecting and preventing its spread. Following this approach, this survey aims to review the contributions of NLP to the field of extremism research, providing the reader with a comprehensive picture of the state of the art of this research area. The content includes a first conceptualization of the term extremism, the elements that compose an extremist discourse and the differences with other terms. After that, a review description and comparison of the frequently used NLP techniques is presented, including how they were applied, the insights they provided, the most frequently used NLP software tools, descriptive and classification applications, and the availability of datasets and data sources for research. Finally, research questions are approached and answered with highlights from the review, while future trends, challenges and directions derived from these highlights are suggested towards stimulating further research in this exciting research area.

Abstract Automated segmentation of multiple organs and tumors from 3D medical images such as magnetic resonance imaging (MRI) and computed tomography (CT) scans using deep learning methods can aid in diagnosing and treating cancer. However, organs often overlap and are complexly connected, characterized by extensive anatomical variation and low contrast. In addition, the diversity of tumor shape, location, and appearance, coupled with the dominance of background voxels, makes accurate 3D medical image segmentation difficult. In this paper, a novel 3D large-kernel (LK) attention module is proposed to address these problems to achieve accurate multi-organ segmentation and tumor segmentation. The advantages of biologically inspired self-attention and convolution are combined in the proposed LK attention module, including local contextual information, long-range dependencies, and channel adaptation. The module also decomposes the LK convolution to optimize the computational cost and can be easily incorporated into CNNs such as U-Net. Comprehensive ablation experiments demonstrated the feasibility of convolutional decomposition and explored the most efficient and effective network design. Among them, the best Mid-type 3D LK attention-based U-Net network was evaluated on CT-ORG and BraTS 2020 datasets, achieving state-of-the-art segmentation performance when compared to avant-garde CNN and Transformer-based methods for medical image segmentation. The performance improvement due to the proposed 3D LK attention module was statistically validated.

Over the last few years, convolutional neural networks (CNNs) have dominated the field of computer vision thanks to their ability to extract features and their outstanding performance in classification problems, for example in the automatic analysis of X-rays. Unfortunately, these neural networks are considered black-box algorithms, i.e. it is impossible to understand how the algorithm has achieved the final result. To apply these algorithms in different fields and test how the methodology works, we need to use eXplainable AI techniques. Most of the work in the medical field focuses on binary or multiclass classification problems. However, in many real-life situations, such as chest X-rays, radiological signs of different diseases can appear at the same time. This gives rise to what is known as ”multilabel classification problems”. A disadvantage of these tasks is class imbalance, i.e. different labels do not have the same number of samples. The main contribution of this paper is a Deep Learning methodology for imbalanced, multilabel chest X-ray datasets. It establishes a baseline for the currently underutilised PadChest dataset and a new eXplainable AI technique based on heatmaps. This technique also includes probabilities and inter-model matching. The results of our system are promising, especially considering the number of labels used. Furthermore, the heatmaps match the expected areas, i.e. they mark the areas that an expert would use to make a decision.

Abstract Atmospheric extreme events cause severe damage to human societies and ecosystems. The frequency and intensity of extremes and other associated events are continuously increasing due to climate change and global warming. The accurate prediction, characterization, and attribution of atmospheric extreme events is, therefore, a key research field in which many groups are currently working by applying different methodologies and computational tools. Machine learning and deep learning methods have arisen in the last years as powerful techniques to tackle many of the problems related to atmospheric extreme events. This paper reviews machine learning and deep learning approaches applied to the analysis, characterization, prediction, and attribution of the most important atmospheric extremes. A summary of the most used machine learning and deep learning techniques in this area, and a comprehensive critical review of literature related to ML in EEs, are provided. The critical literature review has been extended to extreme events related to rainfall and floods, heatwaves and extreme temperatures, droughts, severe weather events and fog, and low-visibility episodes. A case study focused on the analysis of extreme atmospheric temperature prediction with ML and DL techniques is also presented in the paper. Conclusions, perspectives, and outlooks on the field are finally drawn.

This paper gravitates on the spectrum channel allocation problem where each compounding node of a cognitive radio network is assigned a frequency channel for transmission over a given outgoing link, based on optimizing an overall network performance metric dependant on the level of interference among nearby nodes. In this context, genetically inspired algorithms have been extensively used so far for solving this optimization problem in a computationally efficient manner. This work extends previous preliminary research carried out by the authors on the application of the heuristic Harmony Search (HS) algorithm to this scenario by presenting further results and derivations on both HS-based centralized and distributed spectrum allocation techniques. Among such advances, a novel adaptive island-like distributed allocation procedure is presented, which dramatically decreases the transmission rate required for exchanging control traffic among nodes at a quantifiable yet negligible performance penalty. Extensive simulation results executed over networks of increasing size verify, on one hand, that our proposed technique achieves near-optimum spectral channel assignments at a low computational complexity. On the other hand, the obtained results assess that HS vastly outperforms genetically inspired allocation algorithms for the set of simulated scenarios. Finally, the proposed adaptive distributed allocation approach is shown to attain a control traffic bandwidth saving of more than 90% with respect to the naive implementation of a HS-based island allocation procedure.

The use of intelligent optimization systems has been a major topic of research in the last few years for improving the existing urban infrastructure, the traffic optimization and the mobility of citizens. These techniques are of great importance in the analysis and optimization of transportation networks, as well as their re-organization to improve users’ mobility. In this paper we focus on the reconfiguration of one-way roads in a city after the occurrence of a major problem (e.g. a long-term road cut) in order to provide alternative routes that guarantee the mobility of citizens. In this manuscript a novel definition of this problem is formulated, for whose efficient resolution a novel two-objective approach based on the harmony search (HS) algorithm is proposed. The effectiveness of this proposal is tested in several synthetic instances, along with a real scenario in a city near Madrid, Spain. Extensive simulation results have been analyzed to verify that our proposal obtains excellent results in all the considered scenarios.

The Industry 4.0 revolution allows gathering big amounts of data that are used to train and deploy Artificial Intelligence algorithms to solve complex industrial problems, optimally and automatically. From those, Long-Short Term Memory Fully Convolutional Network (LSTM-FCN) networks are gaining a lot of attention over the last decade due to their capability of successfully modeling nonlinear feature interactions. However, they have not been yet fully applied for pattern classification tasks in time series data within the digital industry. In this paper, a novel approach based on an evolutionary algorithm for optimizing the networks hyperparameters and on the resulting deep learning model for pattern classification is proposed. In order to demonstrate the applicability of this method, a test scenario that involves a process related to blind fastener installation in the aeronautical industry is provided. The results achieved with the proposed approach are compared with shallow models and it is demonstrated that the proposed method obtains better results with an accuracy value of 95%.

CCTV cameras installed for continuous surveillance generate enormous amounts of data daily, forging the term Big Video Data (BVD). The active practice of BVD includes intelligent surveillance and activity recognition, among other challenging tasks. To efficiently address these tasks, the computer vision research community has provided monitoring systems, activity recognition methods, and many other computationally complex solutions for the purposeful usage of BVD. Unfortunately, the limited capabilities of these methods, higher computational complexity, and stringent installation requirements hinder their practical implementation in real-world scenarios, which still demand human operators sitting in front of cameras to monitor activities or make actionable decisions based on BVD. The usage of human-like logic, known as fuzzy logic, has been employed emerging for various data science applications such as control systems, image processing, decision making, routing, and advanced safety-critical systems. This is due to its ability to handle various sources of real-world domain and data uncertainties, generating easily adaptable and explainable data-based models. Fuzzy logic can be effectively used for surveillance as a complementary for huge-sized artificial intelligence models and tiresome training procedures. In this article, we draw researchers’ attention toward the usage of fuzzy logic for surveillance in the context of BVD. We carry out a comprehensive literature survey of methods for vision sensory data analytics that resort to fuzzy logic concepts. Our overview highlights the advantages, downsides, and challenges in existing video analysis methods based on fuzzy logic for surveillance applications. We enumerate and discuss the datasets used by these methods, and finally provide an outlook toward future research directions derived from our critical assessment of the efforts invested so far in this exciting field.

Much has been said about the fusion of bio-inspired optimization algorithms and Deep Learning models for several purposes: from the discovery of network topologies and hyperparametric configurations with improved performance for a given task, to the optimization of the model's parameters as a replacement for gradient-based solvers. Indeed, the literature is rich in proposals showcasing the application of assorted nature-inspired approaches for these tasks. In this work we comprehensively review and critically examine contributions made so far based on three axes, each addressing a fundamental question in this research avenue: (a) optimization and taxonomy (Why?), including a historical perspective, definitions of optimization problems in Deep Learning, and a taxonomy associated with an in-depth analysis of the literature, (b) critical methodological analysis (How?), which together with two case studies, allows us to address learned lessons and recommendations for good practices following the analysis of the literature, and (c) challenges and new directions of research (What can be done, and what for?). In summary, three axes – optimization and taxonomy, critical analysis, and challenges – which outline a complete vision of a merger of two technologies drawing up an exciting future for this area of fusion research.

In clinical medicine, magnetic resonance imaging (MRI) is one of the most important tools for diagnosis, triage, prognosis, and treatment planning. However, MRI suffers from an inherent slow data acquisition process because data is collected sequentially in k-space. In recent years, most MRI reconstruction methods proposed in the literature focus on holistic image reconstruction rather than enhancing the edge information. This work steps aside this general trend by elaborating on the enhancement of edge information. Specifically, we introduce a novel parallel imaging coupled dual discriminator generative adversarial network (PIDD-GAN) for fast multi-channel MRI reconstruction by incorporating multi-view information. The dual discriminator design aims to improve the edge information in MRI reconstruction. One discriminator is used for holistic image reconstruction, whereas the other one is responsible for enhancing edge information. An improved U-Net with local and global residual learning is proposed for the generator. Frequency channel attention blocks (FCA Blocks) are embedded in the generator for incorporating attention mechanisms. Content loss is introduced to train the generator for better reconstruction quality. We performed comprehensive experiments on Calgary-Campinas public brain MR dataset and compared our method with state-of-the-art MRI reconstruction methods. Ablation studies of residual learning were conducted on the MICCAI13 dataset to validate the proposed modules. Results show that our PIDD-GAN provides high-quality reconstructed MR images, with well-preserved edge information. The time of single-image reconstruction is below 5ms, which meets the demand of faster processing.

Randomized neural networks have become more and more attractive recently since they use closed-form solutions for parameter training instead of gradient-based approaches. Among them, the random vector functional link network (RVFL) and its deeper version ensemble deep random vector functional link network (edRVFL) show great performance on both classification and regression tasks. However, the previous research on these two models mainly focuses on the supervised learning area. Although there have been efforts to extend the RVFL network to solve semi-supervised learning problems, the potential of the edRVFL network has not been fully investigated. Therefore, we propose a jointly optimized learning strategy for the edRVFL network (JOSedRVFL) for semi-supervised learning tasks in this paper. The JOSedRVFL network uses an iterative procedure to compute the output weights and consequently predicts the class labels of the unlabeled training data during the training process. In addition, we propose another semi-supervised edRVFL network (SS-edRVFL) using manifold regularization in this work. We then do a brief comparison between these two methods to illustrate their similarities and differences. In the experimental part, we conduct the first set of experiments using the UCI datasets to compare the performance of our proposed semi-supervised algorithms against 11 other classifiers to demonstrate the superior performance of the SS-edRVFL and JOSedRVFL networks. JOSedRVFL achieves the highest accuracy on all 4 datasets while SS-edRVFL takes the second place 3 times which is only worse than JOSedRVFL. Moreover, we apply the proposed methods to real-world applications using the electroencephalography-based emotion recognition dataset to compare the performance of RVFL-based methods (RVFL, SS-RVFL, and JOSRVFL) and their edRVFL counterparts (edRVFL, SS-edRVFL, and JOSedRVFL). Results from this test revealed that the edRVFL-based models (edRVFL, SS-edRVFL, and JOSedRVFL) can obtain higher accuracy than the RVFL-based versions (RVFL, SS-RVFL, and JOSRVFL) with the same learning framework on 45 real-world semi-supervised benchmarks. We then perform the Wilcoxon signed-rank test to show that JOSedRVFL is significantly better than 5 other competitors, which supports our claim that JOSedRVFL can be treated as a superior classifier for semi-supervised classification on both benchmark datasets and real-world applications.