The journal Computers & Electrical Engineering provides rapid publication of topical research into the integration of computer technology and computational techniques with electrical and communication and information systems. The journal publishes papers featuring novel implementations of computers and computational techniques in areas like:

    Signal Processing
    Power Engineering (including renewable and green energies)
    Artificial Intelligence - methods and applications
    Security
    Privacy
    Communication

The journal regularly publishes special sections covering specific topics of interest. Proposals for special sections should be submitted to the Editor-in-Chief. The list of current special sections can be found at https://www.sciencedirect.com/journal/computers-and-electrical-engineering/special-issues.

Special Issue on Power System and Energy Storage based on Artificial Intelligence and Machine Learning (VSI-pses)
Submission Date: 2024-08-30

With the growth of global energy demand, continuous depletion of fossil fuels and concerns about the environmental crisis, clean energy and renewable energy power generation have been popularized and applied in many countries due to their abundant and clean advantages. Power technologies such as energy storage and electric drives, power electronic converters, and smart grid control have become current research hotspots. The development of clean energy such as electricity will play an increasingly important role in the future energy structure system. However, modern energy storage and power system research still faces many challenges with the limited investment in energy system expansion, the high penetration rate of renewable energy, the uncertainty related to the power output of such power plants, the uncertainties brought about by the increasing popularity of renewable energy generation and its implementation shortcomings (high initial investment, high maintenance cost, and intermittency).

Guest Editors:

    Dr. Jinfeng Wang, Zhengzhou University, China, Email: jf.wang@zzu.edu.cn (Main Guest Editor)
    Dr. Om Malik, University of Calgary, Canada, Email: maliko@ucalgary.ca​
    Dr. Mohan Lal Kolhe, University of Agder, Noway, Email: mohan.l.kolhe@uia.no

Short Bio:

Dr. Jinfeng Wang
Prof. Jinfeng Wang has been working at Zhengzhou University since 2002. She has successively published in Automation of Electric Power Systems, Electric Power Automation Equipment, Journal of Electrical Technology and other journals / conferences, more than 280 papers. In addition, she has served as an editorial board member and a reviewer in many international academic journals, like Environmental Science and Pollution Research, Journal of Energy Storage, International Journal of Energy Research, Ain Shams Engineering Journal, Sensors and so on. She also has served as General Chair, Co-Chair, Publication Chair, Organizing Committee Chair, Technical Committee Member and Organizing Committee Member of more than 30 international conferences and has given over 20 invited talks at international conferences, universities, and companies. Her main research areas are electrical engineering, smart grid, power system planning and reliability, electricity market risk management, etc. She has participated in and supported many scientific research projects, and has won the first and second prizes for scientific and technological achievements many times.

Dr. Om Malik
Professor Om P. Malik has done pioneering work in the development of controllers for application in electric power systems and wind power generation over the past over 50 years. After extensive testing, the adaptive controllers developed by his group are now employed on large generating units. His other interests include digital protection, control of renewable power generation and micro-grids, and AI applications in power system control. He has published over 800 papers including over 410 papers in international Journals and is the coauthor of four books: (1) Electric Distribution Systems, (2) Power System Stability, (3) Power Grids with Renewable Energy, (4) Power System Stability and Control.
Professor Malik graduated in 1952 from Delhi Polytechnic. After working for nine years in electric utilities in India, he obtained a Master Degree from Roorkee University in 1962, a Ph.D. from London University and a DIC from the Imperial College, London in 1965. He was teaching and doing research in Canada from 1966 to 1997 and continues to do research as Professor Emeritus at the University of Calgary. Over 100, including 54 Ph.D., students have graduated under his supervision. Professor Malik is a Life Fellow of IEEE, and a Fellow of IET, the Engineering Institute of Canada, Canadian Academy of Engineering, Engineers Canada and World Innovation Foundation. He is a registered Professional Engineer in the Provinces of Alberta and Ontario, Canada, and has received many awards. He was Director, IEEE Region 7 and President, IEEE Canada during 2010-11 and President, Engineering Institute of Canada, 2014-2016.

Dr. Mohan Lal Kolhe
Prof. Dr. Mohan Lal Kolhe is a full professor in smart grid and renewable energy at the Faculty of Engineering and Science of the University of Agder (Norway). He is a leading renewable energy technologist with three decades of academic experience at the international level and previously held academic positions at the world's prestigious universities, e.g., University College London (UK / Australia), University of Dundee (UK), University of Jyvaskyla (Finland), Hydrogen Research Institute, QC (Canada), etc. In addition, he was a member of the Government of South Australia's first
Renewable Energy Board (2009-2011) and worked on developing renewable energy policies. Prof. Kolhe is an expert evaluator of many prestigious international research councils (e.g., European Commission: Erasmus+ Higher Education – International Capacity Building, Royal Society London (UK), Engineering and Physical Sciences Research Council (EPSRC UK), Cyprus Research Foundation, etc.). Professor Kolhe has successfully won competitive research funding from the prestigious research councils (e.g., Norwegian Research Council, EU, EPSRC, BBSRC, NRP, etc.) for his work on sustainable energy systems. His research works in energy systems have been recognized within the top 2% of scientists globally by Stanford University's 2020, 2021 matrices. He is an internationally recognized pioneer in his field, whose top 10 published works have an average of over 175 citations each.

Special issue information:

Overview

With the growth of global energy demand, continuous depletion of fossil fuels and concerns about the environmental crisis, clean energy and renewable energy power generation have been popularized and applied in many countries due to their abundant and clean advantages. Power technologies such as energy storage and electric drives, power electronic converters, and smart grid control have become current research hotspots. The development of clean energy such as electricity will play an increasingly important role in the future energy structure system. However, modern energy storage and power system research still faces many challenges with the limited investment in energy system expansion, the high penetration rate of renewable energy, the uncertainty related to the power output of such power plants, the uncertainties brought about by the increasing popularity of renewable energy generation and its implementation shortcomings (high initial investment, high maintenance cost, and intermittency).

Fortunately, the rapid development of artificial intelligence, especially machine learning-based technologies, is opening up new opportunities for power operators. Artificial intelligence and machine learning can help us effectively extract and analyze the large amount of data generated in different power system domains, handle its variety and volume through faster computation, and guide some decision-making processes required for power systems to make a contribution.

The aim of this special section is to disseminate recent advances associated with the application of AI and machine learning in power systems and energy storage, which is of key importance for addressing power and energy supply challenges.

Topics:

• Smart grids
• Optimal operation of microgrid systems
• Smart energy system planning
• Machine learning for load forecasting in energy system
• Generation forecasting and power system scheduling based on neural network
• Economic dispatch
• Intelligent energy management systems
• Energy-optimal adaptive control
• Energy storage systems
• Energy storage technologies and devices
• Data science, AI and machine learning for energy storage modeling and control
• Electric vehicle charging forecast
• Adaptive charge control strategy

Manuscript submission information:

Submission Guidelines:

New papers, or extended versions of papers presented at related conferences, are welcome. Submissions must not be currently under review for publication elsewhere. Conference papers may be submitted only if they are substantially extended (more than 50%), and must be referenced. All submitted papers will be peer-reviewed using the normal standards of CAEE, and accepted based on quality, originality, novelty, and relevance to the theme of the special section. By submitting a paper to this issue, the authors agree to referee one paper (if asked) within the time frame of the Special Section.

Before submission, authors should carefully read the Guide for Authors. Authors should submit their papers through the journal's web submission tool by selecting “VSI-pses” under the “Issues” tab.

For additional questions, contact the Main Guest Editor.

Schedule

Submission deadline: August 30, 2024
First notification: October 15, 2024
Submission of revised manuscript: November 30, 2024
Notification of the re-review: December 30, 2024
Final notification: February 28, 2025
Final paper due: March 30, 2025
Publication: June 30, 2025

Special Issue on Multisensor Image Fusion in the Internet of Vehicles for Autonomous Systems (VSI-ifas)
Submission Date: 2024-09-25

This special section serves as a comprehensive repository, offering a multidimensional view of the advancements, challenges, and future directions in multisensor image fusion, essential for the realization of reliable and intelligent autonomous systems in the IoV landscape.

Guest editors:

Dr. Pei Xiao
University of Surrey, United Kingdom
Email: p.xiao@ieee.org; p.xiao@surrey.ac.uk
https://scholar.google.co.uk/citations?user=1xI_0DoAAAAJ&hl=en

Prof. Alex Alexandridis
University of West Attica, Greece
Email: alexx@uniwa.gr
https://scholar.google.com/citations?user=H1yA4TgAAAAJ&hl=th

Dr. Pawel Burdziakowski
Gdansk University of Technology, Poland
Email:pawel.burdziakowski@pg.edu.pl
https://scholar.google.pl/citations?user=xC6mTPsAAAAJ&hl=pl

Special issue information:

Evolving autonomous systems (ASs) refer to technological frameworks or mechanisms that can adapt, learn, and improve their functionality over time without direct human intervention. Autonomous systems rely on various sensors (such as cameras, lidar, radar, etc.) to perceive and gather information from their environment. The evolving nature of multisensor image fusion involves a continuous learning process, where the fusion algorithms or systems adapt and improve based on new data, experiences, and feedback. This evolving capability is crucial in many applications where accurate and reliable fusion information is essential for decision-making and analysis. In addition, the internet of vehicles (IoV) represents a dynamic ecosystem that interconnects vehicles, infrastructure, and the internet. It merges cutting-edge technologies with AS to create intelligent networks that optimize and provide a range of innovative services. The IoV relies on a multitude of sensors, communication devices, and data analytics for exchanging real-time information, allowing them to make informed decisions autonomously. The IoV's evolution is closely tied to the development of ASs. In IoV-based AS multisensor image fusion enables a more robust and accurate understanding of the environment by mitigating individual sensor limitations. As the IoV continues to evolve, the integration of 5G and future wireless communication technologies will further enhance connectivity, enabling faster and more reliable data exchange among autonomous systems.

The fusion of multisensor data in IoV contributes to improved object detection, tracking, and localization. This comprehensive perception is crucial for ensuring the safety and efficiency of ASs in real time, considering various environmental factors and potential hazards. Furthermore, the integration of multisensor image fusion into IoV systems also presents challenges such as data synchronization, alignment, calibration, and computational complexity. Overcoming these challenges requires advanced algorithms, signal processing techniques, and sensor fusion methodologies to effectively merge data from disparate sources while ensuring accuracy and real-time performance. Continued advancements in this field will be crucial for the further development and deployment of ASs in the future.

This special section serves as a comprehensive repository, offering a multidimensional view of the advancements, challenges, and future directions in multisensor image fusion, essential for the realization of reliable and intelligent autonomous systems in the IoV landscape.

Topics include but are not limited to the following:

    Advanced methodologies and algorithms in multisensor image fusion techniques for enhancing the perception accuracy of IoV ASs
    Deep learning models to multisensor image fusion: object detection, classification, and scene understanding of ASs
    Real-time multisensor fusion algorithms in IoV-AS applications for privacy and security
    Edge computing in multisensor fusion for faster and more flexible decision-making by IoV-based ASs
    Artificial intelligence (AI)-enabled multisensor image fusion of IoV solutions for AS in smart city development
    Multi-sensor image fusion algorithm for IoV-enabled autonomous blind spot detection systems
    Novel approaches to the challenges and opportunities of multisensor image fusion in 5G and beyond networks for next-gen IoV-ASs
    Multisensor image fusion in an IoV-powered autonomous control switching mechanism for intelligent device applications
    AI trends in multisensor image fusion-based smart IoV for intelligent anti-interference of industrial ASs

Manuscript submission information:

Submission Guidelines:

New papers, or extended versions of papers presented at related conferences, are welcome. Submissions must not be currently under review for publication elsewhere. Conference papers may be submitted only if they are substantially extended (more than 50%), and must be referenced. All submitted papers will be peer-reviewed using the normal standards of CAEE, and accepted based on quality, originality, novelty, and relevance to the theme of the special section. By submitting a paper to this issue, the authors agree to referee one paper (if asked) within the time frame of the special section.

Before submission, authors should carefully read the Guide for Authors available at https://www.elsevier.com/journals/computers-and-electrical-engineering/0045-7906/guide-for-authors Authors should submit their papers through the journal's web submission tool at https://www.editorialmanager.com/compeleceng/default.aspx by selecting “VSI-ifas” under the “Article Type” tab. For additional questions, contact the Main Guest Editor.

Important Dates:

    Last Date for Paper Submission: 25th Sep, 2024
    Revised Version: 15th Jan, 2025
    Acceptance: 30th Mar, 2025

Special Issue on Artificial Intelligence and Signal Processing for Enhanced Data Analysis (VSI- aispeda)
Submission Date: 2024-09-30

The evolution of technology has revolutionized our living spaces by simplifying and enhancing our day-to-day activities. Technology serves as a pivotal tool and plays a fundamental role, finding its application across various domains from healthcare to agriculture. However, it's evident that no single machine can meet the unique demands of every sector. To address this challenge, we've engineered an embedded system that offers the adaptability and customization needed for diverse specifications. 

Guest editors:

Prof. Aleksandra Kawala-Sterniuk

[Managing Guest Editor] 

    Faculty of Electrical Engineering, Automatic Control and Informatics, Opole University of Technology, 45-758 Opole, Poland
    E-mail: a.kawala-sterniuk@po.edu.pl, biomed.bspl@gmail.com
    ORCiD-Link: https://orcid.org/0000-0001-7826-1292
    Scholar-Link: https://scholar.google.com/citations?user=stUsxGgAAAAJ&hl=en

Prof. Adam Sudol,

[First Co-Guest Editor],

    Institute of Environmental Engineering and Biotechnology, Faculty of Natural and Technical Sciences, University of Opole, Kominka 6/6A, 45-035 Opole, Poland 
    E-mail: dasiek@uni.opole.pl
    ORCiD-Link: https://orcid.org/0000-0001-9620-0688
    Scholar-Link: https://scholar.google.com/citations?user=n0WRLDgAAAAJ&hl=en

Prof. Mariusz Pelc,

[Second Co-Guest Editor],

    School of Computing and Mathematical Sciences, University of Greenwich, London, SE10 9LS, UK
    E-mail: m.pelc@greenwich.ac.uk
    ORCiD-Link: https://orcid.org/0000-0003-2818-1010
    Scholar-Link: https://scholar.google.com/citations?user=ikv9LOMAAAAJ&hl=pl

Prof. Radek Martinek,

[Third Co-Guest Editor],

    Department of Cybernetics and Biomedical Engineering, VSB-Technical University of Ostrava,
    70800 Ostrava, Czech Republic
    E-mail: radek.martinek@vsb.cz
    ORCiD-Link: https://orcid.org/0000-0003-2054-143X
    Scholar-Link: https://scholar.google.cz/citations?user=56BAo9AAAAAJ&hl=en 

Special issue information:

The evolution of technology has revolutionized our living spaces by simplifying and enhancing our day-to-day activities. Technology serves as a pivotal tool and plays a fundamental role, finding its application across various domains from healthcare to agriculture. However, it's evident that no single machine can meet the unique demands of every sector. To address this challenge, we've engineered an embedded system that offers the adaptability and customization needed for diverse specifications. Embedded systems involve the integration of hardware components with embedded software. These systems can function as standalone units or as subsystems within larger frameworks. They are purpose-built to execute specific tasks, such as a fire alarm system designed solely to detect smoke. The integration of AI with embedded systems heralds the future of this technology. Embedded AI refers to the implementation of machine learning and deep learning within the software at the device level. This approach empowers the system to provide predictive insights and flexible data analysis. Crafting intelligent software that operates within resource-constrained environments, especially in real-time settings, is a complex endeavour. To address this complexity, solutions like parallelizing reasoning or incorporating hardware components have been devised. Moreover, forging connections between AI models and various embedded systems is a paramount objective in this domain.

The effective application of embedded AI hinges on advancements in hardware technology. In this special issue, we aim to attract original research papers that investigate the use of AI to enhance the flexibility of embedded systems. We encourage papers that address innovative AI-driven solutions for various domains including but not limited to autonomous vehicles, smart healthcare devices, edge computing, and the Internet of Things. We are particularly interested in studies that address the practical implementation of AI in embedded systems, assess their performance in real-world scenarios, and propose solutions to address challenges such as security, resource constraints, and reliability.

Topics of particular interest include, but are not limited to:

    Edge AI for real-time decision-making in embedded systems.
    Machine learning techniques for adaptive power management in IoT devices.
    Predictive maintenance using AI in industrial embedded systems.
    Security measures and challenges in AI-driven embedded systems.
    Lightweight AI models for resource-constrained embedded devices.
    AI-based solutions for autonomous vehicles, including perception and decision-making.
    Health monitoring and diagnosis through AI-powered medical embedded systems.
    Human-robot interaction with AI-enhanced robotic systems.
    AI for intelligent control in smart grid applications.
    Natural language processing in embedded systems for voice commands and chatbots.
    AI-driven image and video processing for surveillance and computer vision applications.
    Reinforcement learning for adaptive control in embedded systems.
    AI-based fault detection and isolation in aerospace and automotive systems.

Manuscript submission information:

Submission Guidelines:

New papers, or extended versions of papers presented at related conferences, are welcome. Submissions must not be currently under review for publication elsewhere. Conference papers may be submitted only if they are substantially extended (more than 50%), and must be referenced. All submitted papers will be peer-reviewed using the normal standards of CAEE, and accepted based on quality, originality, novelty, and relevance to the theme of the special section. By submitting a paper to this issue, the authors agree to referee one paper (if asked) within the time frame of the special section.

Before submission, authors should carefully read the Guide for Authors available at https://www.elsevier.com/journals/computers-and-electrical-engineering/0045-7906/guide-for-authors Authors should submit their papers through the journal's web submission tool at https://www.editorialmanager.com/compeleceng/default.aspx by selecting “VSI-aispeda” under the “Article Type” tab. For additional questions, contact the Main Guest Editor.

Schedule

    Submission deadline: 30 Sept 2024
    Acceptance deadline: 31 Dec 2024

Keywords:

Artificial Intelligence; Embedded systems; IoT; Health monitoring; Robotics

Special Issue on Randomization-Based Deep and Shallow Learning Algorithms (VSI-rdsla)
Submission Date: 2024-09-30

Randomization-based learning algorithms have received considerable attention from academics, researchers, and domain workers because randomization-based neural networks can be trained by non-iterative approaches possessing closed-form solutions. Those methods are, in general, computationally faster than iterative solutions and less sensitive to parameter settings. Even though randomization-based non-iterative methods have attracted much attention in recent years, their deep structures have not been sufficiently developed nor benchmarked. This special session aims to bridge this gap.

Guest editors:

    Prof. M. Tanveer, IIT Indore, India. mtanveer@iiti.ac.in 
    Dr. Ruobin Gao, Nanyang Technological University, Singapore. ruobin.gao@ntu.edu.sg 
    Prof. Ping Zhou, Northeastern University, China. zhouping@mail.neu.edu.cn 
    Prof. Claudio Gallicchio, University of Pisa, Italy. claudio.gallicchio@unipi.it 

Special issue information:

Randomization-based learning algorithms have received considerable attention from academics, researchers, and domain workers because randomization-based neural networks can be trained by non- iterative approaches possessing closed-form solutions. Those methods are, in general, computationally faster than iterative solutions and less sensitive to parameter settings. Even though randomization-based non-iterative methods have attracted much attention in recent years, their deep structures have not been sufficiently developed nor benchmarked. This special session aims to bridge this gap.

The first target of this special session is to present the recent advances in randomization-based learning methods. Randomization-based neural networks usually offer non-iterative closed-form solutions. Secondly, the focus is on promoting the concepts of non-iterative optimization with respect to counterparts, such as gradient-based methods and derivative-free iterative optimization techniques. Besides the dissemination of the latest research results on randomization-based and/or non-iterative algorithms, it is also expected that this special session will cover some practical applications, present some new ideas, and identify directions for future studies.

Original contributions, as well as comparative studies among randomization-based methods and non- randomized methods, are welcome with unbiased literature reviews and comparative studies. Typical deep/shallow paradigms include (but are not limited to) random vector functional link (RVFL), echo state networks (ESN), liquid state networks (LSN), kernel ridge regression (KRR) with randomization, extreme learning machines (ELM), randomized convolutional neural networks (CNN), stochastic configuration networks (SCN), broad learning system (BLS), random forests (RF), and so on.

Topics of the special session include (with randomization-based methods), but are not limited to:

    Randomized convolutional neural networks
    Randomized internal representation learning
    Regression, classification, and time series analysis by randomization-based methods
    Kernel methods such as kernel ridge regression, kernel adaptive filters, etc. with randomization
    Feedforward, recurrent, multilayer, deep, and other structures with randomization
    Ensemble learning with randomization
    Moore-Penrose pseudoinverse, SVD, and other solution procedures
    Gaussian process regression
    Randomization-based methods for large-scale problems with and without kernels
    Theoretical analysis of randomization-based methods
    Comparative studies with competing methods with or without randomization
    Applications of randomized methods in domains such as power systems, biomedical, finance, signal processing, big data, and all other relevant areas

Manuscript submission information:

Papers will be evaluated based on their originality, presentation, relevance, and contribution to the development of Randomization-Based Deep and Shallow Learning Algorithms, as well as their suitability and quality in terms of both technical contribution and writing. The submitted papers must be written in good English and describe original research that has not been published nor is currently under review by other journals or conferences. If used, the previously published conference papers should be clearly identified by the authors (at the submission stage), and an explanation should be provided as to how such papers have been extended to be considered for this special issue. Guest Editors will make an initial determination on the suitability and scope of all submissions. Papers that either lack originality or clarity in presentation or fall outside the scope of the special issue will not be sent for review, and the authors will be promptly informed in such cases. Author guidelines for the preparation of the manuscript can be found at https://www.sciencedirect.com/journal/computers-and-electrical-engineering. Manuscripts should be submitted online at https://www2.cloud.editorialmanager.com/compeleceng/default2.aspx, and when submitting, authors are asked to select the following submission category: “VSI-rdsla”

Important dates

    VSI Submission Opens: 22nd Jan 2024 
    VSI Submission Closes: 30th Sep 2024
    Expected Review Duration: 2-3 Months per review cycle.

Keywords:

Randomized convolutional neural networks; Ensemble learning with randomization; Randomization-based methods for large-scale problems with and without kernels; Randomized internal representation learning; Applications of randomized methods in domains such as power systems, biomedical, finance, signal processing, big data, and all other relevant areas.

Special Issue on Safe Planning and Control for Autonomous Driving Using Advanced Machine Learning Methods and Control Theories (VSI-spcad)
Submission Date: 2024-10-15

The recent proliferation of autonomous driving technologies has revolutionized cities by making autonomous vehicles (AVs) a viable option for daily transportation. AVs significantly enhance road safety, optimize traffic flow, and provide efficient and accessible mobility. In the early deployment stages of AVs with very low penetration rates, consider an AV navigating through urban traffic while avoiding other agents such as human-driven vehicles, and pedestrians. These scenarios are safety-critical and challenging as the agents’ intentions and policies are unknown. This special issue aims to explore the latest developments and applications of advanced control theory and machine learning technology for the safe path-planning and motion control of AVs.

Guest editors:

Dr. Zejiang Wang
Oak Ridge National Laboratory, USA Email: wangz2@ornl.gov

Dr. Jinhao Liang
National University of Singapore, Singapore Email: jh.liang@nus.edu.sg

Dr. Zhenwu Fang
National University of Singapore, Singapore Email: zhenwu.fang@u.nus.edu

Prof. Guodong Yin
Southeast University, China Email: ygd@seu.edu.cn

Special issue information:

Overview:

Navigating through dynamic environments in a safe maneuver is a critical mission of AVs. This necessitates AVs to systematically assess their autonomous driving capabilities and understand the behavior of surroundings. It is challenging as the intentions and policies of nearby traffic agents are unknown so that their a-priori unknown trajectories need to be estimated. In recent years, learning-based approaches have demonstrated their effectiveness in motion prediction tasks. Meanwhile, advanced control theory provides safety guarantees for the motion-control of AVs. This special issue is dedicated to the exploration of combining advanced control theory and machine learning technology for achieving the safe path-planning and motion control of AVs.

The problem of safe planning requires AVs to predict the future states of the nearby traffic participants based on the current and past observations of the surrounding environment. This helps enhance their awareness of the imminent hazards. Recent advances in machine learning techniques (e.g., deep learning) have provided new and powerful tools for solving the problem of behavior prediction. Such approaches have become increasingly important due to their promising performance in complex and realistic scenarios. Despite the success of existing prediction models in encoding the driving scene and representing future actions through agents’ past trajectories, they often fail to provide valid safety guarantees unless strong assumptions are placed on the prediction algorithm. Note that advanced control theory has already demonstrated remarkable advancements in ensuring the safety guarantees of motion control for AVs.

In this special issue, we encourage contributions that focus on the latest advancements in machine learning methods, advanced control theory, statistical approaches, and engineering applications for the safe path-planning and control of autonomous driving.

Topics of interest include, but are not limited, to the following:

    Deep Learning for Trajectory Prediction
    Safe and Robust Control of Autonomous Driving Statistical Methods for Quantifying Uncertain Predictions Recognition and Classification of Human Driver Behaviors
    Human-machine Dynamics Modeling for Intelligent Vehicles Modeling and Advanced Simulation of Autonomous Driving Risk-Aware Prediction in a Mix Traffic Flow
    Trustworthiness Analysis of Autonomous Driving Algorithms
    Cooperative Control between Autonomous Vehicles and Human-Driven Vehicles Application of Game-theory in the Human-Vehicle Interaction System
    Machine Learning Methods for Autonomous Path-planning Advanced Vehicle-to-Infrastructure (V2I) Communication Technology

Manuscript submission information:

Submission Guidelines:

New papers, or extended versions of papers presented at related conferences, are welcome. Submissions must not be currently under review for publication elsewhere. Conference papers may be submitted only if they are substantially extended (more than 50%), and must be referenced. All submitted papers will be peer-reviewed using the normal standards of CAEE, and accepted based on quality, originality, novelty, and relevance to the theme of the special section. By submitting a paper to this issue, the authors agree to referee one paper (if asked) within the time frame of the special section.

Before submission, authors should carefully read the Guide for Authors available at https://www.elsevier.com/journals/computers-and-electrical-engineering/0045-7906/guide-for-authors Authors should submit their papers through the journal's web submission tool at https://www.editorialmanager.com/compeleceng/default.aspx by selecting “VSI-spcad” under the “Article Type” tab. For additional questions, contact the Main Guest Editor.

Schedule

    Submission deadline: 15 Oct 2024
    Acceptance deadline: 31 Dec 2024

Keywords:

Autonomous Driving Technology; Machine Learning Methods; Safe Path-planning and Control; Social Human-vehicle Dynamics.

Special Issue on Security and Privacy Protection Technologies in AI (VSI: SPPT in AI)
Submission Date: 2024-11-01

In the realm of artificial intelligence (AI) and its burgeoning technologies, data holds paramount importance, serving as the cornerstone for a plethora of advanced applications such as intelligent transportation systems, smart home technologies, and financial risk management. These revolutionary technologies facilitate the collection, retention, and manipulation of sensitive personal data without explicit consent, thereby posing significant challenges to privacy protection. Furthermore, the constant advancement of AI technologies enables the extraction of increasingly profound insights into personal information, further exacerbating privacy concerns. As a result, the challenges associated with privacy protection in the realm of artificial intelligence technologies have attained utmost significance, urging the implementation of robust measures to safeguard sensitive data in the rapid evolution of AI technologies.

Guest editors:

Prof. Elisa Bertino
Purdue University, USA 

Prof. Xiaofeng Chen
Xidian University, China 

Prof. Jin Li
Guangzhou University, China 

Prof. Elisa Bertino (Fellow, IEEE) is a professor of computer science with Purdue University. She serves as director of the Purdue Cyberspace Security Lab (Cyber2Slab). In her role as director of Cyber2SLab, she leads multi-disciplinary research in data security and privacy. Her main research interests include security, privacy, digital identity management systems, database systems, distributed systems, and multimedia systems. She received the 2002 IEEE Computer Society Technical Achievement Award for outstanding contributions to database systems and security and received the 2005 Tsutomu Kanai Award by the IEEE Computer Society for pioneering and innovative research contributions to secure distributed systems. She is a fellow member of the ACM and AAAS.

Prof. Xiaofeng Chen received his B.S. and M.S. on Mathematics from Northwest University, China in 1998 and 2000, respectively. He got his Ph.D degree in Cryptography from Xidian University in 2003. Currently, he works at Xidian University as a professor. His research interests include applied cryptography and cloud computing security. He has published over 300 research papers in refereed international conferences and journals. His work has been cited more than 16000 times at Google Scholar. He is in the Editorial Board of IEEE Transactions on Dependable and Secure Computing, IEEE Transactions on Knowledge and Data Engineering, International Journal of Foundations of Computer Science etc. He has served as the program/general chair or program committee member in over 30 international conferences.

Prof. Jin Li received his B.S. (2002) and M.S. (2004) from Southwest University and Sun Yat-sen University, both in Mathematics. He got his Ph.D degree in information security from Sun Yat-sen University at 2007. He is an executive vice president of Huangpu Research Institute of Guangzhou University and an executive director of Artificial Intelligence and Blockchain Research Institute. His research interests include blockchain, artificial intelligence security, cloud computing security. He has published more than 100 papers in international conferences and journals, including IEEE INFOCOM, IEEE TIFS, IEEE TPDS, IEEE TOC and ESORICS etc. His work has been cited more than 22000 times at Google Scholar. He has been selected as a highly cited scholar in the world, and many of his papers have won the Best paper award of international academic conferences. He also served as program chairs and committee for many international conferences. He received three National Science Foundation of China (NSFC) Grants and more than ten Grants from Guangdong Province and other departments for the research on security and privacy in new computing environments.

Special issue information:

In the realm of artificial intelligence (AI) and its burgeoning technologies, data holds paramount importance, serving as the cornerstone for a plethora of advanced applications such as intelligent transportation systems, smart home technologies, and financial risk management. These revolutionary technologies facilitate the collection, retention, and manipulation of sensitive personal data without explicit consent, thereby posing significant challenges to privacy protection. Furthermore, the constant advancement of AI technologies enables the extraction of increasingly profound insights into personal information, further exacerbating privacy concerns. As a result, the challenges associated with privacy protection in the realm of artificial intelligence technologies have attained utmost significance, urging the implementation of robust measures to safeguard sensitive data in the rapid evolution of AI technologies.​

At present, the realm of security and privacy protection continues to undergo constant evolution, exacerbated by the emergence of novel research challenges that require concerted attention and rigorous investigation. These challenges encompass various aspects, including but not limited to privacy risks during data collection and processing, privacy threats arising from data sharing and interaction, risks of privacy leakage during model training. To address these concerns, this special issue solicits contributions from scholars and practitioners operating within the domains of security and privacy protection. Its overarching objective is to galvanize collaborative efforts aimed at elucidating and mitigating these multifaceted challenges. This special issue endeavors to disseminate cutting-edge research outcomes delineating both theoretical advancements and practical methodologies of security and privacy protection in AI and its related fields.

Topics

The objective of the proposed special issue is to foster scholarly research and showcase the latest advancements in privacy-preserving technologies within the field of artificial intelligence, with emphasis on the following aspects, but certainly not limited to:

    Adversarial Machine Learning;
    Backdoor Attacks and Defenses;
    Big Data Protection, Integrity and Privacy;
    Copyright Protection for Models and Datasets;
    Security Techniques for Deep Learning and Federal Leaning
    Federated Learning Attacks and Defenses;
    Metrics for Security and Privacy;
    Machine Learning Applications to Privacy;
    Machine Learning Privacy Issues and Methods;
    Machine Unlearning;
    Privacy Protection for Cloud/edge Computing;
    Privacy Protection of Large Language Models;
    Privacy-enhancing Technologies, Anonymity, and Censorship;
    Trustworthy Machine Learning;
    Usable Security and Privacy;
    Security for Mobile Devices;
    Web Privacy.

Manuscript submission information:

Submission Guidelines: New papers, or extended versions of papers presented at related conferences, are welcome. Submissions must not be currently under review for publication elsewhere. Conference papers may be submitted only if they are substantially extended (more than 50%), and must be referenced. All submitted papers will be peer-reviewed using the normal standards of CAEE, and accepted based on quality, originality, novelty, and relevance to the theme of the special section. By submitting a paper to this issue, the authors agree to referee one paper (if asked) within the time frame of the special section. 

Before submission, authors should carefully read the Guide for Authors available at https://www.elsevier.com/journals/computers-and-electrical-engineering/0045-7906/guide-for-authors 

Authors should submit their papers through the journal's web submission tool at https://www.editorialmanager.com/compeleceng/default.aspx by selecting “VSI-SPPT in AI” under the “Article Type” tab. For additional questions, contact the Main Guest Editor. 

 Schedule

    Submission Due: November 1, 2024
    First Round Notification: February 1, 2025
    Final Notification: April 1, 2025
    Publication date: 2025/2026

Special Issue on Internet of Things-Aided Intelligent Transport Systems: Sensors, Methods, and Applications
Submission Date: 2024-12-30

The rapid advancement of Internet of Things (IoT) technology has revolutionized various industries, including the field of Intelligent Transport Systems (ITS). IoT has enabled the deployment of sensors and interconnected devices in transportation networks, which exhibits high potential in enhancing safety, efficiency, and sustainability. This special issue aims to explore the latest developments and applications of IoT in the realm of ITS, with a focus on sensors, methods, and real- world applications.

Guest editors:

Dr. Maohan Liang
    National University of Singapore
    Email: mhliang@nus.edu.sg

Prof. Hua Wang
    Hefei University of Technology
    Email: hwang191901@hfut.edu.cn

Prof. Guoqing Zhang 
    Dalian Maritime University 
    Email: zgq_dlmu@163.com

Special issue information:

Overview:

In recent years, the rapid advancement of Internet of Things (IoT) technology has heralded a transformative era in the field of Intelligent Transport Systems (ITS). The combination of IoT and ITS has led to a proliferation of innovative applications, driven by creative sensor technology, advanced modeling techniques, and real-world implementations. This special issue is dedicated to exploring the multifaceted impact of IoT on ITS, delving into the intricacies of sensors, models, and practical applications that are shaping the future of transportation.

In the realm of IoT-aided ITS, a diverse array of sensors, including cameras, satellite remote sensing, and GPS devices, serve as the foundation for data acquisition within the transportation domain. These sensors provide a wealth of information, which is crucial for enhancing safety, efficiency, and sustainability for our transportation society. Integrated with cutting-edge technologies in deep learning and machine learning, these sensors enable real-time decision-making by analyzing data streams. The applications of IoT- aided ITS cover various transport-related aspects, such as autonomous driving, environmental protection, accident prevention, decision systems for intelligent vehicles, and traffic planning. These advancements are pivotal in reshaping the future of transportation, spanning across multiple transportation modes including road, maritime, and aviation.

In this special issue, we invite authors to focus on the profound impact of IoT across these diverse transportation domains. We encourage contributions that address the challenges, opportunities, and innovations arising from the integration of IoT and ITS.

Topics of Interest:

We invite authors to submit original research articles, reviews, and case studies related to IoT-Aided ITS. Topics of interest include but are not limited to:

    Artificial Intelligence (AI) Model in IoT-Aided ITS
    Deep Learning Applications in IoT-Aided ITS
    Machine Learning Based Traffic Optimization
    Traffic Forecasting and Traffic Simulation
    Traffic Pattern Recognition Methods and Applications
    IoT Solutions for Sustainable and Efficient Transportation
    IoT-Based Vehicle Monitoring and Safety Systems
    Autonomous Vehicle Technologies
    Security and Privacy in IoT-Aided ITS
    IoT-Enabled Digital Twins for ITS
    Advanced Vehicle-to-Infrastructure (V2I) Communication Systems
    Advanced Vehicle-to-Vehicle (V2V) Communication Systems

Manuscript submission information:

Submission Guidelines

New papers, or extended versions of papers presented at related conferences, are welcome. Submissions must not be currently under review for publication elsewhere. Conference papers may be submitted only if they are substantially extended (more than 50%), and must be referenced. All submitted papers will be peer-reviewed using the normal standards of CAEE, and accepted based on quality, originality, novelty, and relevance to the theme of the special section. By submitting a paper to this issue, the authors agree to referee one paper (if asked) within the time frame of the Special Section.

Before submission, authors should carefully read the Guide for Authors. Authors should submit their papers through the journal's web submission tool by selecting “VSI-IoTA” under the “Issues” tab.

Important Dates:

    VSI Submission Opens: 30th Jan 2024 
    VSI submission Closes: 30th Dec 2024 
    Expected Review Duration: 2-3 Months

Keywords:

Internet of Things; Intelligent Transport Systems; Deep Learning

Special Issue on TinyML Empowered Intelligent Systems (VSI: TinyML IS)
Submission Date: 2024-12-31

Intelligent systems refer to the combination of software and hardware to imitate humans’ cognition, judgment and reasoning abilities. The software mainly refers to artificial intelligence (AI) models, while the hardware may be personal computer, cloud server or even a mobile computing platform. In general, the performance of intelligent system depends on the scale of existing knowledge library. The larger the knowledge library is, the better the expert system performs. However, the hardware may restrict the scale of knowledge library or AI model. For example, edge nodes in edge computing have limited memory and computing ability; the microcontroller unit (MCU) deployed in outside must keep low power consumption for long time. It has become a challenge to implement intelligent systems under limited hardware.

Compared with traditional machine learning (ML) models or large models, TinyML models require less memory, fewer computing resources, and lower power consumption. These merits make TinyML model can adapt the intelligence under limited resource environment. For example, TinyML models can be deployed in the intelligent edge nodes which are widely used in the Internet of Things (IoTs) or Artificial Intelligence of Things (AIoTs). This special issue will focus on the advances and challenges of TinyML to spur the development of intelligent system.

Guest editors:

    Fa Zhu, Nanjing Forestry University, China, fazhu@njfu.edu.cn
    Muhammad Waqas, University of Greenwich, UK, muhammad.waqas@greenwich.ac.uk
    Zhiyuan Tan, Edinburgh Napier University, UK, z.tan@napier.ac.uk
    Jalil Piran, Sejong University, South Korea, piran@sejong.ac.kr
    Massimo Merenda, Università Mediterranea di Reggio Calabria, Reggio Calabria, Italy, massimo.merenda@unirc.it

Special issue information:

Intelligent systems refer to the combination of software and hardware to imitate humans’ cognition, judgment and reasoning abilities. The software mainly refers to artificial intelligence (AI) models, while the hardware may be personal computer, cloud server or even a mobile computing platform. In general, the performance of intelligent system depends on the scale of existing knowledge library. The larger the knowledge library is, the better the expert system performs. However, the hardware may restrict the scale of knowledge library or AI model. For example, edge nodes in edge computing have limited memory and computing ability; the microcontroller unit (MCU) deployed in outside must keep low power consumption for long time. It has become a challenge to implement intelligent systems under limited hardware.

Compared with traditional machine learning (ML) models or large models, TinyML models require less memory, fewer computing resources, and lower power consumption. These merits make TinyML model can adapt the intelligence under limited resource environment. For example, TinyML models can be deployed in the intelligent edge nodes which are widely used in the Internet of Things (IoTs) or Artificial Intelligence of Things (AIoTs). This special issue will focus on the advances and challenges of TinyML to spur the development of intelligent system.

The object of this special issue is to promote the researches on TinyML to empower intelligent system under limited resource environment. Researchers from academic and practitioners from industry are welcome to share their recent works that adopt TinyML to handle aforementioned challenges of theory or application in intelligent system using limited resources.

Topics of interest include, but are not limited to, the following

    Novel findings of TinyML for intelligent system deployed in IoTs and IIoTs
    Explainability and interpretability of TinyML for intelligent systems
    Novel intelligent applications of intelligent system using TinyML in smart devices
    Security and privacy protection using TinyML in intelligent systems
    Intelligent systems in edge-cloud collaborating learning using TinyML
    Data processing using TinyML to enhance intelligent systems
    Intelligent systems in human behavior analysis using TinyML
    Intelligent systems using TinyML in Internet of Medical Things (IoMT)
    Intelligent systems using TinyML in Smart Grids and Energy Internet
    Intelligent systems using TinyML in Smart Agriculture

Manuscript submission information:

Submission Guidelines:New papers, or extended versions of papers presented at related conferences, are welcome. Submissions must not be currently under review for publication elsewhere. Conference papers may be submitted only if they are substantially extended (more than 50%), and must be referenced. All submitted papers will be peer-reviewed using the normal standards of CAEE, and accepted based on quality, originality, novelty, and relevance to the theme of the special section. By submitting a paper to this issue, the authors agree to referee one paper (if asked) within the time frame of the special section. 

Before submission, authors should carefully read the Guide for Authors available at https://www.elsevier.com/journals/computers-and-electrical-engineering/0045-7906/guide-for-authors 

Authors should submit their papers through the journal's web submission tool at https://www.editorialmanager.com/compeleceng/default.aspx by selecting “VSI-TinyML IS” under the “Article Type” tab. For additional questions, contact the Main Guest Editor. 

Important dates:

    Submissions Deadline: December 31, 2024
    First Reviews Due: March 30, 2025
    Revision Due: May 30, 2025
    Second Reviews Due/Notification: June 30, 2025
    Final Decision Due: July 31, 2025
    Tentative Publication Date: 4th quarter 2025