Neural Computing & Applications is an international journal which publishes original research and other information in the field of practical applications of neural computing and related techniques such as genetic algorithms, fuzzy logic and neuro-fuzzy systems.  

All items relevant to building practical systems are within its scope, including but not limited to:

    adaptive computing
    algorithms
    applicable neural networks theory
    applied statistics
    architectures
    artificial intelligence
    benchmarks
    case histories of innovative applications
    fuzzy logic
    genetic algorithms
    hardware implementations
    hybrid intelligent systems
    intelligent agents
    intelligent control systems
    intelligent diagnostics
    intelligent forecasting
    machine learning
    neural networks
    neuro-fuzzy systems
    pattern recognition
    performance measures
    self-learning systems
    software simulations
    supervised and unsupervised learning methods
    system engineering and integration

Featured contributions fall into several categories: Original Articles, Review Articles, Book Reviews and Announcements.
The Original Articles will be high-quality contributions, representing new and significant research, developments or applications of practical use and value.  They will be reviewed by at least two referees. 

FOUNDING EDITOR
Howard James

JOURNAL ADMINISTRATOR
Tanya Daly, United Kingdom

For all queries relating to papers after submission, please contact the Journal Editorial Office via “contact us” at Editorial Manager.

Special Issue on Artificial Intelligence of Things for Future Networks and Service Management
Submission Date: 2024-08-31

Aims, Scope and Objective:

Future networks like 5G networks, space-air-ground integrated networks, and large-scale distributed networks, will face numerous innovations and improvements. With the large-scale deployment of Internet of Things (IoT) applications, millions of edge devices are connected to the Internet, to provide high-quality services for people’s digital lives. IoT, nevertheless, poses difficulties in existing networks to meet the quality of experience of subscribers, and traditional communication and computing approaches might fail to meet future network requirements.

Recently, as a collaborative application of artificial intelligence (AI) and IoT techniques, Artificial Intelligence of Things (AIoT), has been propsoed to improve the management and optimization of future networks. The introduction of AIoT can boost the network to monitor the traffic in real time, quickly identify abnormalities, and dynamically adjust the configuration, thereby ensuring the high-speed and reliable transmission. For example, for complex networks with high loads and constrained resources, the AI algorithm, e.g., the reinforcement learning can optimize the resource allocation and scheduling to meet the future network’s requirements. Besides, deep learning methods can also detect and respond to potential dynamics in real-time so that proactive measures can be taken to ensure the network performance. Further, AIoT can also facilitate the implementation of advanced authentication and access control mechanisms, to ensure the integrity and privacy of data through IoT devices.

AIoT provides new ideas for designing and optimizing future networks by integrating AI and IoT, which would bring the intelligent decision-making, efficient communication, and precise management of connected devices. This special issue will focus on, but not limited to, the latest research advents in designing, evaluating, and optimizing future networks by the AIoT technique.

The topics of interest include, but are not limited to:

    Designing, implementation, and optimization of future networks by AIoT
    Intelligent management and efficient routing in future networks by AIoT
    Large-scale data processing and analytics for future networks
    AI empowered communication optimization in future networks
    Cloud-edge-terminal collaboration-enabled AIoT in future networks
    Trusted, secure, and privacy computing system designing for AIoT in future networks
    Privacy and anonymity for future network applications
    AIoT-enabled techniques and applications in future networks
    AIoT-enabled modeling, simulation, and analytics for future networks
    Blockchain-eanbled AIoT in future networks

Guest Editors:

Prof. Li Zhu (Lead Guest Editor), Beijing Jiaotong University, China, lizhu@bjtu.edu.cn
Prof. Mianxiong Dong, Muroran Institute of Technology, Japan, mx.dong@csse.muroran-it.ac.jp
Prof. Jie Feng, Xidian University, China, fengjie@xidian.edu.cn
Prof. F. Richard Yu, Carlton University, Canada, Richard.Yu@carleton.ca
Dr. Mian Ahmad Jan, University of Sharjah, United Arab Emirates; mjan@sharjah.ac.ae

Manuscript submission deadline: 31st August 2024

Special Issue on Machine Learning and Big Data Analytics for IoT Security and Privacy (SPIOT 2023)
Submission Date: 2024-10-30

The "Internet of Things" heralds the connections of a nearly countless number of devices to the internet thus promising accessibility, boundless scalability, amplified productivity and a surplus of additional paybacks. The hype surrounding the IoT and its applications is already forcing companies to quickly upgrade their current processes, tools, and technology to accommodate massive data volumes and take advantage of insights. Since there is a vast amount of data generated by the IoT, a well-analysed data is extremely valuable. However, the large-scale deployment of IoT will bring new challenges and IoT security is one of them. The philosophy behind machine learning is to automate the creation of analytical models in order to enable algorithms to learn continuously with the help of available data. Continuously evolving models produce increasingly positive results, reducing the need for human interaction. These evolved models can be used to automatically produce reliable and repeatable decisions. Today's machine learning algorithms comb through data sets that no human could feasibly get through in a year or even a lifetime's worth of work. As the IoT continues to grow, more algorithms will be needed to keep up with the rising sums of data that accompany this growth. One of the main challenges of the IoT security is the integration with communication, computing, control, and physical environment parameters to analyse, detect and defend cyber-attacks in the distributed IoT systems.

The 4th International Conference on Machine Learning and Big Data Analytics for IoT Security and Privacy (SPIOT 2023) is an international conference dedicated to promoting novel theoretical and applied research advances in the interdisciplinary agenda of Internet of things. This special issue includes selected papers (with no less than 60% new content of the journal version) from SPIoT 2023, Oct. 20-21, 2023, Fuyang, Anhui, as well as an open call.

Topics of interests include, but are not limited to:

    Novel machine learning and big data analytics methods for IoT security
    Big data analytics/machine learning/deep learning for IoT security such as smart grid security analytics
    Data mining and statistical modelling for the secure IoT
    Machine learning and big data analytics architectures for IoT security
    Machine learning based security detecting protocols
    Machine learning experiments, test-beds and prototyping systems for IoT security
    Analytics and machine learning applications to IoT security
    Data based metrics and risk assessment approaches for IoT
    Data confidentiality and privacy in IoT
    Authentication and access control for data usage in IoT
    Data-driven co-design of communication, computing and control for IoT security
    Big data analytics/machine learning/deep learning edge/fog security
    Emerging standards for IoT security

Guest Editor

Jinghua Zhao, University of Shanghai for Science and Technology, China, zhaojinghua@usst.edu.cn

Important Dates

Manuscript Due:             30th October 2024
First Round of Reviews:  15th December 2024
Final Decision:                30th January 2025

Special Issue on AI Techniques for Optimal Control and Operation of Modern Power Systems
Submission Date: 2024-11-01

The control and operation of modern power systems can greatly benefit from the application of various cutting-edge artificial intelligence (AI) techniques. Reinforcement Learning (RL) offers an exciting opportunity to optimize control actions, such as load shedding and generation dispatch, by enabling systems to learn optimal strategies through interaction with the environment. Generative adversarial networks (GANs) have shown promise in generating synthetic power system data, facilitating improved system modeling accuracy and supporting decision-making processes. Deep neural networks (DNNs) are effective tools for tasks such as load forecasting, fault detection, generation control and power system stability analysis, thanks to their ability to extract complex patterns and relationships from large datasets. Long short-term memory (LSTM) networks, with their focus on time-series data analysis, can be employed for short-term load forecasting and real-time prediction of power system parameters. Convolutional neural networks (CNNs) excel in processing spatial data and can be utilized for fault detection and classification based on images captured by phasor measurement units (PMUs) or overhead line inspections. Hybrid models, which combine different AI techniques, offer the potential to enhance the accuracy and effectiveness of power system control and operation. Moreover, natural language processing (NLP) techniques can extract valuable insights from textual data, aiding decision-making in areas like maintenance and incident reports.

Other commonly employed AI approaches in power system applications includes expert systems, fuzzy logic systems, adaptive fuzzy logic systems, artificial neural networks (ANN), adaptive-neuro fuzzy inference systems (ANFIS), support vector machines (SVMs), decision trees, and evolutionary computing, among others. These techniques have proven effective in decision-making and control actions, supporting secure and stable operation of power systems. However, there remains a vast array of emerging AI techniques that have not been thoroughly explored or applied in power system operation and control applications. These include deep learning, reinforcement learning, Blockchain, cloud computing, cognitive AI, explainable AI, transfer learning, convolutional neural networks (CNNs), global optimization, meta-heuristics based control strategies and hybrid algorithms techniques. These promising avenues hold potential for further advancements in power system operation and control, awaiting in-depth exploration and practical application. By leveraging these advanced AI techniques, power systems can achieve improved efficiency, reliability, and sustainability. This issue targets to encourage the latest advances in the field of utilization of AI techniques for the control and operation of modern power systems, enabling control engineers to maximize the use of engineering assets in close alignment with available infrastructure and technical operating conditions.

Scope

This topical collection will cover a wide range of topics related to the application of AI techniques in power systems, including but not limited to:

    AI-based control strategies for power system stability and reliability.
    Machine learning approaches for demand response and load forecasting.
    Deep learning techniques for fault detection, diagnosis, and self-healing in power systems.
    Reinforcement learning for optimal power dispatch and economic operation.
    AI-driven predictive maintenance and condition monitoring of power system assets.
    Data analytics and AI methods for grid integration of renewable energy sources.
    AI applications in smart grid operations and management.
    Cybersecurity and AI-based anomaly detection for power system protection.
    Evolutionary algorithms, swarm intelligence, nature and biologically inspired meta-heuristics based control strategies for AGC/LFC/AVR, etc.

Guest Editors

Dr. Yogendra Arya (Lead Guest Editor), Department of Electrical Engineering, J.C. Bose University of Science & Technology, YMCA, Faridabad, India, yarya@jcboseust.ac.in
Dr.  Sandeep Dhundhara, Department of Basic Engineering, COAE&T, CCS Haryana Agricultural University, Hisar, Haryana, India, sandeep08@hau.ac.in
Dr. Yajvender Pal Verma, Department of Electrical & Electronics Engineering, University Institute of Engineering and Technology, Panjab University, Chandigarh, India, yp_verma@pu.ac.in

Manuscript submission deadline: 1st November 2024

Special Issue on AI for Space: Theories, Models and Applications
Submission Date: 2024-11-30

Aims, Scope and Objective 

Artificial Intelligence (AI) is becoming increasingly important in the space sector. Indeed, AI-based systems are contributing to several space operations including mission planning, big space data collection and processing, autonomous navigation, spacecraft monitoring and so on. The International Workshop on “The use of Artificial Intelligence for Space Applications” has been co-organized by the University Mediterranea of Reggio Calabria (Italy), the University of Arizona Space Systems Engineering Laboratory (SSEL) (USA), the Italian Space Agency (ASI) (Italy), the European Space Agency - ESA’s Φ-lab (Italy) and Thales Alenia Space (Italy) and was held in Reggio Calabria, Italy, in September 1-3, 2022.

This Topical Collection intends to examine the “dialogue” between AI and space and aims to report new theories, models and applications in this field, by including expanded versions of selected workshop and also newly innovative papers.

The topics of interest include, but are not limited to:

    AI for space and aerospace applications
    AI for fault detection and diagnosis in space applications
    AI for studying astronautics’ neurodegeneration
    AI and learning systems for satellite communications
    AI and learning systems for space robotics
    AI for earth observation
    Meta-learning for space applications
    IoT for space applications
    Space informatics
    Human-machine interaction systems in space applications
    Intelligent and optimal control for aerospace systems
    Intelligent search and optimization methods in aerospace applications
    Bio-inspired solutions for automatic navigation in space applications
    Sensors for space applications
    Space data processing for ground-based and onboard analysis

Guest Editors

Dr. Cosimo Ieracitano (Lead Guest Editor), University Mediterranea of Reggio Calabria, Italy, cosimo.ieracitano@unirc.it
Prof. Nadia Mammone, University Mediterranea of Reggio Calabria, Italy, nadia.mammone@unirc.it
Dr. Piergiorgio Lanza, Thales Alenia Space, Italy, Piergiorgio.Lanza@thalesaleniaspace.com
Prof. Fei Gao, Beihang University, China, youfeigao@buaa.edu.cn
Dr. Bertrand Le Saux, European Space Agency, Φ-lab, Italy, Bertrand.Le.Saux@esa.int
Prof. Roberto Furfaro, University of Arizona, USA, robertof@arizona.edu
Prof. Francesco Carlo Morabito, University Mediterranea of Reggio Calabria, Italy, morabito@unirc.it

Manuscript submission deadline: 30th November 2024

Special Issue on Neural Computing in the Advancement of Automated Connected & Electrical (ACE) Vehicles
Submission Date: 2024-11-30

Aims and Scope:

Automated Connected & Electrical (ACE) vehicle technologies are rapidly transforming the transportation sector and are a cornerstone in the development of future smart cities. The journey from research labs to real-world application, however, is fraught with challenges, including extensive time and financial investments, and stringent regulatory environments. Crucially, the evolution of ACE technologies is increasingly reliant on advanced computational methods, including neural networks, fuzzy logic, and deep learning, to enhance predictive analytics, system modeling, pattern identification, and more.

This Special Issue seeks to explore how neural computing and related approaches can optimize the development, testing, and implementation of ACE vehicle technologies. We invite contributions that not only focus on ACE vehicles but also highlight the application of neural computing, machine learning, and intelligent systems in this domain.

Topics of Interest include, but are not limited to:

    Integration of Neural Networks and Deep Learning in ACE Vehicle Development
    Cooperative Driving Automation (CDA) Enhanced by AI Techniques
    AI-Driven Edge-Computing for CAV Operations
    Neural Computing in CAV-Infrastructure Integration
    Intelligent Vehicle Control Strategies Using Machine Learning
    Advanced Diagnostics and Forecasting in ACE Vehicles
    V2X Communications Optimized through Intelligent Algorithms
    5G Technologies in ACE Vehicles Enhanced by Neural Computing
    Simulation and Validation of Automated Driving Parameters Using AI
    Neural Network-Based Methodologies for Test Scenario Generation
    Hardware/Vehicle in the Loop Simulation with Intelligent Systems
    Practical Systems Modeling in ACE Technologies
    Real-World Case Studies Demonstrating the Application of Neural Computing in ACE Vehicles

Guest Editors:

Yang Liu, Chalmers University of Technology, Sweden, liuy@chalmers.se
Tom Shi, University of Wisconsin-Milwaukee, USA,  tomshi@uwm.edu
Xiaopeng (Shaw) Li, University of Wisconsin-Madison, USA, xli2485@wisc.edu
Xiaobo Qu, Tsinghua University, China, xiaobo@tsinghua.edu.cn

Manuscript submission deadline: 30th November 2024

This topical collection is connected to SDG 11: Sustainable cities & communities

Special Issue on Explainable Sequential Decision-Making
Submission Date: 2025-01-01

Aims and Scope

As we work with AI and rely on AI for more and more decisions that influence our lives, the research area of explainable AI (XAI) has rapidly developed, with goals such as increasing trust, enhancing collaboration, and enabling transparency in AI. The focus of this topical collection is on explainable sequential decision-making – XAI for systems that are required to make a sequence of decisions to achieve their goals or objectives. This stands in contrast to the substantial existing work on interpretable machine learning, which generally focuses on the single input-output mappings of "black box" models such as neural networks. While such ML models are an important tool, intelligent behavior extends over time and needs to be explained and understood as such. We may have superhuman chess agents, but can they teach us how to play? We may have search & rescue robots, but can we effectively and efficiently communicate with them in the field?

This topical collection targets high-quality original papers covering all aspects of explainable sequential decision-making. Manuscripts that extend a previous conference or workshop publication are welcome, provided that there is a significant amount (at least 30%) of new material in the submission. Relevant topics include, but are not limited to, the following:

    Explainable/interpretable/intelligible reinforcement learning
    Explainable planning and search
    Explainability in Multi-Agent Systems
    Explainability for and through negotiations or argumentation
    Extended explanatory dialogue with users
    Modeling users over extended interactions
    Explanation-aware sequential decision-making
    Foundational frameworks for formalizing and evaluating explainable agency in sequential decision-making settings
    Integration of explainable agents and explainable deep learning, e.g. when DL models are guiding agent behaviors
    User interfaces/visualizations for explaining agent behavior, learning or planning
    Evaluation methods for explainable sequential decision-making systems
    Explainability for embodied systems/robotics
    Other practical applications for explainability in sequential or goal-oriented tasks, e.g. in planning/scheduling, in pathfinding, etc.
    Policy/plan summarization
    Cognitive theories
    Empirical studies in explainable sequential decision making

Guest Editors

Hendrik Baier (Lead Guest Editor), Eindhoven University of Technology, The Netherlands, h.j.s.baier@tue.nl
Sarath Sreedharan, Colorado State University, USA, ssreedh3@colostate.edu

Manuscript submission deadline: 1st January 2025

Special Issue on Multi-Objective Decision Making 2024 (MODeM 2024)
Submission Date: 2025-02-17

Building on two previous successful topical collections (TCs), we are delighted to invite submissions to a new topical collection of Neural Computing and Applications (NC&A, impact factor 6.0) on Multi-Objective Decision Making 2024 (MODeM 2024).

Previous topical collections in this series were hosted in:

    Neural Computing and Applications - TC on MODeM 2023 (in progress)
    Journal of Autonomous Agents and Multi-Agent Systems - TC on MODeM (completed in 2023)

Explicitly modelling multiple objectives can be essential for decision support, explainability, and human-AI alignment. As such, there has been a growing awareness of the need for automated and assistive decision making systems to move beyond single-objective formulations when dealing with complex real-world issues, which invariably involve multiple competing objectives. In this topical collection, we aim to provide a platform for original research in multi-objective decision making using AI.

This topical collection targets high-quality original papers covering all aspects of multi-objective decision making, including, but not limited to, the list of topics below. Manuscripts that extend a previous conference or workshop publication are welcome, provided that there is a significant amount of new material in the submission (i.e., the manuscript should contain at least 50% new material).

Please note that manuscripts submitted to this TC should have a clear link to artificial intelligence and/or agent-based systems - manuscripts without a clear link to these areas will be desk rejected without being sent for review.

Topics

The following is a non-exhaustive list of topics that we would like to cover in the topical collection:

    Multi-objective/multi-criteria/multi-attribute decision making
    Multi-objective reinforcement learning
    Multi-objective planning and scheduling
    Multi-objective multi-agent decision making
    Multi-objective game theory
    Multi-objective/multi-criteria/multi-attribute utility theory
    Preference elicitation for MODeM
    Social choice and MODeM
    Multi-objective decision support systems
    Multi-objective metaheuristic optimisation (e.g., evolutionary algorithms) for autonomous agents and multi-agent systems
    Multi-objectivisation
    Human-AI alignment through multi-objective modelling
    Ethical AI through multi-objective modelling
    Explainable AI through multi-objective modelling
    Interactive systems for MODeM
    Applications of MODeM
    Interdisciplinary work (MODeM research that relates to other fields)
    New benchmark problems for MODeM

Guest Editors

Roxana Rădulescu (Lead Guest Editor), Utrecht University & Vrije Universiteit Brussel, r.t.radulescu@uu.nl
Patrick Mannion, University of Galway
Pieter Libin, Vrije Universiteit Brussel

Please direct queries about the NC&A MODeM 2024 TC to the Lead Guest Editor at r.t.radulescu@uu.nl

Timeline

Submission deadline: 17th February 2025

Manuscript submissions will be considered for publication in the NC&A MODeM 2024 TC on a continuous basis until the submission deadline. Submissions accepted for publication before the completion of the TC will be available on the journal website shortly after acceptance.