The Official Journal of the World Federation on Soft Computing (WFSC) http://www.softcomputing.org

Applied Soft Computing is an international journal promoting an integrated view of soft computing to solve real life problems. Soft computing is a collection of methodologies, which aim to exploit tolerance for imprecision, uncertainty and partial truth to achieve tractability, robustness and low solution cost. The focus is to publish the highest quality research in application, advance and convergence of the areas of Fuzzy Logic, Neural Networks, Evolutionary Computing, Swarm Intelligence and other similar techniques to address real world complexities.

Applied Soft Computing is a rolling publication: articles are published as soon as the editor-in-chief has accepted them. Therefore, the web site will continuously be updated with new articles and the publication time will be short.

Major Topics:

The scope of this journal covers the following soft computing and related techniques, interactions between several soft computing techniques, and their industrial applications:

    Evolutionary Computing
    Fuzzy Computing
    Hybrid Methods
    Immunological Computing
    Neuro Computing
    Swarm Intelligence
    Machine and Deep Learning
    Rough Sets

The application areas of interest include but are not limited to applications of soft computing to:

    Agricultural Machinery, Smart Farming
    Autonomous Reasoning
    Big Data, IoT, Edge Computing
    Combinatorial Optimization
    Data Mining
    Decision Support
    Engineering Design Optimization
    Fault Diagnosis
    Finance
    Human-Machine Interface
    Intelligent Agents
    Manufacturing Systems
    Power Electronics
    Multi-objective Optimization
    Power and Energy
    Process and System Control
    Robotics
    Security
    Sensor Systems
    Signal or Image Processing
    Software Engineering
    Supply Chain Economy
    System Identification and Modelling
    Telecommunications
    Time Series Prediction
    Extended Reality, Metaverse, Digital Twins
    Vision or Pattern Recognition

Authors are welcome to submit letters promoting original soft computing research to Applied Soft Computing's open access companion title, Systems and Soft Computing.

Special Issue on Intelligent Decision Making, Deep and Machine Learning, Generative AI to Empower Smart Production and Service
Día de Entrega: 2025-05-31

Deep and machine learning, swarm intelligence, big data analytics, generative artificial intelligence, and LLM (Large Language Model) are increasingly developed for intelligent decision making involved in smart production and service in various industrial contexts. To meet with various needs of different customers, paradigm is shifting from mass production and mass-customization towards personalization and flexibility for smart production and service. In addition to the challenges in real settings, more opportunities are made available by state-of-the-art soft computing and AI technologies to empower novel applications for smart production and service to enhance supply chain resilience and change the business ecosystem.

Guest editors:

Dr. Chen-Fu Chien, National Tsing Hua University, Taiwan;
Dr. Kanchana Sethanan, Department of Industrial Engineering, Khon Kaen University, Thailand;
Dr. Run-Liang Dou, Department of Information Management and Management Science, Tianjin University, China;
Dr. Rapeepan Pitakaso, Department of Industrial Engineering, Ubon Ratchathani University, Thailand;
Dr. Chia-Yu Hsu, Department of Industrial Management, National Taiwan University of Science and Technology, Taiwan

Manuscript submission information:

Flexible decisions and intelligent decision making involved in production and service processes, manufacturing networks, supply chain management, and industry ecosystem are critical to enhance the efficiency and effectiveness of human-system collaborations to empower smart production and service.

This special issue of the Applied Soft Computing aims to address research issues involved in shifting paradigms driven by the developments of intelligent decision making, deep and machine learning, swarm intelligence, big data analytics, generative artificial intelligence, and LLM for smart production and service in various industrial contexts. Empirical studies with technical and/or methodological advances to address realistic issues are encouraged. In particular, high-tech industries such as semiconductor industries consist of complex and lengthy manufacturing processes with tightly constrained processing technologies, reentrant process flows, sophisticated equipment, volatile demands, and high product mix. While big data is accumulated via the fully automated production and service facilities and supply chain management systems, various solutions and techniques can be developed to empower intelligent decision making to address new challenges in real time.

Scope of this Virtual Special Issue:

Topics to be covered include the application of the following artificial intelligence and soft computing methodologies and interactions between several soft computing techniques:

    Ant Colony Optimization  
    Artificial Intelligence  
    Big Data Analytics  
    Convolutional Neural Networks 
    Deep and Machine Learning  
    Evolutionary Computing  
    Fuzzy Computing  
    Generative AI  
    Hybrid Methods  
    Immunological Computing  
    Intelligent Decision-Making Technologies  
    LLM (Large Language Model)  
    Neuro Computing  
    Particle Swarm Optimization  
    Probabilistic Computing  
    Rough Sets  
    Wavelet 

to address critical, not restricted to the following aspects of smart production in real settings:

    Advanced equipment/process control (AEC/APC)  
    Automated material handling systems (AMHS), automatic guided vehicle (AGV)
    Intelligent Decision technologies for Real-time Decision
    Equipment diagnosis, Predictive maintenance, and Tool Health
    Factory modeling, analysis and performance evaluation
    Flexible Production Planning & Scheduling
    Industry 4.0 & Manufacturing Strategy
    Intelligent systems & Robots
    Manufacturing Intelligence & Manufacturing Informatics
    Mass personalization and customization
    Predictive Maintenance
    Smart Decision for Corporate Resource Planning & Allocation
    Sustainability and circular economy
    Virtual Reality (VR), Augmented Reality (AR), Mixed Reality (MR)
    Yield enhancement and e-Diagnosis

Important date:

Deadline for Submission: 31 May, 2025
Final Decision: 31 August, 2025

Special Issue on Soft Computing for Modern Engineering: Addressing Environmental Challenges
Día de Entrega: 2025-07-30

In the face of pressing environmental concerns and the need for responsible resource management, achieving sustainable engineering practices has become a central focus across various industries. Traditional engineering approaches often struggle with the inherent complexities of these challenges, which frequently involve multi-criteria decision-making and the need to balance environmental, economic, and social objectives. This special issue, titled "Soft Computing for Modern Engineering: Addressing Environmental Challenges", proposes to explore the growing potential of soft computing techniques as powerful tools to bridge this gap. Soft computing, encompassing methodologies like fuzzy logic, neural networks, and evolutionary algorithms, offers a unique ability to handle uncertainty and ambiguity - characteristics that are prevalent in real-world sustainability problems.

Guest editors:

Dr. Masoomeh Mirrashid
Abu Dhabi University, UAEmirrashid.research@adu.ac.ae

Prof. Abdollah Shafieezadeh
Ohio State University, USAshafieezadeh.1@osu.edu

Prof. Hosein Naderpour
Semnan University, Irannaderpour@semnan.ac.ir

Prof. Mahdi Kioumarsi
Oslo Metropolitan University, Norwaymahdik@oslomet.no

Special issue information:

This special issue will welcome original research articles and reviews that showcase the innovative application of soft computing methodologies in sustainable engineering.

Potential topics

include, but are not limited to:
Energy Systems Optimization: Leveraging fuzzy logic and neural networks for optimizing energy consumption in buildings and renewable energy integration.

Sustainable Materials Development: Utilizing evolutionary algorithms and fuzzy sets for designing eco-friendly materials and optimizing manufacturing processes.

Life Cycle Assessment (LCA): Employing machine learning techniques to analyze the environmental impact of products and systems throughout their life cycle.

Risk Management and Decision Support: Developing hybrid fuzzy-neural models for assessing environmental risks and supporting sustainable decision-making in engineering projects.

Smart Infrastructure Systems: Implementing soft computing techniques for intelligent control and optimization of sustainable infrastructure systems like transportation networks and water management.

Multi-Objective Optimization: Exploring how soft computing can handle multiple, often conflicting, objectives in sustainable engineering problems. This could involve optimizing cost, environmental impact, and performance simultaneously.

Uncertainty Modeling and Management: Highlighting the application of soft computing for dealing with inherent uncertainties and complexities in sustainability challenges. This could involve fuzzy logic for representing imprecise data or probabilistic models for risk assessment.

Data-Driven Sustainability Analysis: Showcasing the use of soft computing techniques for analyzing large datasets related to sustainability. This could include machine learning for identifying patterns in energy consumption data or using natural language processing to analyze sustainability reports.

Soft Computing for Policy and Regulation Development: Exploring how soft computing can inform the development of sustainable policies and regulations. This might involve using evolutionary algorithms to design incentive programs for sustainable practices or employing fuzzy logic to assess environmental compliance.

Soft Computing for Education and Awareness: Investigating the role of soft computing in promoting sustainability education and raising awareness. This could involve developing interactive learning platforms or using natural language generation to create engaging sustainability content.

Social Sustainability: Encouraging submissions that explore the intersection of soft computing and social aspects of sustainability, such as promoting equitable access to resources or fostering community engagement in sustainable development projects.

Life Cycle Thinking: Highlighting the use of soft computing for assessing the environmental, social, and economic impacts of products and systems throughout their entire life cycle. This could involve combining LCA methodologies with soft computing techniques.

Sustainable Urban Development: Welcoming research on how soft computing can contribute to creating sustainable and resilient cities. This could encompass traffic management systems, resource optimization in buildings, or smart grid applications.

Circular Economy: Exploring the use of soft computing for optimizing resource use and promoting circular economy principles in engineering design and manufacturing. This might involve designing for disassembly and recyclability or optimizing waste-to-resource conversion processes.

Climate Change Mitigation and Adaptation: Showcasing how soft computing can contribute to addressing climate change challenges. This could involve developing models for climate change impact assessment, designing strategies for mitigation and adaptation, and optimizing resource allocation for climate action initiatives.

Sustainable Concrete: Utilizing soft computing techniques to optimize the design, performance, and sustainability of concrete as a building material. This could include employing genetic algorithms and fuzzy logic to design low-carbon concrete mixes, using neural networks to predict the durability and lifespan of concrete structures under varying environmental conditions, or applying machine learning methods to enhance the recycling and reuse of concrete materials.

Special Issue on Robust and Secure AI Systems
Día de Entrega: 2025-07-31

The rapid development of AI has ushered in transformative possibilities across various sectors, such as transportation, robotics, and healthcare. However, this proliferation of AI technologies has brought complex safety and reliability challenges. Ensuring the robust deployment of AI systems and safeguarding them against adversarial attacks and unintended consequences are paramount concerns in the realm of AI research and application.

Guest editors:

Dr. Peilan Xu

Nanjing University of Information Science and Technology, School of Artificial Intelligence
Nanjing, 210044, China
E-mail: xpl@nuist.edu.cn 

Prof. Wenjian Luo
Harbin Institute of Technology Shenzhen, School of Computer Science and Technology
HIT Campus, Xili University Town, Shenzhen, 518055, China
E-mail: luowenjian@hit.edu.cn 

Dr. Hansheng Lei
The University of Texas Rio Grande Valley, Department
of Informatics and System Engineering
West University Blvd, SETB 1.506, UTRGV, Brownsville, TX 78521
E-mail: hansheng.lei@utrgv.edu 

Special issue information:

Aim and Scope:

The rapid development of AI has ushered in transformative possibilities across various sectors, such as transportation, robotics, and healthcare. However, this proliferation of AI technologies has brought complex safety and reliability challenges. Ensuring the robust deployment of AI systems and safeguarding them against adversarial attacks and unintended consequences are paramount concerns in the realm of AI research and application. 

Recently, significant strides have been made in advancing the frontiers of robust and secure intelligence. State-of-the-art attack techniques and defense methods play a vital role in improving the security of AI systems and protecting user data and privacy. Moreover, the concept of robust intelligence has emerged as a critical area of focus, which enables AI systems to perform well under uncertain environment, ensuring their stability and reliability against unforeseen challenges. These advances have enabled breakthroughs in areas, mitigating the risks associated with AI systems solving real world problems. 

Despite the remarkable progress, challenges persist. Ensuring that AI models are safe, robust, interpretable, and unbiased remains a pressing concern. Additionally, the vulnerability of AI systems to adversarial attacks and uncertain environment poses a significant threat, requiring robust and secure innovative solutions to fortify these systems against malicious manipulation. Addressing these challenges is central to creating trustworthy and secure AI systems that can be reliably deployed in real-world environments. 

The aims of this special issue are: (1) to bring together cutting-edge research that addresses the robustness and security challenges in AI, with a specific focus on robust and security intelligence. (2) to provide a platform for researchers and practitioners to propose innovative, practical, and implementable solutions and present their views on future research trends in building robust and secure intelligence systems.

Themes:

Following the development of artificial intelligence, the topics of this special issue will focus on the new robust and secure intelligence techniques and their applications. Topics of interest include, but are not limited to:

    Robust optimization and decision
    Robust AI architectures
    Adversarial attack and defense techniques on AI models
    Data and privacy-preserving techniques for AI models
    Secure training and deployment in distributed AI models
    Explainability and interpretability in robust AI 
    Human-AI collaboration and trust
    Real-world applications of robust and secure intelligence

Manuscript submission information:

Important Dates:

    Submission Deadline: July 31, 2025
    Final Date (Accept/Reject): November 30, 2025