Special Session 1：Hybrid Intelligence-Driven Optimization and Decision-Making for Complex Systems
Special Session Chairs
• Prof. Chang Liu, Shenyang Institute of Automation, Chinese Academy of Sciences (Email: changl@sia.cn)
• A/Prof. Bing Yan, Rochester Institute of Technology, USA
• A/Prof. Xincheng Zhong, Department of Computer Science, Changzhi University
Introduction
We are entering an era of complex giant systems characterized by deeply interconnected physical, social, and information systems. From flexible production in smart factories to holistic governance in smart cities, and from real-time scheduling in energy internet to emergency decision-making in major crises, the core challenge lies in achieving efficient, reliable, and interpretable optimization and decision-making in massive, dynamic, and uncertain environments. Traditional methods relying solely on mathematical models or purely data-driven approaches often face dilemmas of "model mismatch" or "black-box skepticism."
To address these challenges, Hybrid Intelligencehas emerged as a transformative paradigm that integrates data-driven intelligence, model-driven knowledge, and human cognition. It aims to achieve synergistic enhancement beyond the sum of its parts through interdisciplinary and multi-method integration, providing a novel methodological toolkit for tackling complex system decision-making problems.
This special session aims to provide a high-level platform for researchers and practitioners from academia and industry to exchange ideas on the cutting-edge topic of "Hybrid Intelligence-Driven Optimization and Decision-Making for Complex Systems." We focus on its theoretical foundations, paradigm innovations, key technologies, and representative applications. We warmly invite submissions from scholars worldwide to jointly explore the construction of next-generation smarter, more reliable, and more human-centric intelligent decision-making systems.
Topics of Interest
Topics include but are not limited to:
• Formal Theories and Modeling Frameworks for Hybrid Intelligence
• Unified Decision Theories Integrating Logic, Probability, and Learning
• Human-in-the-Loop Optimization and Interactive Machine Learning
• Neuro-Symbolic Reasoning and Explainable Hybrid Decision Models
• Deep Fusion Architectures Integrating Symbolic Rules and Neural Networks
• Multi-Agent Collaboration, Game Theory, and Swarm Intelligence Decision-Making
• Digital Twins and Dynamic Simulation-Deduction for Complex Systems
• Integration of Large Models (LLM/MLLM) with Optimization and Decision-Making
• Innovative Applications of Hybrid Intelligence Optimization in Smart Manufacturing, Energy and Power Systems, and Other Fields
• Architectures, Platforms, and Evaluation Methods for Hybrid Intelligent Decision Systems
Special Session 2：Special Session on Analysis, Modeling and Control with Complex Data
Special Session Chairs
• Prof. Shiyuan Han, Shandong Women’s University, Jinan, Shandong, China (Email: ai_hansy@sdwu.edu.cn)
• Prof. Jin Zhou, Shandong Women’s University, Jinan, Shandong, China
Introduction
With the development of information science and technology, many practical processes such as those relevant to the industry, transportation, electronics, metallurgy, and logistics, have undergone significant changes. These processes generate and store huge amounts of process data at every time instant of every day, containing all valuable state information of process operations and equipment. Using those data, both on-line and off-line, to directly predict the trend, evaluate performance and make decisions for complex system, would be very significant, especially under the lack of accurate supervision. However, the complex characteristics of those data, such as high dimension, nonlinearity, heterogeneity, and uncertainty, lead to the ineffectiveness of the existing analysis, modeling and control algorithms to deal with. This special issue is focusing on the latest development, trends, and novel techniques of analysis, modeling and control algorithms in decision-making systems and their applications.
Topics of Interest
Topics include but are not limited to:
• Data mining
• Pattern recognition
• Data modeling and optimization
• Data driven control
• Decision making system
• Knowledge discovery
• Theory for security and cybernetics
• Applications related to the above topics
Special Session 3：Biomedical and Health Informatics
Special Session Chairs
• A/Prof. Shengpeng Yu, Shandong Women’s University, Jinan, Shandong, China (Email: ysp@sdwu.edu.cn)
• A/Prof. Zhen Cui, Shandong Women’s University, Jinan, Shandong, China
Introduction
This session provides a comprehensive overview of the pillars of Biomedical and Health Informatics. We bring together diverse research areas, including Machine Learning, Healthcare Knowledge Reasoning, and Mobile Health, to discuss how digital systems can improve health outcomes. Key topics include data visualization, interoperability standards, and the human factors that drive the adoption of clinical and health information systems.
Topics of Interest
Topics include but are not limited to:
• Data Mining, Machine Learning, and Artificial Intelligence
• Big Data Analytics
• Information Retrieval, Ontologies, Natural Language Processing, and Text Miningn
• Biomedical Image Analysis
• Healthcare Knowledge Representation & Reasoning
• Data Visualization
• Data Interoperability and Health Information Exchange
• Human-computer Interaction and Human Factors
• Clinical and Health Information Systems
• Consumer Informatics and Personal Health Records
• Electronic Medical/Health Records and Standards
• Mobile Health
• Clinical Decision Support
Special Session 4：LLM-Enhanced and Data-Driven Dynamic Optimization and Its Applications
Special Session Chairs
• Prof. Wei Song, Jiangnan University, Wuxi, China. (Email: songwei@jiangnan.edu.cn)
• Prof. Yinan Guo, China University of Mining and Technology, Beijing, China. (Email: nanfly@126.com)
• Prof. Weiguo Sheng, Hangzhou Normal University, Hangzhou, China. (Email: weiguouk@hotmail.com)
Introduction
With the rapid development of large language models (LLMs) and intelligent data technologies, LLM-enhanced and data-driven dynamic optimization has emerged as a cutting-edge and crucial approach in various fields, such as industrial production, energy management, transportation systems, and smart services. Traditional optimization algorithms struggle to handle the high complexity, strong uncertainty, dynamic changes, and unstructured information in modern systems. In contrast, by effectively leveraging useful data and the powerful capability of LLMs in natural language understanding, knowledge reasoning, and unstructured data processing, LLM-enhanced dynamic optimization can achieve more accurate, flexible, and efficient optimization results.
This special session aims to bring together researchers, engineers, and industry practitioners to discuss the latest research progress, challenges, and practical applications in the field of LLM-enhanced and data-driven dynamic optimization. We encourage submissions that cover theoretical research, algorithm design, and real-world case studies, with a particular focus on the integration of LLM models, real-time data processing, and dynamic optimization algorithms.
Topics of Interest
Topics include but are not limited to:
• Data-Driven and/or LLM-Enhanced Dynamic Optimization
• Data-Driven and/or LLM-Enhanced Dynamic Multi-Objective Optimization
• Data-Driven and/or LLM-Enhanced Dynamic Constrained Optimization
• Data-Driven and/or LLM-Enhanced Dynamic Constrained Multi-Objective Optimization
• LLM-Enhanced Knowledge Integration for Dynamic Optimization
• Data-Driven and/or LLM-Enhanced Architecture for Large-Scale Dynamic Optimization
• Data-Driven and/or LLM-Enhanced Optimization Framework for Dynamic Route Planning
• LLM-Based Dynamic Constrained Optimization in Resource Allocation
• Industrial Applications of LLM-Enhanced Dynamic Optimization
• Dynamic Multi-Objective Optimization in Smart Grids, Robotics, and Autonomous Systems with LLM Enhancement
• Data-Driven and/or LLM-Enhanced Dynamic Optimization of Transportation Systems
• LLM-Enhanced Uncertainty Handling in Dynamic Optimization
• Real-Time Data Processing for LLM-Enhanced Dynamic Optimization
Special Session 5：Data-Driven Evolutionary Neural Architecture Search and Generative Model Optimization for Complex Systems
Special Session Chairs
• Prof. Yu Xue, Nanjing University of Information Science and Technology, China (xueyu@nuist.edu.cn)
• Dr. Pengcheng Jiang, Nanjing University of Information Science and Technology, China (pcjiang@nuist.edu.cn)
• Prof. Mohamed Wahib, RIKEN Center for Computational Science, Japan (mohamed.attia@riken.jp)
• Prof. Peng Chen, RIKEN Center for Computational Science, Japan (peng.chen@riken.jp)
Introduction
Recent advances in data-driven learning and optimization are reshaping the design of intelligent models for complex systems. In applications such as intelligent manufacturing, autonomous systems, and resource-constrained AI, model design often involves large search spaces, expensive evaluations, and multiple conflicting objectives, which make manual design increasingly difficult. Neural Architecture Search (NAS) and evolutionary optimization provide effective solutions for automated model design in such settings. In particular, evolutionary NAS has shown strong potential in handling complex search spaces, heterogeneous design variables, and multi-objective requirements. Meanwhile, generative models, including GANs and diffusion models, have introduced new optimization challenges in architecture design, training strategy adaptation, and performance-efficiency trade-off analysis.
This special session focuses on data-driven evolutionary optimization methods for neural and generative models in complex systems. It welcomes recent advances in evolutionary NAS, optimization for GANs and diffusion models, surrogate-assisted and Bayesian NAS, LLM-assisted model optimization, and multi-objective model design. The session aims to provide a focused forum for researchers and practitioners to discuss theories, algorithms, and applications at the intersection of machine learning, evolutionary computation, and intelligent optimization.
Topics of Interest
Topics include but are not limited to:
• Data-Driven Evolutionary Neural Architecture Search
• Evolutionary Optimization for Deep Neural Network Design
• Multi-Objective Neural Architecture Search
• Bayesian Optimization and Surrogate-Assisted NAS
• Evolutionary NAS for Generative Adversarial Networks
• Diffusion Model Architecture Search and Optimization
• Diffusion Models for Optimization and Model Design
• LLM-Assisted Neural Architecture Search and Optimization
• Data-Driven Decision Paradigms for Neural and Generative Systems
Special Session 6：AI-driven Scheduling Optimization, Supply Chain Management and Industrial Internet
Special Session Chairs
• Prof. Pengyu Yan, University of Electronics and Science Technology of China, Chengdu China (Email: yanpy@uestc.edu.cn)
• A/Prof. Weidong Lei, Xi’an University of Science and Technology
• A/Prof. Xiaohui Li, Chang’an University, Xi’an China
Introduction
In the era of digital transformation, efficient scheduling and supply chain management are key drivers for industrial competitiveness. The optimization of resource allocation, logistics networks, and energy supply chains through advanced scheduling algorithms and supply chain intelligence is fundamentally reshaping modern industries. As global supply networks become increasingly complex, the need for sophisticated optimization techniques, real-time decision support, and intelligent coordination mechanisms has become critical. This special session invites researchers and industry experts to explore scheduling optimization techniques, supply chain management innovations, and their integration with Industrial Internet technologies. We seek submissions that delve into theoretical frameworks, optimization algorithms, practical implementations, and real-world case studies, with a strong emphasis on pioneering approaches to solving complex scheduling and supply chain challenges in sustainable and efficient industrial systems.
Topics of Interest
Topics include but are not limited to:
• Scheduling Algorithms and Optimization Techniques
• Supply Chain Network Design and Optimization
• Logistics Planning and Route Optimization
• Resource Allocation in Industrial Systems
• Inventory Management and Optimization
• Demand Forecasting and Supply Planning
• Production Scheduling and Job Shop Optimization
• Green Logistics and Sustainable Supply Chain Management
• Real-time Monitoring and Supply Chain Visibility
• Integration of IIoT with Supply Chain Decision Support