The rapid evolution of digital technologies and IoT infrastructures is transforming urban landscapes, healthcare delivery, sports performance, environmental monitoring, and wireless sensing. Massive real-time data streams from smart sensors, connected devices, and social platforms present unique opportunities to optimize resource management and enhance user engagement across diverse sectors. However, extracting actionable insights from such heterogeneous data requires advanced hybrid models that combine structured domain knowledge—such as urban planning theories, medical ontologies, sports science, and environmental policies—with state-of-the-art data-driven techniques including machine learning, deep learning, and large language models.

The primary objective of this special session is to advance research and practice at the intersection of domain-specific knowledge and AI-driven methodologies. By synergizing knowledge representation methods, such as ontologies, semantic networks, and rule-based systems, with robust data analytics, the session seeks to address complex challenges in smart systems. This integration is aimed at enhancing model interpretability, robustness, and predictive performance while ensuring adaptability to dynamic, real-world scenarios.

The special session invites submissions addressing, but not limited to, the following areas:

  • Theoretical Foundations
    • Knowledge representation for smart system data across urban, healthcare, sports, environmental, and sensing domains, including approaches like ontologies and semantic networks.
    • Conceptual frameworks that connect static domain knowledge with the dynamics of real-time sensor and social data.
    • Theoretical models of human-system interactions and decision-making processes in smart environments.
  • Methodological Innovations
    • Hybrid approaches that integrate knowledge graphs with neural networks for predictive analytics in smart cities, healthcare systems, sports performance, rail transit management, and environmental monitoring.
    • Multi-source data fusion techniques that combine text, sensor outputs, imagery, and social media data under domain-specific guidance.
    • Knowledge-enhanced reinforcement learning strategies for adaptive control and operational optimization of smart systems.
    • Transfer learning methodologies across diverse domains that leverage shared knowledge bases to identify common patterns in behavioral and sensor data.
  • Applications in Smart Domains
    • Smart Cities: Intelligent urban planning, real-time infrastructure monitoring, energy management, and improved citizen engagement through integrated data analytics.
    • Smart Healthcare: Personalized medical interventions, early-diagnosis systems, and remote patient monitoring driven by the integration of sensor and clinical data insights.
    • Smart Sports: Data-driven athlete performance analytics, injury risk assessment, and immersive fan experiences generated by real-time statistics and behavioral analysis.
    • Environmental Monitoring: AI-driven models for initiatives aimed at carbon neutrality, controlling carbon emissions, and promoting sustainable energy utilization.
    • Rail Transit: Advanced transportation systems that incorporate predictive maintenance, intelligent passenger flow prediction, and enhancements in operational safety.
    • Wireless Sensing: Pervasive and non-invasive sensing solutions for security monitoring, environmental assessments, and dynamic context recognition.
  • Ethical and Societal Considerations
    • Strategies for bias mitigation and fairness in AI models that span cross-domain applications.
    • Privacy-preserving techniques and data security measures in the collection, analysis, and deployment of smart system data.
    • Development of legal and ethical frameworks to ensure the responsible implementation of AI in both public and private sectors.
  • Surveys and Future Directions
    • Systematic reviews on the integration of knowledge and data-driven AI in smart cities, healthcare, sports, and environmental computing.
    • Establishment of benchmarking datasets and evaluation metrics tailored for multidisciplinary smart system applications.
    • Insights into next-generation AI paradigms and speculative directions for merging behavioral, sensory, and smart domain data.

Important Dates

  • Special Session Papers Submission: 15 July 2025
  • Acceptance Notification: 15 August 2025
  • Author Registration: 1 September 2025
  • Camera-Ready Submission: 1 September 2025
  • Conference Date: 16-18 Oct 2025

Paper submission instruction

Paper submission system is available at: https://cmt3.research.microsoft.com/BESC2025.

All papers will be reviewed by the Program Committee on the basis of technical quality, relevance to BESC 2025, originality, significance and clarity.

Please note:

  • All submissions should use IEEE two-column style. Templates are available from here.
  • All papers must be submitted electronically through the paper submission system in PDF format only. BESC 2025 accepts special session papers in 6 pages. The page count excludes the references.
  • Paper review will be double-blind, and submissions not properly anonymized will be desk-rejected without review.
  • Submitted papers must not substantially overlap with papers that have been published or that are simultaneously submitted to a journal or a conference with proceedings.
  • Papers must be clearly submitted in English and will be selected based on their originality, timeliness, significance, relevance, and clarity of presentation.
  • Submission of a paper should be regarded as a commitment that, should the paper be accepted, at least one of the authors will register and attend the conference to present the work.
  • Accepted papers will be submitted for inclusion into IEEE Xplore subject to meeting IEEE Xplore’s scope and quality requirements and indexed by EI. Top quality papers after presented in the conference will be selected for extension and publication in several special issues of international journals, e.g., World Wide Web Journal (Springer), Web Intelligence (IOS Press), Social Network Analysis and Mining (Springer), Human-Centric Intelligent Systems (Springer), Natural Language Processing (Elsevier), etc.
  • The use of artificial intelligence (AI)–generated text in an article shall be disclosed in the acknowledgements section of any paper submitted to an IEEE Conference or Periodical. The sections of the paper that use AI-generated text shall have a citation to the AI system used to generate the text.

Organizing Committee

Special Session Chairs
  • Prof. Imad Rida, Université de Technologie de Compiègne, France
  • Prof. Rui Wang, Shanghai University, China
  • Dr. Wei Zhou, Cardiff University, UK
  • Dr. Xianxun Zhu, Shanghai University, China (Contact: [email protected])

Program Committee Members
  • Prof. Jiancun Zuo, Shanghai Polytechnic University, China
  • Prof. Xiangyang Wang, Shanghai University, China
  • Prof. Lizhen Shao, Beijing University of Science and Technology, China
  • Dr. Xiaoshuai Hao, Beijing Academy of Artificial Intelligence, China
  • Dr. Qiang Zhao, Shanghai Youyun Information Technology Co., Ltd., China
  • Dr. Xiaohan Yu, Macquarie University, Australia
  • Dr. Hengyu Liu, Aalborg University, Denmark
  • Dr. Hui Chen, Macquarie University, Australia