Data Driven Discovery of Cyber Physical Systems

The increasing complexity and the distributed nature of modern systems (e.g. power generation plants, manufacturing processes, aircraft and automobiles) have provided traction for important research agendas, such as Cyber Physical Systems (CPSs). Cyber-physical systems (CPS), including mobile CPS and Internet of Things (IoT), embed software into the physical world. They can be used for numerous critical applications in a wide spectrum of fields, such as aerospace, automotive, chemical processes, civil infrastructure, consumer appliances, energy, entertainment, healthcare, manufacturing, transportation, and so forth, have become a core transdisciplinary area of research, both in industry and academia. Cyber-physical systems have proved to present new challenges to modeling due to their intrinsic complexity arising from the tight coupling of computation, communication and control with physical systems.

This special issue is focused on the role of data and data analytics in in CPS Monitoring, Control, Safety, Security and Service Sustainability. It covers applications of machine learning and big data analytics to various CPS problems, and also discusses the security and privacy problems associated with machine learning and big data. This Special Issue solicits high-quality original research and survey papers with consolidated and thoroughly evaluated research on various aspects of Data Driven Discovery in CPS Applications. This Special Issue will serve as a comprehensive collection of the current state-of-the-art technologies within the context. Topics of interest include (but are not limited to):

• 
  New data-driven CPS model description and modelling techniques

• 
  Robust data-driven optimization algorithms for CPSs

• 
  Unified framework for CPS formulation and analysis

• 
  Advanced approaches for CPS monitoring

• 
  Data-Driven CPS fault detection, isolation and diagnosis methods

• 
  Data-Driven Services and

• 
  CPS-oriented fault-tolerant control

• 
  CPS-oriented robust control

• 
  Data-driven artificial intelligence approaches applied in CPS

• 
  Challenges and techniques for potential industrial and domestic applications

• 
  Applications of AI technologies in cyber security and privacy

• 
  Security-related big data capture, classification and analytics

• 
  Data mining and knowledge discovery for security

• 
  Intelligent systems for security and privacy

• 
  Theoretical studies on big data privacy and security

• 
  Privacy-preserving machine/deep learning and data mining

• 
  AI-driven attacks and mitigation methods

• 
  Data science-based solutions for CPS security and privacy issues;

• 
  Blockchain-based security and privacy solutions for CPS applications;

• 
  Smart contract-based trustable and verifiable computations for CPS applications;

• 
  Adaptive attack mitigation for CPS;

• 
  Authentication and access control for CPS;

• 
  Availability, recovery, and auditing for CPS;

• 
  Data security and privacy for CPS;

• 
  Embedded systems security and privacy;

• 
  Electric vehicle charging systems security and privacy;

• 
  Intrusion detection for CPS;

• 
  Legacy CPS system protection;

• 
  Security and privacy in industrial control systems;

• 
  Smart grid security and privacy;

• 
  Urban transportation system security and privacy;

• 
  Vulnerability analysis for CPS;

• 
  Wireless sensor network security and privacy.

Guest Editors:

• 
  Prof. Dalin Zhang – Beijing Jiaotong University, China, [email protected]

• 
  Prof. Taihoon Kim - Beijing Jiaotong University, China, [email protected]


• 
  Prof. Ruay-Shiung Chang - President, National Taipei University of Business Taipei, Taiwan, [email protected]


• 
  Prof. Sabah Mohammed - Lakehead University, Canada, [email protected]


• 
  Prof. Carlos Ramos - ISEP, Polytechnic of Porto,  [email protected]

Key Dates

Deadline for Submission: 30 Dec, 2020

First Reviews Due: 28 Feb, 2021 Revised Manuscript Due: 30 May, 2021

Final Decision: 30 July, 2021