Cybersecurity and Artificial Intelligence for Connected and Autonomous Vehicles (CAVs)
- Apr. 2019, CTV News: Autonomous Cars Tested against Cyber-Attacks
- Feb. 2019, CBC News: Research Collaboration with BlackBerry/QNX to Develop and Secure Autonomous Vehicles
- Apr. 2018, CTV News: Research on Cybersecurity of Connected/Autonomous Vehicles at Carleton
- Apr. 2018, Ottawa Business Journal: Carleton University, BlackBerry QNX Join Forces to Put Brakes on Cyber Threats to Self-Driving Cars
- Apr. 2018, Carleton Stories: Connected Autonomous Vehicle Research at Carleton
- Jan. 2018, Ingenious Magazine: Connecting and Protecting Canada’s Roadways
Connected vehicle systems provide connectivity among vehicles to enable crash prevention, between vehicles and the infrastructure to enable safety, mobility and environmental benefits; among vehicles, infrastructure, and wireless devices to provide continuous real-time connectivity to all system users. An autonomous vehicle (a.k.a. driverless vehicle, self-driving vehicle, and robotic vehicle) is a vehicle that is capable of sensing its environment and navigating without human input. The potential of CV and AV has been acknowledged with the establishment of ambitious research programs around the globe. Despite the potential vision of CV and AV systems, there are numerous design challenges, including cybersecurity and artificial intelligence, remaining to be addressed before widespread deployment of CV and AV systems.
News reports about our research on CAVs:
Blockchain and Distributed Ledger Technology
- F. Richard Yu, Blockchain Technology and Applications - From Theory to Practice, ISBN 978-1729142592, Kindle Direct Publishing, 2019.
- F. Richard Yu, “A Service-Oriented Blockchain System with Virtualization,” Trans. Blockchain Technology and Applications, vol. 1, no. 1, pp. 1-10, 2019.
- F. Richard Yu, J. Liu, Y. He, P. Si, and Y. Zhang, “Virtualization for Distributed Ledger Technology (vDLT),” IEEE Access, vol. 6, pp. 25019-25028, 2018.
Recently, with the tremendous development of crypto-currencies, distributed ledger technology (DLT) (e.g., blockchain) has attracted significant attention. Although DLT has great potential to create new foundations for our economic and social systems, the existing DLT has a number of drawbacks (e.g., scalability) that prevent it from being used as a generic platform for distributed ledger across the globe. We propose a service-oriented blockchain system with virtualization and decoupled management/control and execution. This is a paradigm shift from the existing “blockchain-oriented” DLT systems to next generation“service-oriented” DLT systems. In addition, we present mathematical modeling and optimization for blockchain systems from the aspects of scalability, decentralization, latency and security.
Machine Learning and Artificial Intelligence
- C. Qiu, H. Yao, F. Richard Yu, F. Xu, and C. Zhao, ``Deep Q-learning Aided Networking, Caching, and Computing Resources Allocation in Software-Defined Satellite-Terrestrial Networks," IEEE Trans. Veh. Tech., accepted, Mar. 2019.
- Y. Guo, F. Richard Yu, J. An, K. Yang, Y. He, and V.C.M. Leung ``Buffer-Aware Streaming in Wireless Networks: A Deep Reinforcement Learning Approach," IEEE Trans. Veh. Tech., accepted, Mar. 2019.
- Y. Fu, C. Li, T.H. Luan, Y. Zhang, and F. Richard Yu, “Graded Warning for Rear-End Collision: An Artificial Intelligence Aided Algorithm,” IEEE Trans. Intell. Transp. Sys., accepted, Feb. 2019.
- M. Liu, Richard Yu, Y. Teng, V.C.M. Leung, and M. Song, “Performance Optimization for Blockchain-Enabled Industrial Internet of Things (IIoT) Systems: A Deep Reinforcement Learning Approach,” IEEE Trans. Industrial Electronics, accepted, Jan. 2019.
- Y. Wei, Z. Wang, D. Guo, F. Richard Yu, “Deep Q-Learning based Computation Offloading Strategy for Mobile Edge Computing,” Computers, Materials & Continua, accepted, Dec. 2018.
- Y. Wei, F. Richard Yu, M. Song, and Z. Han, “Joint Optimization of Caching, Computing, and Radio Resources for Fog-Enabled IoT Using Natural Actor-Critic Deep Reinforcement Learning,” IEEE Internet of Things Journal, accepted, Oct. 2018.
- C. Qiu, S. Cui, H. Yao, F. Xu, F. Richard Yu, and C. Zhao “A Novel QoS-Enabled Load Scheduling Algorithm Based on Reinforcement Learning in Software-Defined Energy Internet,” Future Generation Computer Systems, accepted, Sept. 2018.
- C. Qiu, F. Richard Yu, H. Yao, F. Xu, and C. Zhao, “Blockchain-Based Software-Defined Industrial Internet of Things: A Dueling Deep Q-Learning Approach,” IEEE Internet of Things Journal, accepted, Sept. 2018.
- Y. He, C. Liang, F. Richard Yu, and Z. Han, “Trust-based Social Networks with Computing, Caching and Communications: A Deep Reinforcement Learning Approach,” IEEE Trans. Network Science and Eng., accepted, May 2018.
- J. Xie, F. Richard Yu, T. Huang, R. Xie, J. Liu, C. Wang, and Y. Liu, “A Survey of Machine Learning Techniques Applied to Software Defined Networking (SDN): Research Issues and Challenges,” IEEE Comm. Survey and Tutorials, vol. 21, no. 1, pp. 393-430, First Quarter. 2019.
- Y. Wei, F. Richard Yu, M. Song, and Z. Han, “User Scheduling and Resource Allocation in HetNets with Hybrid Energy Supply: An Actor-Critic Reinforcement Learning Approach,” IEEE Tran. Wireless Comm., vol. 17, no.1, pp. 680-692, Jan. 2018.
- Y. He, F. Richard Yu, N. Zhao, V.C.M. Leung, and H. Yin, “Software-defined Networks with Mobile Edge Computing and Caching for Smart Cities: A Big Data Deep Reinforcement Learning Approach,” IEEE Comm. Mag., vol. 55, no. 12, pp. 31-37, Dec. 2017.
- Y. He, Z. Zhang, F. Richard Yu, N. Zhao, H. Yin, and V.C.M. Leung, “Deep-Reinforcement-Learning-Based Optimization for Cache-Enabled Opportunistic Interference Alignment Wireless Networks,” IEEE Trans. Veh. Tech., vol. 66, no. 11, pp. 10433 – 10445, Nov. 2017.
- L. Zhu, Y. He, F. Richard Yu, B. Ning, T. Tang, and N. Zhao, “Communication-Based Train Control System Performance Optimization Using Deep Reinforcement Learning,” IEEE Trans. Veh. Tech., vol. 66, no. 12, pp. 10705-10717, Dec. 2017.
- Y. Teng, F. Richard Yu, K. Han, Y. Wei, and Y. Zhang, “ Reinforcement-Learning-Based Double Auction Design for Dynamic Spectrum Access in Cognitive Radio Networks,” Springer Wireless Personal Comm., online, DOI: 10.1007/s11277-012-0611-9, 2012.
Recent advances in machine learning and artificial intelligent can provide solutions to many problems. Machine learning can be roughly classified into three categories: supervised, unsupervised and reinforcement learning. Reinforcement learning is an important branch of machine learning, where an agent learns to take actions that would yield the most reward by interacting with the environment. By replacing ordinary neural networks with advanced multi-layer deep neural networks, recently, deep reinforcement learning is proven to be more advantageous with greater performance and more robust learning.
Wireless Cyber-Physical Systems
- Feb. 15, 2017, CBC News: Carleton Prof Award $600,000 Grant to Improve 5G Networks
- Feb. 15, 2017, Carleton Stories: Bringing 5G Wireless to Life – Richard Yu’s Award-Winning Research
Wireless cyber-physical systems (CPS) are integrations of wireless communication, computation, networking, and physical processes. Examples of wireless CPS include connected and autonomous vehicles, intelligent transportation, communication-based train control (CBTC), industrial Internet, smart grid, etc. CPS integrates the dynamics of the physical processes with those of networking, providing abstractions and modeling, design, and analysis techniques for the integrated whole. Although the layered structure is one of the key reasons behind the success of the Internet, cross-layer/cross-system design is appropriate and may even be necessary in wireless CPS.
News reports about our research on wireless systems:
Security and Privacy in Networks
- Aug. 19, 2014, Defence Research and Development Canada: Tactical Wearable and the Self-Organizing Network (Search ‘Richard’ on the page)
Security and privacy are becoming more and more important issues in networks. Two classes of approaches, prevention-based (such as authentication) and detection-based (such as intrusion detection), can be used to protect high security wireless networks. As the front line of defense, user authentication is crucial for integrity, confidentiality and non-repudiation. Moreover, intrusion detection systems (IDSs), serving as the second wall of protection, can effectively help identify malicious activities. In addition, privacy concerns have drawn more and more attentions, involving the right of mandating personal privacy concerning storing, re-purposing, provision to third parties, and displaying of information pertaining to oneself via the network. Many technical challenges remain to be addressed to develop security and privacy schemes in future networks.
News reports about our research on wireless systems: