VLVictor Chung Sing Lee

Victor Chung Sing Lee

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Victor Chung Sing Lee has a total of 158 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • An Expert-Guided RAG Chatbot as a “Virtual TA” for a Project-Based Engineering Course: A Continuous Deployment Case Study

    by Yun Wing Kiang, Zhenglong Li, Albert T. L. Lee, Vincent Tam, King Hang Lam, Victor C. S. Lee

  • Towards Pervasive WLAN Localization Leveraging Collaborative Mobile Sites: A Multi-Agent Deep Reinforcement Learning Approach

    by Wendi Nie, Yuanyi Zhang, Kam-Yiu Lam, Victor C.S. Lee, Min Wei, Yaoxin Duan, Kai Liu, Chun Jason Xue, Guan Gui

    Indoor location-based services (LBS) have witnessed rapid growth in applications such as user tracking, healthcare monitoring, and smart facility management, driving the critical need for efficient and pervasive indoor localization. Traditional WiFi fingerprinting methods face significant challenges: multi-site localization (MSL) relies on densely deployed static WiFi sites, incurring high infrastructure costs and conflicting with the Integrated Sensing and Communication (ISAC) paradigm; single-site localization (SSL) requires complex hardware; and single mobile site localization (SMSL) suffers from poor real-time performance due to long traversal paths. To address these limitations, this paper proposes a Multi-Agent Deep Reinforcement Learning-based Collaborative Indoor Localization (MADRL-CIL) framework. MADRL-CIL leverages multiple collaborative mobile sites to dynamically acquire Received Signal Strength (RSS) fingerprints. By modeling each mobile site as an agent, the framework formulates the path selection and fingerprint acquisition task as a Multi-Agent Deep Reinforcement Learning (MADRL) problem under a Centralized Training with Decentralized Execution (CTDE) paradigm, facilitating effective collaboration among multiple mobile sites to optimize localization accuracy while minimizing localization time. Additionally, a Multi-Site Fingerprint Matching (MS-FM) model is specifically designed to process collaboratively collected RSS fingerprints, enabling fine-grained localization accuracy. Experimental evaluations in a real-world indoor environment demonstrate that MADRL-CIL achieves localization accuracy comparable to dense multi-static site deployments while provides good real-time performance.

  • A Multiagent DRL-Based Method for Cooperatively Determining Coordination and Lane Change of Vehicles at Signal-Free Intersections With Free-Direction Lanes

    by Wendi Nie, Deya Gao, Chaofan Liu, Yaoxin Duan, Victor C. S. Lee, Kai Liu, Chun Jason Xue, Guan Gui, Sang Hyuk Son

    Owing to the growing population and rapid urbanization, intersections, where traffic converges from various directions, have become major bottlenecks for road capacity due to frequent congestion. Recent advances in connected and autonomous vehicle (CAV) technology enable signal-free intersections, where CAVs collaborate to cross intersections without collisions. Most existing signal-free intersection control methods focus on accommodating conflicts among vehicles inside the intersection and fixed-direction lanes are commonly adopted. However, the use of fixed-direction lanes is a legacy from conventional signalized intersections, where turning lanes are predetermined and fixed, so as to direct vehicles with different turning intentions to different lanes and avoid collisions. In this article, we aim to make full utilization of the capacity of signal-free intersections by making use of free-direction lanes, which allow vehicles to make right, straight or left turns from any lane. To this end, we propose a cooperative multiagent deep reinforcement learning (DRL)-based control method for signal-free intersections with free-direction lanes. Specifically, we first study the problem of cooperatively determining coordination of vehicles inside the intersection and lane changes of vehicles on the incoming arms. Then, a multiagent DRL-based control method for cooperatively determining coordination and lane change (LC) of vehicles for signal-free intersections with free-direction lanes, named CD-CLC, is proposed for maximizing nonconflicting vehicles crossing the intersection simultaneously while taking vehicle fairness into consideration, to minimize travel delays of vehicles and improve traffic efficiency. Extensive experiments have been conducted to compare CD-CLC with other state-of-the-art methods to demonstrate the effectiveness of the proposed approach.


  • A Cooperative Vehicle Localization and Trajectory Prediction Framework Based on Belief Propagation and Transformer Model

    by Feiyu Jin, Kai Liu, Chunhui Liu, Tongtong Cheng, Hao Zhang, Victor C. S. Lee

    The advancement of sensing, transmission, and computation technologies has transformed modern vehicles into ubiquitous consumer electronics. This paper presents a cooperative vehicle localization and trajectory prediction framework for enabling Intelligent Transportation Systems (ITS) applications. Specifically, the proposed framework consists of a Belief Propagation based Location Approximation (BPLA) algorithm for cooperative vehicle localization and a Transformer-based Vehicle trajectory prediction model called VFormer. The BPLA algorithm first establishes a factor graph based on the sensor measurements transmitted by vehicles, and then adopts a modified belief propagation procedure to approximate the posterior distribution of vehicles. On this basis, VFormer extracts the hidden features from historical positions estimated by BPLA and vehicle motion data to model long-term and short-term motion patterns of vehicles. Moreover, the multi-head attention layer in the VFormer is utilized to learn the spatial-temporal dependencies between the target vehicle and its surrounding vehicles at different timestamps to improve prediction accuracy. A comprehensive performance evaluation has been conducted based on the public vehicle trajectory dataset and the real-world system prototype. Experiment results demonstrate the superiority of the proposed framework on improving vehicle localization and trajectory prediction performance.


  • Top Cited Papers

    Accelerating DNN Inference With Reliability Guarantee in Vehicular Edge Computing

    by Kai Liu, Chunhui Liu, Guozhi Yan, Victor C. S. Lee, Jiannong Cao

    This paper explores on accelerating Deep Neural Network (DNN) inference with reliability guarantee in Vehicular Edge Computing (VEC) by considering the synergistic impacts of vehicle mobility and Vehicle-to-Vehicle/Infrastructure (V2V/V2I) communications. First, we show the necessity of striking a balance between DNN inference acceleration and reliability in VEC, and give insights into the design rationale by analyzing the features of overlapped DNN partitioning and mobility-aware task offloading. Second, we formulate the Cooperative Partitioning and Offloading (CPO) problem by presenting a cooperative DNN partitioning and offloading scenario, followed by deriving an offloading reliability model and a DNN inference delay model. The CPO is proved as NP-hard. Third, we propose two approximation algorithms, i.e., Submodular Approximation Allocation Algorithm (SA $^3$ ) and Feed Me the Rest algorithm (FMtR). In particular, SA $^3$ determines the edge allocation in a centralized way, which achieves 1/3-optimal approximation on maximizing the inference reliability. On this basis, FMtR partitions the DNN models and offloads the tasks to the allocated edge nodes in a distributed way, which achieves 1/2-optimal approximation on maximizing the inference reliability. Finally, we build the simulation model and give a comprehensive performance evaluation, which demonstrates the superiority of the proposed solutions.


  • Online algorithms for the maximum k-interval coverage problem

    by Songhua Li, Minming Li, Lingjie Duan, Victor C. S. Lee

  • Adaptive Offloading for Time-Critical Tasks in Heterogeneous Internet of Vehicles

    by Chunhui Liu, Kai Liu, Songtao Guo, Ruitao Xie, Victor C. S. Lee, Sang H. Son

    With recent development of wireless communication, sensing and computing technologies, Internet of Vehicles (IoV) has attracted great attention in both academia and industry. Nevertheless, it is challenging to process time-critical tasks due to unique characteristics of IoV, including heterogeneous computation and communication capacities of network nodes, intermittent wireless connections, unevenly distributed workload, massive data transmission, intensive computation demands, and high mobility of vehicles. In this paper, we propose a two-layer vehicular fog computing (VFC) architecture to explore the synergistic effect of the cloud, the static fog and the mobile fog on processing time-critical tasks in IoV. Then, we give a motivational case study by implementing a prototype of a traffic abnormity detection and warning system, which demonstrates the necessity and urgency of developing adaptive task offloading mechanisms in such a scenario and gives insight into the problem formulation. Further, we formulate the offloading model, aiming at maximizing the completion ratio of time-critical tasks. On this basis, we propose an adaptive task offloading algorithm (ATOA). Specifically, it adaptively categorizes all tasks into four types of pending lists by considering the dynamic requirements and resources constraints, and then tasks in each list will be cooperatively offloaded to different nodes based on their features. Finally, we build the simulation model and give a comprehensive performance evaluation. The results demonstrate the superiority of ATOA.


  • Fog Computing Empowered Data Dissemination in Software Defined Heterogeneous VANETs

    by Kai Liu, Ke Xiao, Penglin Dai, Victor C.S. Lee, Songtao Guo, Jiannong Cao

    This paper makes the first effort on proposing a fog computing empowered architecture together with a dedicated scheduling algorithm for data dissemination in software defined heterogeneous vehicular ad-hoc networks (VANETs). Specifically, the architecture supports both the logically centralized control via the cloud node in the core network and the distributed data dissemination via the fog nodes at the network edge. A problem called fog assisted cooperative service (FACS) is formulated, which takes network coding and vehicular caching into consideration, and aims at minimizing the overall service delay via the cooperation of vehicle-to-cloud (V2C), vehicle-to-fog (V2F) and vehicle-to-vehicle (V2V) communications. Further, we derive an equivalence problem of FACS and prove that FACS is NP-hard. On this basis, we propose a Clique Searching based Scheduling (CSS) algorithm at the SDN controller, which considers the heterogeneous communication interfaces and vehicle mobility in scheduling, and enables the collaborative data encoding and transmission among the cloud, fog nodes and vehicles. The complexity analysis demonstrates the feasibility of the proposed algorithm. Finally, we build the simulation model and give a comprehensive performance evaluation based on real vehicular trajectories extracted from different time and space. The simulation results conclusively demonstrate the superiority of the proposed solution.


  • Multi-Armed Bandit Learning for Computation-Intensive Services in MEC-Empowered Vehicular Networks

    by Penglin Dai, Zihua Hang, Kai Liu, Xiao Wu, Huanlai Xing, Zhaofei Yu, Victor Chung Sing Lee

    Mobile edge computing (MEC) is an emerging paradigm to offload computations from the cloud to the MEC servers in vehicular networks, aiming at better supporting computation-intensive services with requirements of low latency and real-time processing. In this work, we investigate a new service scenario of computation offloading and workload balancing in MEC-empowered vehicular networks, where the computational resources of MEC/cloud servers are cooperatively utilized. Then, we formulate a distributed task assignment (DTA) problem by considering heterogeneous computation resources, high mobility of vehicles and uneven distribution of workloads, targeting at optimizing task assignment among MEC/cloud servers and minimizing task completion time. We prove that the DTA is NP-hard. Further, we propose a multi-armed bandit learning algorithm called Utility-table based Learning. For workload balancing among MEC servers, a utility table is established to determine the optimal solution by online learning of real-time workload distribution, which is updated based on the feedback signal of task assignment. For optimal computation offloading, a theoretical bound is derived to determine the ratio of workload assigned to the cloud. Lastly, we build the simulation model and conduct an extensive experiment, which demonstrates the superiority of the proposed algorithm.


  • Packet Delivery Ratio Fingerprinting: Toward Device-Invariant Passive Indoor Localization

    by Yaoxin Duan, Kam-Yiu Lam, Victor C. S. Lee, Wendi Nie, Hao Li, Joseph Kee-Yin Ng

    Passive indoor localization for mobile Wi-Fi devices, e.g., smartphones, has attracted increasing attention from research communities recently. Existing passive localization techniques leverage received signal strength (RSS) of packets transmitted by target Wi-Fi devices and do not require a dedicated software installed on the devices. However, RSS-based passive localization techniques 1) are device-dependent, which results in poor localization accuracy for a wide variety of mobile devices; and 2) cannot perform real-time passive localization. In this paper, we present a novel passive localization technique, namely packet delivery ratio (PDR) fingerprinting, to address these problems. In PDR fingerprinting, a lowest-power and highest-modulation scheme (LPHMS) is proposed to generate device-invariant packet delivery ratio, which replaces RSS to construct fingerprints, to achieve device-invariant localization accuracy. Moreover, instead of passively monitoring packets rarely sent by mobile devices, in PDR fingerprinting, access points (APs) actively transmit request-to-send (RTS) frames to trigger target devices to reply clear-to-send (CTS) frames to calculate packet delivery ratio. The RTS/CTS mechanism enables PDR fingerprinting to perform real-time localization. We have conducted extensive experiments in a real-world testbed. The experimental results demonstrate that PDR fingerprinting presents a competitive localization accuracy compared to RSS-based passive fingerprinting methods but is device-invariant.