Dr Man-Fai Leung

Man-Fai is a Lecturer in Computing and Artificial Intelligence.

[email protected]

Background

Man-Fai obtained his Bachelor of Science (Hons) and Master of Philosophy in Computing from Hong Kong Metropolitan University, Doctor of Philosophy in Computer Science from the City University of Hong Kong.

Man-Fai worked at Hong Kong Metropolitan University as a Lecturer before joining ARU. He is a member of the Computing, Informatics and Applications Research Group.

Man-Fai served as the Publications Chair for the 10th, 11th, and 13th International Conference on Information Science and Technology. His current research interests include intelligent systems, machine learning, and optimisation.

Spoken Languages

• Cantonese
• Mandarin

Research interests

• Intelligent systems
• Computational intelligence
• Machine Learning
• Data Science
• Portfolio optimization

Teaching

Computing and Artificial Intelligence

Qualifications

• Post Graduate Certificate in Teaching and Learning, (PGCert), Anglia Ruskin University, UK.
• PhD in Computer Science, City University of Hong Kong
• MPhil in Computing, Hong Kong Metropolitan University
• BSc (Hons) in Computing, Hong Kong Metropolitan University

Memberships, editorial boards

• Fellow, Higher Education Academy (FHEA), UK
• Associate Editor: Complex & Intelligent Systems
• Associate Editor: Intelligent Systems with Applications
• Guest Editor: Special Issue on Advances in Analysis and Application of Multi-Objective Memetic Optimization Algorithms, Memetic Computing(Impact factor 5.900)

Research grants, consultancy, knowledge exchange

• PI - HKMU R&D Fund (PFDS/2021/07) High-Dimensional Data Analysis Based on Neural Computation (Dec 2021 – Apr 2022), HKD$150,000
• PI - HKMU PACRD (2020/1.4) Collaborative Neurodynamic Approaches to Sparse Optimization (Feb 2021 – Apr 2022), HKD$199,000
• Co-I - RGC FDS (UGC/FDS16/E12/20) Modelling the social aspects of interactive objects for pedestrian trajectory prediction in urban areas (Jan 2021 – Apr 2022), HKD$832,700
• PI - HKMU R&D Fund (R5083/2019/20 S&T) Artificial Neural Network based Techniques for Portfolio Management (Dec 2019 – Jul 2020), HKD$40,000.

Selected recent publications

Che, H., Yang, X., Leung, M. F., Cao, Y. & Yan, Z. (In press). Tensor Factorization With Sparse and Graph Regularization for Fake News Detection on Social Networks. IEEE Transactions on Computational Social Systems. DOI: 10.1109/TCSS.2023.3296479

Pan, B., Li, C., Che, H., Leung, M. F., & Yu, K. (In press). Low-Rank Tensor Regularized Graph Fuzzy Learning for Multi-View Data Processing. IEEE Transactions on Consumer Electronics. DOI: 10.1109/TCE.2023.3301067

Yang, X., Che, H., Leung, M. F. & Liu, C. (2023). Adaptive graph nonnegative matrix factorization with the self-paced regularization. Applied Intelligence, 53, 15818–15835. DOI:10.1007/s10489-022-04339-w

Li, C., Che, H., Leung, M. F., Liu, C. & Yan Z. (2023). Robust multi-view non-negative matrix factorization with adaptive graph and diversity constraints. Information Sciences, 634, 587-607. DOI:10.1016/j.ins.2023.03.119

Chen, K., Che, H., Li, X. & Leung, M. F. (2023). Graph non-negative matrix factorization with alternative smoothed L0 regularizations. Neural Computing and Applications, 35(14), 9995-10009. DOI:10.1007/s00521-022-07200-w

Leung, M. F., Wang, J. & Li, D. (2022). Decentralized robust portfolio optimization based on cooperative-competitive multiagent systems. IEEE Transactions on Cybernetics, 52(12), 12785-12794. DOI:10.1109/TCYB.2021.3088884

Yuen, M.C., Ng, S.C., Leung, M.F. & Che, H. (2022). A Metaheuristic-Based Framework for Index-Tracking with Practical Constraints. Complex & Intelligent Systems, 8, 4571-4586. DOI: 10.1007/s40747-021-00605-5

Leung, M. F. & Wang, J. (2022). A collaborative neurodynamic approach to cardinality-constrained bi-objective portfolio optimization. Neural Networks, 145, 68-79. DOI:10.1016/j.neunet.2021.10.007

Leung, M. F. & Wang, J. (2021). Minimax and bi-objective portfolio selection based on collaborative neurodynamic optimization. IEEE Transactions on Neural Networks and Learning Systems, 32(7), 2825-2836. DOI:10.1109/TNNLS.2019.2957105

Dai, C., Che, H. & Leung, M. F. (2021). A neurodynamic optimization approach for L1 minimization with application to compressed image reconstruction. International Journal on Artificial Intelligence Tools, 30(1), 2140007. DOI:10.1142/S0218213021400078

Yuen, M.C., Ng, S.C. & Leung, M. F. (2021). A competitive mechanism multi-objective particle swarm optimization algorithm and its application to signalized traffic problem. Cybernetics and Systems, 52(1), 73-104. DOI:10.1080/01969722.2020.1827795

Leung, M. F. & Wang, J. (2018). A collaborative neurodynamic approach to multiobjective optimization. IEEE Transactions on Neural Networks and Learning Systems, 29(11), 5738-5748. DOI: 10.1109/TNNLS.2018.2806481

Recent presentations and conferences

Lui, A. K. & Chan, Y. H. & Leung, M. F. (2021, December). Modelling of Destinations for Data-driven Pedestrian Trajectory Prediction in Public Buildings. 2021 IEEE International Conference on Big Data (IEEE BigData 2021) (Acceptance rate 19.7%) (pp 1-6). Orlando, FL, USA.

Leung, M. F. & Wang, J. (2021, December). Another Two-Timescale Duplex Neurodynamic Approach to Portfolio Selection. In International Conference on Intelligent Control and Information Processing (ICICIP 2021) (pp 401-405). Dali, Yunnan, China.

Leung, M. F. & Ng, S.C. (2020, July) A hybrid algorithm based on MOEA/D and local search for multiobjective optimization. In 2020 IEEE Congress on Evolutionary Computation (CEC) (pp 1-8). Glasgow, United Kingdom.

Tam, H. H., Leung, M. F., Wang, Z., Ng, S. C., Cheung, C. C. & Lui, A. K. (2016, July). Improved adaptive global replacement scheme for MOEA/D-AGR. In 2016 IEEE Congress on Evolutionary Computation (CEC) (pp. 2153-2160).

Leung, M. F., Ng, S. C., Cheung, C. C. & Lui, A. K. (2015, May). A new algorithm based on PSO for multi-objective optimization. In 2015 IEEE Congress on Evolutionary Computation (CEC) (pp. 3156-3162).

Leung, M. F., Ng, S. C., Cheung, C. C. & Lui, A. K. (2014, July). A new strategy for finding good local guides in MOPSO. In 2014 IEEE Congress on Evolutionary Computation (CEC) (pp. 1990-1997).