People

Philip Yu is a Professor at the Department of Mathematics and Information Technology of the Education University of Hong Kong. He is the Associate Director of the University Research Facility of Data Science and Artificial Intelligence and an Executive Committee Member of the International Association of Statistical Computing. Philip was the Chairperson of the Asian Region Section of the International Association of Statistical Computing, the Vice President of the Hong Kong Statistical Society, a Council Member of the Hong Kong Mathematical Society, and a member of the Technical Committee of Computational Finance and Economics, IEEE Computational Intelligence Society. He is also an Associate Editor of Frontiers in Artificial Intelligence, Journal of Data Science, Statistics, and Visualisation, Journal of Applied Statistics, and Digital Finance.

His research interests are broad; they include analysis of ranking data, data mining and STEM Education, AI and big data analytics, time series analysis, financial data analysis and risk management, and ranked set sampling. He has a substantial volume of work on most of these topics, including more than 140 publications and two Springer monographs on ranking methodology which have been favorably reviewed. Many publications contain novel ideas in the above-mentioned fields and appeared in top-tier journals and conferences such as AAAI, Biometrika, Journal of Business and Economic Statistics, Journal of Statistical Software, Finance Research Letters, Expert Systems with Applications, and IEEE Transactions on Neural Networks and Learning Systems.

Professor Yu has been continuously engaged in performing outstanding teaching and mentoring activities, providing exceptional service to the statistics/data science profession through numerous conferences and committee work, and promoting statistical and AI literacy in Hong Kong through a number of outreach activities. He has been involved in the organizing and program committees at many international conferences. He was a member of the Assessment Working Group of the Chief Executive’s Award for Teaching Excellence (2020/2021). He possesses over three decades of extensive experience in diverse contracted research/consulting projects and professional services for businesses, industries, and public bodies, including banks and insurance companies, stock exchanges, the Hospital Authority, the Department of Health (HKSAR), the Census and Statistics Department (HKSAR), secondary schools, etc.

• Data Science and AI
• Preference Learning
• AI in Education and Healthcare
• Time Series Analysis
• Statistical and AI Education.

Courses Taught on 2023-24:

• MTH6184 Data Mining and STEM Education (MSc(AI&EdTech) course, 2nd semester)

Chapter in an edited book (author)

• 楊良河和陳昊 (2022)。 淺談總體比例的置信區間估算法。輯於課程發展組編， 《學校數學通訊》，第 25 期， (頁 106-115)。香港: 香港特別行政區政府教育局課程發展處數學教育組

Journal Publications (Publication in refereed journal)

• Liang, L., Zhuang, Y., & Yu, P.L.H. (2024). Variable selection for high-dimensional incomplete data. Computational Statistics and Data Analysis, 192, 107877. https://doi.org/10.1016/j.csda.2023.107877
• Zhao, R., Xie, Z., Zhuang, Y., & Yu, P.L.H. (2023). Automated quality evaluation of large-scale benchmark datasets for vision-language tasks. International Journal of Neural Systems, Online first. https://doi.org/10.1142/S0129065724500096
• Zhao, R., Zhuang, Y., Zou, D., Xie, Q. & Yu, P.L.H. (2023). AI-assisted automated scoring of picture-cued writing tasks for language assessment. Education and Information Technologies, 28 (6), 7031-7063. https://doi.org/10.1007/s10639-022-11473-y
• Gu, J., & Yu, P.L.H. (2023). Social order statistics models for ranking data with analysis of preferences in social networks. Annals of Applied Statistics, 17(1), 89-107. https://doi.org/10.1214/22-AOAS1617
• Kuo, M. D., Chiu, K. W. H., Wang, D. S., Larici, A. R., Poplavskiy, D., Valentini, A., Napoli, A., Borghesi, A., Ligabue, G., Fang, X.H.B., Wong, H.K.C., Zhang, S., Hunter, J., Mousa, A., Infate, A., Elia, L., Golemi, S., Yu, P.L.H., Hui, C.K.M., & Erickson, B. J. (2023). Multi-center validation of an artificial intelligence system for detection of COVID-19 on chest radiographs in symptomatic patients. European Radiology, 33, 23-33 Doi:10.1007/s00330-022-08969-z.
• Wang, X., Yu, P.L.H., Yang, W. and Su, J. (2022). Bayesian robust tensor completion via CP decomposition. Pattern Recognition Letters, 163, 121-128.
• Gu, J., & Yu, P.L.H. (2022). Joint Latent Space Models for Ranking Data and Social Network. Statistics and Computing, 32, 1-15 Doi:https://doi.org/10.1007/s11222-022-10106-1.
• Xin, L., Lam, K., & Yu, P.L.H. (2021). Effectiveness of filter trading as an intraday trading rule. Studies in Economics and Finance, 38(3), 659-674. https://doi.org/10.1108/SEF-09-2018-0294
• Lu, R., & Yu, P.L.H. (2021). Buffered Vector Error-Correction Models: An Application to the U.S. Treasury Bond Rates. Studies in Nonlinear Dynamics & Econometrics, 25(5), 267-287 Doi:https://doi.org/10.1515/snde-2019-0047.
• You, J., Yu, P.L.H., Tsang, A.C.O., Tsui, E.L.H., Woo, P.P.S., Lui, C.S.M., Leung G.K.K., Mahboobani, N., Chu, C.-Y., Chong, W.-H., Poon, W.-L. (2021). 3D Dissimilar-Siamese-U-Net for Hyperdense Middle Cerebral Artery Sign Segmentation. Computerized Medical Imaging and Graphics, 90 (June 2021), 101898
• K.K.F. LAW, W.K. LI and Philip L.H. YU (2021). An Alternative Nonparametric Tail Risk Measure. Quantitative Finance , 21(4), 685-696
• Chiu, W. H. K., Vardhanabhuti, V., Poplavskiy, D., Yu, P. L. H., Du, R., Yap, A. Y. H., Zhang, S., Fong, A. H. T., Chin, T. W. Y., Lee, J. C. Y., Leung, S. T., Lo, C. S. Y., Lui, M. M. S., Fang, B. X. H., Ng, M. Y. and Kuo, M. D. (2020). Detection of COVID-19 Using Deep Learning Algorithms on Chest Radiographs. Journal of Thoracic Imaging, 35(6), 369-376
• Seto, W. K. W., Chiu, W. H. K., Yu, P. L. H., Cao, W., Cheng, H. M., Wong, E. M. F., Wu, J., Lui, G. C. S., Shen, X., Mak, L. Y., Li, W. K. and Yuen, R. M. F. (2020). An end-to-end artificial intelligence model accurately diagnosing hepatocellular carcinoma on computed tomography. United European Gastroenterology Journal, 8(8 suppl), 48-49
• Seto, W., Chiu, K., Yu, P. L. H., Cao, W., Cheng, H. M., Lui, G., Wong, E. M. F., Wu, J., Mak, L. Y., Shen, X. P., Li, W. K. and Yuen, M. F. (2020). High diagnostic performance of a deep learning artificial intelligence model in accurately diagnosing hepatocellular carcinoma on computed tomography . Hepatology, 72 (1 Suppl), 84-85
• Yu, P. L. H., Ng, F. C., and Ting, J. K. W. (2020). Adjusting covariance matrix for risk management. Quantitative Finance, 20(10), 1681-1699
• K.K.F. LAW, W.K. LI and Philip L.H. YU (2020). Evaluation Methods for Portfolio Management. Applied Stochastic Models in Business and Industry, 36(5), 857-876
• Lu, R., Yu, P. L. H., and Wang, X. (2020). Sparse vector error correction models with application to cointegration‐based trading. Australian & New Zealand Journal of Statistics, 62(3), 297-321
• K. LAW, W.K. LI and P. YU (2020). An Empirical Evaluation of Large Dynamic Covariance Models in Portfolio Value-at-Risk Estimation. Journal of Risk Model Validation, 14(2), 21-39
• Lu, R., and Yu, P. L. H. (2020). Smooth buffered autoregressive time series models. Journal of Statistical Planning and Inference, 206, 196-210
• You, J., Tsang, A. C. O., Yu, P. L. H., Tsui, E. L. H., Woo, P. P. S., Lui, C. S. M., and Leung, G. K. K. (2020). Automated hierarchy evaluation system of large vessel occlusion in acute ischemia stroke. Frontiers in Neuroinformatics, 14, 14
• Zhu, Y., Yu, P. L. H., and Mathew, T. (2020). Improved estimation of optimal portfolio with an application to the US stock market. Journal of Statistical Theory and Practice, 14(1), 25
• Tsang, A. C. O., You, J., Li, L. F., Tsang, F. C. P., Woo, P. P. S., Tsui, E. L. H., Yu, P. L. H. and Leung, G. K. K. (2020). Burden of large vessel occlusion stroke and the service gap of thrombectomy: A population-based study using a territory-wide public hospital system registry. International Journal of Stroke, 15(1), 69-74

Journal Publications (Publication in policy or professional journal)

• Yu P. L. H. and Li, W. K. (2021). Project-based Learning via Competition for Data Science Students. Harvard Data Science Review, 3(1), 1-4

Conference Papers (Invited conference paper)

• 楊良河 (2022，6). 人工智能驅動的看圖造句自動評分。論文發表於「EDTECH教育科技研討會2022：特殊教育科技的創新和發展」，香港

Conference Papers (Refereed conference paper)

• Gao, J., Xu, H., Shi, H., Ren, X., Yu, P.L.H., Liang, X., Jiang, X., & Li, Z. (2022, 6). AutoBERT-Zero: Evolving BERT Backbone from Scratch. Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI-22), virtual Doi:https://doi.org/10.1609/aaai.v36i10.21311.
• Gao, J., Zhou, Y., Yu, P.L.H., Joty, S., & Gu, J. (2022, 6). UNISON: Unpaired Cross-Lingual Image Captioning. Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI-22), virtual Doi:https://doi.org/10.1609/aaai.v36i10.21310.
• Seto, W.K.W., Chiu, K.H.K., Cao, W., Lui, G., Zhou, J. Cheng, H.M., Wu, J., Shen, X., Mak, L.Y., Huang, J., Li, W.K. and Yuen, R.M.F. & Yu, P.L.H. (2022). Training, validation and testing of a multiscale three-dimensional deep learning algorithm in accurately diagnosing hepatocellular carcinoma on computed tomography. Journal of Hepatology. Volume 77. Supplement 1, Abstracts of The International Liver Congress: London, United Kingdom, 22-26 June 2022, p. S78-S79.
• Song, Y., Yu, P.L.H., Lee, J.C.K., Wu, K., & Cao, J. (2022, 6). Developing an Avatar Generation System for the Metaverse in Education. Paper presented at The 1st International Workshop on Metaverse and Artificial Companions in Education and Society (MetaACES 2022), Hong Kong https://www.eduhk.hk/metaaces2022/download/MetaACES%202022%20Program_20220622.pdf

Bayesian Robust Tensor Completion via CP Decomposition

The real-world tensor data are inevitable missing and corrupted with noise. We propose a robust Bayesian tensor completion method, called MoG BTC-CP, which could impute the missing data and remove the complex noise simultaneously.
Project Start Year: 2021, Principal Investigator(s): WANG, Xiaohang (YU, Leung Ho Philip 楊良河 as Co-Principal Investigator)

Research and Development of Artificial Intelligence in Educational and Financial Technologies

...
Project Start Year: 2021, Principal Investigator(s): YU, Leung Ho Philip 楊良河

Research and Development of Artificial Intelligence in Educational and Financial Technologies (RMG)

...
Project Start Year: 2021, Principal Investigator(s): YU, Leung Ho Philip 楊良河

Moving Average for Buffered Time Series Modelling

he buffered time series model is a new type of nonlinear time series models that have attracted some attention in the literature. However, nearly all buffered time series models are of the autoregressive type. The objective of this project is to extend the buffered time series to include the moving average specification.Project Start Year: 2021, Principal Investigator(s): LI, Wai Keung 李偉強 (YU, Leung Ho Philip 楊良河 as Co-Investigator)

Cross-lingual Image Captioning

...
Project Start Year: 2020, Principal Investigator(s): YU, Leung Ho Philip 楊良河

Modeling Ranking Data in Social Networks

Ranking of items arises in many situations in our daily lives. Very often, not all the items are ranked, resulting in a set of incomplete ranking data. A typical example of incomplete ranking data is movie recommendation where users in a social media platform rated a number of movies and some of these users may be friends of each other. As not all movies are rated by the same user, after converting ratings to rankings, such dataset becomes a set of incomplete rankings with friendship connections among the users in a social network. It is known that individual choice behaviors may be influenced strongly from their peers or friends on social media. So far, traditional ranking models do not account for such spatial or network dependence. This project aims at developing new probabilistic models for ranking data in a social network. As individuals’ rank-order preference behaviors are often correlated with those of their “friends”, it is anticipated that the new models should be able to capture such social network effects and make better inferences, for instance, predicting ranks of the unranked items, inferring the latent social positions, and identifying latent groups. They
can help us to have a better understanding of some sociological phenomena such as homophily as well as the social patterns of the individuals and items. First of all, we develop conditional models of ranking data for a given social network by extending the traditional ranking models to incorporate peer effects. Secondly, we will adopt a latent space approach to model both ranking data and social network jointly. Under this approach, individuals and items are represented by points in a latent space, and the distance between two individual points and the distances from an individual point to the item points will then determine the likelihood of a connection between the two individuals and the probability of observing a ranking given by the individual respectively. One can also develop joint models by combining a marginal model for ranking data (social network) and a conditional model of social network (ranking data).
Efficient estimation procedures of the new models will be developed. To provide a comprehensive study under various conditions, the proposed models will be applied to analyze a number of real-world datasets and semi-synthetic datasets. It is believed that the new models can provide both practical and theoretical contributions to the analysis of ranking data in a social network.
Project Start Year: 2020, Principal Investigator(s): YU, Leung Ho Philip 楊良河

Contributing to the Development of Hong Kong into a Global Fintech Hub

...
Project Start Year: 2019, Principal Investigator(s): YU, Leung Ho Philip 楊良河