In July 1982, Dr. Wong left Paradise (Victoria, B.C.) and joined the Faculty of Science as an Associate Professor in the Department of Computer Science. He was promoted to Professor in 1987.

As a teacher, over the years, he has been responsible for many undergraduate and graduate courses, including Discrete Mathematics, Assembly Language, Database Systems, Information Retrieval, Probabilistic Reasoning and Artificial Intelligence.

Under Dr. Wong’s supervision, 16 M.Sc and 7 Ph.D students have graduated. He is currently supervising three Ph.D students.

Dr. Wong is a well-known researcher in several fields in computer science and has produced many influential results in a number of research areas, such as information retrieval, uncertainty in artificial intelligence, and belief networks. The results of Dr. Wong’s research may have significant and long term impacts on information technologies.

Dr. Wong’s research belongs to basic and theoretical studies, where fundamental questions are asked and crucial issues are examined. He sets an excellent example as a scholar for students and colleagues. His devotion and attitude towards scientific research is particularly commendable. His numerous publications are a testimony to his tireless research endeavours, so are the many successful students who are either following in his footsteps in the academic arena or contributing in the corporate world.

In information retrieval, Dr. Wong’s contributions are on the generalized vector space model, the adaptive linear model, and the probabilistic inference models.

Bayesian networks are becoming established as the primary framework for uncertainty management. On the other hand, the relational database model has long been established as the basis for designing database systems. Many researchers have pointed out both similarities and differences between these two knowledge systems. Dr. Wong’s research, however, established the intrinsic relationship between these two representations. In particular, he showed that the logical implication of the constraint used in Bayesian networks (probabilistic conditional independence) and that used in relational databases (embedded multivalued dependency) coincides on the solvable classes and differs on the unsolvable classes. In other words, there is no real difference in practice between probabilistic expert systems and the conventional relational database management system. This result is very important as it suggests that results obtained in one domain may also be applicable in the other domain.

In recent years, Dr. Wong has been working on generalizing the Bayesian network model. He proposed the notion of the Hierarchical Markov network model, which has advantages over the traditional Bayesian network model in terms of faithful representation and efficiency of inference. Dr. Wong also discovered some nontrivial algebraic properties of Bayesian networks. This inspired him to revisit the Bayesian network model from scratch using the algebraic perspective. He developed an algorithm for efficiently identifying compelled edges in Bayesian networks and this algorithm is the core algorithm for learning Bayesian networks.

Due to his outstanding research work, he was the recipient of the University of Regina Alumni Association Award for Excellence in Research in 1994.

Dr. Wong, the Department of Computer Science and the University of Regina would like to thank you for your commitment to the University. We wish you all the best in your retirement. Now you will have time to do those fun things (travel, ballroom dancing) that you never had time to do before!

To Top of Page