Assoc. Prof. Song-Kyoo Kim, Macao Polytechnic University, China
Dr. Song-Kyoo (Amang) Kim received an M.S. degree in computer engineering and a Ph.D. degree in operations research from the Florida Institute of Technology in 1999 and 2002, respectively. He is currently an Associate Professor of the computing program at the Macao Polytechnic University, Macau, and a Research Scholar at Khalifa University, Abu Dhabi. He used to be an Associate Professor at several United Arab Emirates universities. Before moving to the Gulf Region, he was a Core Faculty Member of the Asian Institute of Management, providing courses in technology, innovation, and operations. Before his academic career, he was a Technical Manager with the Mobile Communications Division, Samsung Electronics, for more than ten years and mainly dealt with technology management in the information technology industry. He is the author of more than 70 research articles and ten patents relating to the mobile technology industries. He has been an Invited Speaker at many international conferences concerning technology management, innovation processes, operations research, and data sciences. He is also an external reviewer of various prestige journals including IEEE Access; ACM Transactions on Multimedia Computing, Communications, and Applications; and the Journal of Information Security and Applications.
Invited Speech: Novel Public Transport Prediction Systems with Dynamic Statistical Attention Technique
Abstract: A novel machine learning (ML) framework for accurate real-time bus arrival time prediction integrates the ML model with a lightweight Dynamic Statistical Attention (DSA) technique. Real-time GPS data from Macao bus routes, synchronized with weather records, constitute the primary dataset. The DSA technique blends ML predictions with historical average arrival times to mitigate random fluctuations and improve result stability. Experimental results indicate that the proposed models, particularly KNN combined with DSA, deliver superior performance through lower mean absolute error, root mean square error, and mean absolute percentage error relative to previous hybrid neural network approaches. This framework provides a computationally efficient solution suitable for deployment in resource-constrained smart city public transport systems while sustaining high prediction accuracy under varying traffic and weather conditions.