Mr. Zhihan Cui (3rd-year doctoral student in Lim Lab, Next-generation Digital Infrastructure Research Area) received the Outstanding Presentation Award at the FY2024 Research Meeting organized by the IEICE Technical Committee on "Sensor Networks and Mobile Intelligence" (SeMI).

The SeMI Technical Committee focuses on research areas centered around mobile sensors, including sensing technologies, mobility technologies, and mobile ubiquitous computing. By integrating these elements through networking technologies, it aims to create intelligent environments. Furthermore, the committee provides a platform for presenting and discussing applications that emerge from such environments.
The Outstanding Presentation Award is given to presentations that have made a particularly strong impact and stimulated active discussion across SeMI research meetings.

＊Reference：Technical Committee on Sensor Networks and Mobile Intelligence (SeMI)

■Date Awarded
July 31, 2025

■Title
Broad Learning System Scheme for Multi-server Wireless Networks

■Authors
Zhihan Cui, Jiancheng Chi, Yuto Lim, Yasuo Tan

■Abstract
Multi-access edge computing (MEC) that can support context aware and delay sensitive applications allows the cloud service computation to run at the edge of the network. MEC can utilize a wireless network to connect all kinds of IoT devices to rapidly analyze data in real-time manner. However, the explosion of connected devices to deliver data will results low net- work capacity and high latency due to the uncertainty of devices choosing the right MEC server. In this paper, we define multi-MEC server wireless networks (MSWNs) as a type of wireless communication network where each device in the network can communicate with a MEC server directly. This paper explores the use of the broad learning system (BLS) for optimizing the network performances in MSWNs. Besides that, we introduce three different strategies based on the BLS scheme: BLS with minimum time delay (BLS/MT), BLS with nearest MEC server (BLS/NS), and BLS with maximum signal-to-interference-plus-noise ratio (BLS/MS), aimed at enhancing network capacity and reducing latency. Through simulations, we analyze the performance of these strategies by varying different network conditions. Our results reveal that, particularly in dense network environments, by effectively selecting the maximum SINR in the wireless networks, BLS/MS can significantly outperform the network capacity and network latency of BLS/MT and BLS/NS.

■Comment
It is a great honor to receive this award from the IEICE Technical Committee on Sensor Network and Mobile Intelligence (SeMI). This award recognizes my research on AI-driven optimization for multi-server wireless multihop networks. I am truly grateful to my supervisors, Professor Yuto Lim and Professor Yasuo Tan, for their continuous support and guidance, and to JAIST for providing a stimulating research environment. This recognition encourages me to continue advancing my work and to contribute to the development of next-generation communication networks that benefit both academia and society.

October 14, 2025