SCALE@NTU Research Webinar Jul 2022

This research webinar on Teams is organized by Singtel Cognitive and Artificial Intelligence Lab for Enterprises (SCALE@NTU) to share the research work in the Corp Lab. For registration, please visit:

https://wis.ntu.edu.sg/pls/webexe88/REGISTER_NTU.REGISTER?EVENT_ID=OA22070813515633

Talk 1: Series Fed Patch Antenna Array for Vital Signs Measurement

For vital signs measurement of the human, we are using 77 GHz mmWave short range radar. The main component of the radar is the antenna through which the signals leave the device and reflected signals are collected back. Since the mmWave signals are relatively lossy, the series fed patch array antenna is used to have the required gain for the vital signs measurement.  The series fed patch array is designed with Dolph-Tschebyshev amplitude tapering. To reduce the loss due to impedance mismatch, usually a matching circuit is used. At 77 GHz, the matching is difficult to implement with realizable dimensions. To solve this problem, a new matching circuit based on stub loaded transmission line is designed for the series fed patch array antenna.

Speaker:Dr Manoj Prabhakar Mohan, Research Fellow, EEE, NTU (Former Research Fellow, SCALE@NTU)

Dr Manoj Prabhakar Mohan received his PhD from NTU,  Singapore. He has been working as Research Fellow in NTU from September 2019. His Research interests include microwave and mmWave circuits like filters, antenna, metalens and microwave wireless power transfer.

Talk 2:Learning to Solve Routing Problems via Distributionally Robust Optimization

Recent deep models for solving routing problems always assume a single distribution of nodes for training, which severely impairs their cross-distribution generalization ability. In this paper, we exploit group distributionally robust optimization (group DRO) to tackle this issue, where we jointly optimize the weights for different groups of distributions and the parameters for the deep model in an interleaved manner during training. We also design a module based on convolutional neural network, which allows the deep model to learn more informative latent pattern among the nodes. We evaluate the proposed approach on two types of well-known deep models including GCN and POMO. The experimental results on the randomly synthesized instances and the ones from two benchmark dataset (i.e., TSPLib and CVRPLib) demonstrate that our approach could significantly improve the cross-distribution generalization performance over the original models.

Speaker: Jiang Yuan, Research Associate, SCALE@NTU

Yuan Jiang received his Master degree in Computer Science from Jilin University, China, in 2018 and is currently pursuing Ph.D. in School of Computer Science and Engineering, Nanyang Technological University, Singapore. He is also working as a Research Associate in Singtel Cognitive and Artificial Intelligence Lab @NTU, Singapore, focusing on integrated planning framework for resource allocation in complex environment. His current research interests are deep learning and operation research.