About

My research interests lie in Human-Computer Interaction (HCI), Human-Centered Computing, Human Behavior Modeling also in Transportation Informatics and Health Informatics. My goal is to bridge the gap between technological expertise and user-friendly experiences by leveraging advanced technologies and creating solutions aligned with user preferences. I am now working at Ubicomp Lab in National University of Singapore as a PhD Student with Prof. Brian lim. Before joining NUS, I spent 2 years as a Research Assistant at COOLA Lab in Southeast University, where I worked with Prof. Yan LYU and Prof. Wanyuan Wang

Publications

AAAI'24

i-Rebalance: Personalized Vehicle Repositioning for Supply Demand Balance
H Chen, P Sun, Q Song, W Wang, W Wu, W Zhang, G Gao, Y Lyu
[Link]

AIAHPC'22

Multi-agent Reinforcement Learning for Fleet Management: A Survey
H Chen, Z Li, X Yao
[Link]

Research Projects

Modularized Interpretable Medical Decision Support System with Visual Programming

Overview:
Current medical decision support systems (MDSS) provides fixed guidlines to doctors while each doctor has a unique way of diagnose, e.g. thresholds of indexes, sequence of examinations. Existing medical prediction tools also offer poor interpretability which is confusing to doctors. This project focuses on enabling doctors to build diagnostic models with their individual preference. With our toolkit, doctors can use visual programming to customize a prediction model that is highly interpretable and precise in practice. (Ongoing)

[GitHub Repo]

[GitHub Repo]

Personalized Vehicle Repositioning for Ride-hailing Platforms

Overview:
Traditional vehicle reposition techniques used in ride-hailing contexts turn out to have little effect due to their ignorance on drivers' preference and response behaviors. This project first demonstrates that drivers do have personalized cruising preferences and carried out experiments to prove it necessary to consider drivers' preference when repositioning. Our on-field User Study of 106 professional drivers further stressed that drivers do have preference and their preference is a key factor in their decision making process of whether to accept a reposition or not. Made up with three key modules: an LSTM predictor of drivers’ preferences, a decision model on drivers and a dual-agent DRL framework, our solution can both satisfy driver preferences and demand-supply gap. [GitHub Repo]

Ear Motion Tracking System for VR Devices

Overview:
Virtual Reality is trending, while there are devices like Xbox Adaptive Controller to provide accessibility for the people in need, they are still hard to use in VR context because people cannot see through a VR Headset. When people have to click a button, they can hardly find it without seeing it. This project detects ear motion and uses it as an input to the VR devices as a replacement of traditional controllers to provide accessibility to the people with special needs. Our user study on 15 volunteers showed that this method is effective and easy to use. This device gives everyone the access to control a VR device, even if they are not good at moving their ears.
[GitHub Repo]

Side Projects

C-H-ina: An Online Hotel Searching Service

Overview:
This project aims at building an online hotel searching website to provide access to hotels all over China. We crawled data and pictures of over 10,000+ hotels from booking.com. This website was built using SSM framework (Spring, Spring MVC, Mybatis) and has been on service for a semester.

[GitHub Repo]

Industrial Big-Data Inspection System

Overview:
IoT devices are widely used in industries like chemical and electricity, while they provide real-time monitoring of the facilities, they requires inspection as well. This system targets at providing convenient inspection system for factories, empowered with a dashboard and a InfloxDB time-series database driven anomaly detection algorithm.

[GitHub Repo]

Semantic Segmentation on CityScapes Dataset

Overview:
Semantic Segmentation is an essential technique used in autonomous driving. It helps the computer to distinguish different objects captured by the camera, making further decisions possible. We trained a U-net semantic segmentation model on CityScape Dataset with an accuracy of 76.75%.

[GitHub Repo]