We Are Working on
Artificial Intelligence & Its Applications
I'm a Professor at the Graduate Institute of Automation Technology, National Taipei University of Technology. My current research focuses on autonomous driving, human activity recognition, and edge computing for smart living. Our lab has received granted projects on autonomous driving and deep learning-based activity recognition. We are recruiting graduate students at both the MS and Ph.D. levels with interests in autonomous driving and deep learning applications. Applicants that have a background or strong interests in computer vision, sensor fusion, and machine learning are welcome to join us. We are recruiting! Two postdoctoral positions are now available. Please visit https://bit.ly/3PyA9fU for more information.
Tel: +886-2-2771-2171 ext 4323
Email:
Office: 1, Sec. 3, Zhongxiao E. Rd., Taipei 10608 Taiwan
Complex Building, Room #605
Lab: +886-2-2771-2171 ext 4371
Complex Building, Room #606-1, #801B-2
Current Granted Research Projects:
-
Deep Learning for Autonomous Driving
-
Edge Computing in Autonomous Vehicles
-
Advanced Driver Assistance Systems (ADAS)
Research Topics on Smart Living Technology Fall, 2019
Courses
Artificial Neural Networks Spring, 2018
Data Analysis and Processing Fall, 2019
Artificial Intelligence
Spring, 2016
Machine Learning
Fall, 2017
Research Projects
Real-time Deep Learning based Object Detection Systems
We implemented a YOLO-v3 object detection system for pothole detection on FPGA in 2019. Check it out at https://youtu.be/WdMGS3K_N4g
FPGA-based Gesture Recognition Systems
This award-winning gesture recognition system was developed by our research team (兆棠, 柏全, 育弘, 舜傑) using Altera DE2-70. We won the best design award in Innovate Asia Competition and were reported in the news media in 2010.
A Double Layer Dementia Diagnosis System Using Machine Learning Techniques
Studies show that dementia is highly age-associated. Early diagnosis can help patient to receive timely treatment and slow down the deterioration. This study proposed a hierarchical double layer structure with multi-machine learning algorithms for early stage dementia diagnosis. This study won the best paper award at the 13th Engineering Applications of Neural Network Conference, held in London, 2012.
Vision-based Swimmer Tracking
This study implements hybrid mean-shift clustering and Kalman filter algorithms for swimmer tracking. Application of this method can be used as drowning incident detection to assist lifeguard in swimming pools.
Sensor-based Activity Recognition on Mobile Devices
Indoor Activity Recognition Based on Fuzzy Conditional Random Fields
People with dementia usually have difficulty in carrying out their daily living activities. There are benefits to be had from realizing ubiquitous computing for those dementia elders. In this study, an intelligent assistive system was developed based on a statistical model using conditional random fields for indoor activity recognition. This study won the Honorable Mention Award at the 11th International Conference on Automation Technology in 2011.
The Design and Implementation for Multiagent Based Smart Home Systems
This study proposed a multiagent based smart home system. It consists of several General Intelligent Appliance ageNTs (GIANTs) and Room Agents (RAs). A control network technology called Simple Control Protocol (SCP) was used to create SCP-enabled home appliances that can communicate with each other over low-speed power line communication networks. Through SCP-to-UPnP bridge, the SCP-enabled appliances can participate in Universal Plug and Play (UPnP) networks to form fully connected home networks. This study won the best thesis award from Institute of Information & Computing Machinery.
