Deputy Director, ST Engineering-NTU Corporate Lab
Director, Neuroengineering Program, School of EEE, NTU
Office: 6790 5410
Justin DAUWELS is an Associate Professor with School of Electrical & Electronic Engineering at Nanyang Technological University (NTU). He is also the Deputy Director of ST Engineering-NTU Corporate Lab and the Director of Neuroengineering Program at the School of EEE. His research interests are in Bayesian statistics, iterative signal processing, machine learning and computational neuroscience. Prior to joining NTU, Justin was a research scientist during 2008-2010 in the Stochastic Systems Group (SSG) at the Massachusetts Institute of Technology, led by Prof. Alan Willsky. He received postdoctoral training during 2006-2007 under the guidance of Prof. Shun-ichi Amari and Prof. Andrzej Cichocki at the RIKEN Brain Science Institute in Wako-shi, Japan. He obtained his PhD degree in electrical engineering from the Swiss Polytechnical Institute of Technology (ETH) in Zurich in December 2005. The research of his lab has been featured by BBC Click/World News, Singapore Straits Times, national TV, and various other media. Outcomes include real-time algorithms for large-scale urban traffic prediction; real-time algorithms for analysing human social behaviour; real-time noise-resilient algorithms for phase imaging; novel data analytics for biomedical signals; tools for large-scale modelling of extreme events.
Relevant research areas
Relevant ongoing projects in our lab include:
- Detection of mental states from EEG signals
- Data-driven dynamical models of human behavior
- Real time analysis of social interactions from audio-visual data and EEG signals
Research Interest in the Neuroscience of Learning and Education
Recent years have witnessed a paradigm shift in teaching methods to move beyond traditional strategies to improve learning and engagement. One such example is team based learning (TBL) that has been shown to work well especially in the context of medical education. However, instructors are often faced with the difficulty of assessing the team effectiveness and students’ engagement that is shaped through social interactions. We propose a multipronged approach to studying team based learning by combining social physics, social signal processing and social neuroscience methods.
a) Social physics: To quantify information flow between students of the entire class or even department, in order to predict outcomes of team-based learning from digital bread crumbs such as learning platforms, forums etc.
b) Social indicators: To quantify the nature of social interactions through real-time analysis of social behavior as markers to predict outcomes of team-based learning. Example: social indicators such as interest, confusion, dominance, frustration can be automatically analyzed to provide feedback to improve learning.
c) Social neuroscience: To investigate the underlying brain process to look for neural markers to predict outcomes of team-based learning (e.g., synchrony between brain signals from students). Our preliminary results in a gaming context involving EEG recordings during social interactions show that higher scores are proportional to higher connectivity (EEG signal synchrony) among the team members.