报告题目：Neuroimaging Data Processing, Analysis, and Classification: Using Brain Connectivity and Machine Learning
EEG and fMRI data were prevalently utilized to explore brain functions pertaining to particular mental states or psychiatric diseases. In this presentation, I will report a few experiments looking insights into brain related to the above two aspects. Methods and results will be shown along with the demonstrations of experiments as videos. Functional connectivity will be focused in this presentation. Specifically, I will show how functional connectivity changes with the progression of fatigue, how functional connectivity alters at the different levels of workload, what the different inter-regional organizations are under different walking conditions with and without an exoskeleton. The findings derived from the above studies were used to guide the feature extraction to facilitate the decoding of brain states. In addition, I will also present our proposed methodology of dynamic functional connectivity and the model of deep learning.
Junhua Li currently is a senior research fellow at the National University of Singapore, Singapore and will be a lecturer (permanent) at the University of Essex, UK soon. Before joining the National University of Singapore, He was a research scientist at the RIKEN, Japan. His research interests are brain computer interface, computational neuroscience, machine learning, and brain connectivity. He has published 48 peer-referred academic papers, 25 of which are indexed by the SCI. He is an IEEE Senior Member, and served as a member of program committee of international conferences (e.g., the 8th International Workshop on Pattern Recognition in Neuroimaging) and Guest Associate Editor for special issues (e.g., Frontiers in Neuroscience, Special Issue in “Recent Developments of Deep Learning in Analyzing, Decoding, and Understanding Neuroimaging Signals”). He was awarded a grant from the National Natural Science Foundation of China. He supervised a student working on gait pattern recognition, by which his student received the award of Finalist in the 2017 EMBS Student Paper Competition.