报告时间：2015年10月19日(周一)上午10：00

报告地点：学科3号楼S410会议室

报告人：张治国 教授

报告题目：Supervised Dimension Reduction for Multivariate Pattern Analysis of NeuroImaging Data （基于监督降维方法的神经影像多变量模式分析）

主持人：徐 军 教授

    欢迎广大师生踊跃参加！

                                                                                      江苏省大数据分析技术重点实验室

                                                                                             江苏省气象能源利用与控制工程技术研究中心

                                                                                                江苏省大气环境与装备技术协同创新中心

                                                                                                         信息与控制学院

                                                                                                          2015年10月19日

    报告摘要：Dimension reduction is essential in multivariate pattern analysis (MVPA) for identifying a small set of discriminative features that are predictive of class labels representing behavioral or cognitive states from high-dimensional neuroimaging data, such as multidimensional electroencephalogram (EEG) and functional magnetic resonance imaging (fMRI). Unsupervised dimension reduction techniques do not make use of class information and they may fail to accurately model the complex relationship between neuroimaging data and behavioral or cognitive parameters. As a result, they cannot reduce the dimension along the most effective directions. In the present work, we introduce two supervised dimension reduction methods, namely partial least-squares (PLS) and sliced inverse regression (SIR), for MVPA on high-dimensional EEG and fMRI data. We apply these methods on EEG and fMRI data recorded in laser-evoked pain experiment, with the aim to identify pain-related EEG and fMRI patterns as well as to predict the level of subjective pain perception from EEG and fMRI.

   报告人简介：Dr. Zhang Zhiguo is an Assistant Professor with the School of Chemical and Biomedical Engineering and School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore. Prior to joining NTU, he was an Assistant Professor in the Department of Electrical and Electronic Engineering at the University of Hong Kong. He received his B.Sc. degree from Tianjin University and his M.Phil. degree from the University of Science and Technology of China. He obtained his Ph.D. degree in the Department of Electrical and Electronic Engineering at the University of Hong Kong in 2008. He was a Research Assistant with the Department of Orthopaedics and Traumatology at the University of Hong Kong from 2007 to 2008, and a Visiting Postdoctoral Research Follow with the Department of Neuroscience, Physiology and Pharmacology at University College London in 2011. His research interests include neural engineering, biomedical signal processing, brain-computer interface, medical image analysis, and computational neuroscience.