Editorial Board

Prof. Baolin LIU Ph.D.

Prof. Baolin LIU Ph.D.
Deputy Director, Tianjin key Laboratory of Cognitive Computing & Application,
Vice Dean, School of Computer Science and Technology,
Tianjin University

Biography :

Baolin Liu received his Ph.D. from Byelorussia State University, Byelorussia, in 1997. From 1999 to 2012, he had been a faculty member at Tsinghua University and was promoted to an associate professor and a professor. In 2013, He joined Tianjin University, and currently he is a full professor at School of Computer Science & Technology and the deputy director of Tianjin Key Laboratory of Cognitive Computing and Application. He is also an adjunct professor at State Key Laboratory of Intelligent Technology and Systems, Tsinghua University; and a visiting professor of Japan Advanced Institute of Science and Technology. Dr. Liu’s work is truly interdisciplinary. He has published many journal articles in the prestigious scientific journal such as Cerebral Cortex, Human Brain Mapping, NeuroImage, Neuroscience, Frontiers in Behavioral Neuroscience, Journal of Neural Engineering, etc., Dr. Liu is also the recipient of 12 national scientific research grants, and has received 2 prestigious awards and honors.

Research Interest :

Dr. Liu’s research emphasis has been placed on Data mining and computational models based on the neural information and bioinformatics systems, Decoding patterns of human brain activity, Emotional computation,Brain-like intelligent system and brain-like key technologies, and Brain-computer interface (BCI) & its application based on the insights into functions of brain, cognition, and behavior. He has made significant contributions to the cognitive computation of audio-visual information, in particular, in the field of cognitive integration of multisensory information, which will significantly change the intelligent information processing technologies and their applications. He and colleagues have pioneered an efficient spatial filtering algorithm by maximizing the SNR of the ERPs, which was based on a probabilistic generative model designed for estimating the time-locked and phase locked ERP components. The new approach opens a novel and revolutionary window into complex event-related brain data (EEG/ERP) based on the fact that the algorithm can converge within a few iterations warrants fast estimation of ERPs, in each iteration it merely has to solve a generalized eigen-value decomposition problem, and its computational load is quite low.