Introduction to statistical pattern recognition (2nd ed.)
Introduction to statistical pattern recognition (2nd ed.)
Fast and robust fixed-point algorithms for independent component analysis
IEEE Transactions on Neural Networks
Multi-channel EEG signal segmentation and feature extraction
INES'10 Proceedings of the 14th international conference on Intelligent engineering systems
Common spatiotemporal pattern analysis
LVA/ICA'10 Proceedings of the 9th international conference on Latent variable analysis and signal separation
| Hi-index | 0.00 |
Evoked and coordinated brain signals often exhibit distinct, individualized spatial and temporal characteristics, such as amplitude and phase couplings across and within spatial channels. In the study of these brain potentials, it is important to characterize both the spatial and temporal morphologies of the responses for a better understanding of both the physiology and function of the brain. This paper presents a method for visualizing the characteristic spatio-temporal brain activity associated with two distinct conditions. This method, called Independent Spatio-Temporal Patterns (ISTPs), extends Common Spatial Patterns (CSPs) for spatio-temporal pattern visualization by adding temporal features. Independent component analysis (ICA) is then applied to extract independent spatio-temporal patterns corresponding to each condition. The results indicate that the inclusion of temporal features can provide useful insight regarding the spatio-temporal characteristics of sensorimotor rhythms.