Extracting Spatio-temporal Feature for Classification of Event-related Potentials*

Functional magnetic resonance imaging studies have indicated that efficient feature search (FS) and inefficient conjunction search (CS) activate partially distinct frontoparietal cortical networks. However, it remains a matter of debate whether the differences in these networks reflect differences in the early processing during FS and CS. In addition, the relationship between the differences in the networks and spatial shifts of attention also remains unknown. We examined these issues by applying a spatio-temporal analysis method to high-resolution visual event-related potentials (ERPs) and investigated how spatio-temporal activation patterns differ for FS and CS tasks. Within the first 450 msec after stimulus onset, scalp potential distributions (ERP maps) revealed 7 different electric field configurations for each search task. Configuration changes occurred simultaneously in the two tasks, suggesting that contributing processes were not significantly delayed in one task compared to the other. Despite this high spatial and temporal correlation, two ERP maps (120–190 and 250–300 msec) differed between the FS and CS. Lateralized distributions were observed only in the ERP map at 250–300 msec for the FS. This distribution corresponds to that previously described as the N2pc component (a negativity in the time range of the N2 complex over posterior electrodes of the hemisphere contralateral to the target hemifield), which has been associated with the focusing of attention onto potential target items in the search display. Thus, our results indicate that the cortical networks involved in feature and conjunction searching partially differ as early as 120 msec after stimulus onset and that the differences between the networks employed during the early stages of FS and CS are not necessarily caused by spatial attention shifts.

Download Full-text

Event-Related Potentials

10.1093/med/9780190228484.003.0039 ◽

2017 ◽

Cited By ~ 1

Author(s):

Marco Congendo ◽

Fernando H. Lopes da Silva

Keyword(s):

Principal Component ◽

Event Related Potentials ◽

Component Analysis ◽

Statistical Testing ◽

Time Averaging ◽

Common Spatial Pattern ◽

Topographic Analysis ◽

Temporal Filtering ◽

Related Potentials ◽

Spatio Temporal

Event-related potentials (ERPs) can be elicited by a variety of stimuli and events in diverse conditions. This chapter covers the methodology of analyzing and quantifying ERPs in general. Basic models (additive, phase modulation and resetting, potential asymmetry) that account for the generation of ERPs are discussed. The principles and requirements of ensemble time averaging are presented, along with several univariate and multivariate methods that have been proposed to improve the averaging procedure: wavelet decomposition and denoising, spatial, temporal and spatio-temporal filtering. We emphasize basic concepts of principal component analysis, common spatial pattern, and blind source separation, including independent component analysis. We cover practical questions related to the averaging procedure: overlapping ERPs, correcting inter-sweep latency and amplitude variability, alternative averaging methods (e.g., median), and estimation of ERP onset. Some specific aspects of ERP analysis in the frequency domain are surveyed, along with topographic analysis, statistical testing, and classification methods.

Download Full-text