Detecting response of somatosensory evoked potentials from averages with small number of epochs using Self-Organizing Map

Author

Costa, J.C.G.D. ; Melges, D.B. ; Almeida, R.M.V.R. ; Infantosi, A.F.C.

Author_Institution

Dept. of Biomed. Eng., Fed. Univ. of Rio de Janeiro, Rio de Janeiro, Brazil

fYear

2011

fDate

March 28 2011-April 1 2011

Firstpage

291

Lastpage

296

Abstract

The aim of this work was to use the Self-Organizing Map (SOM) algorithm to classify EEG signals collected during somatosensory stimulation. Third-six volunteers participated and the signals were classified as containing or not cortical stimuli-response. Five features were used to characterize the signals, referring to the averages´ amplitude, latency and power spectral density using 500, 100 and 50 epochs. The SOM results clearly showed an adequate distinction between the two classes for 500 and 100 epochs. The SOM grid´s sizes were determined by applying non-parametric bootstrap technique.

Keywords

electroencephalography; mechanoception; medical signal processing; neuromuscular stimulation; self-organising feature maps; signal classification; statistical analysis; EEG signals; cortical stimuli-response; epochs; nonparametric bootstrap technique; power spectral density; self-organizing map algorithm; signal amplitude; signal classification; signal latency; somatosensory evoked potentials; somatosensory stimulation; Conferences; Couplings; Electroencephalography; IEEE catalog; Medical services; Neurons; Quantization; Bootstrap; Evoked Potential; Self-organizing map;

fLanguage

English

Publisher

ieee

Conference_Titel

Health Care Exchanges (PAHCE), 2011 Pan American

Conference_Location

Rio de Janeiro

Print_ISBN

978-1-61284-915-7

Type

conf

DOI

10.1109/PAHCE.2011.5871907

Filename

5871907