ICA-SVM combination algorithm for identification of motor imagery potentials

Abstract

Mental tasks such as motor imagery in synchronization with a cue which result event related desynchronization (ERD) and event related synchronization (ERS) are usually studied in brain-computer interface (BCI) system. In this paper we analyze and classify the ERD/ERS response evoked by the motor imagery of left hand, right hand, foot and tongue. The signals were spatially filtered by Independent Component Analysis (ICA) before calculating the power spectral density (PSD) for related electrodes, and then the Support Vector Machine (SVM) was adopted to recognise the different imagery pattern according to ERD/ERS feature for the signals. The results showed that the combination of ICA-based signal extraction algorithm and SVM-based classification method was an effective tool for the identification of motor imagery potentials, with the highest accuracy rate of 91.4% and 77.6% for the lowest.

Performance of channel selection used for Multi-class EEG signal classification of motor imagery

“…There have been a lot of discussions on the imagination of left and right hand movements with many reliable results for its characteristic frequency band and the corresponding cortical activity in the region of cerebral cortex. But the research on the foot and tongue is still limited [3].…”

Classificação Com Máquina De Vetores De Suporte E Coerência Na Imagética Motora Com Prática Mental

“…Os estudos realizados por Ahmadi et al [4] demonstraram que a utilização de redes neurais probabilísticas recorrentes para classificação de movimentos de preensão da mão direta e esquerda com prática mental incrementou a taxa de acerto da primeira sessão (80%) -processamento off line e sem treinamento-em comparação com a última sessão e utilizando uma única imaginação (73% a 91%). Entretanto, Ming et al [5] utilizaram a Máquina de Vetores de Suporte (SVM) em conjunto com análises de componentes independentes para a classificação de movimentos motores encontrando uma taxa de acerto entre 77,6% e 91,4%.…”