DETERMINING THE BEST FEATURE FOR IDENTIFYING THE IMAGINED WORD BASED ON EEG SIGNAL USING FEATURE IMPORTANCE SCORE METHOD

Yosrita, EY and Heryadi, YH and Wulandhari, LAW and Budiharto, WB (2021) DETERMINING THE BEST FEATURE FOR IDENTIFYING THE IMAGINED WORD BASED ON EEG SIGNAL USING FEATURE IMPORTANCE SCORE METHOD. ICIC Express Letters, 12 (11). pp. 1003-1009. ISSN 2185-2766

Text (DETERMINING THE BEST FEATURE FOR IDENTIFYING THE IMAGINED WORD BASED ON EEG SIGNAL USING FEATURE IMPORTANCE SCORE METHOD) elb-12-11-03.pdf - Published Version Download (275kB)

Abstract

The aim of this study is to select the best features of EEG signal, by investigating the AdaBoost feature importance score measure as a means to find a ranking of important features which can improve the classifier performance for recognizing the imagined speech of 8 Indonesian words, i.e., makan (eat), minum (drink), lapar (hungry), haus (thirsty), senang (happy), sedih (sad), sakit (sick) and toilet (toilet). The EEG signal was recorded from 11 healthy students, 7 men and 4 women, using Emotiv epoch and Emotiv Pro. Feature importance score was applied to AdaBoost model. Our research showed that the top ten features based on feature importance score ranking of AdaBoost model were T7 GAMMA, T7 THETA, P7 HIGH BETA, P8 GAMMA, P8 HIGH BETA, F3 GAMMA, F3 HIGH BETA, T7 HIGH BETA, P7 GAMMA and FC5

Actions (login required)

View Item