Emotional Stroop Task Recognition by Band-Localize Fractal Dimension Method

Abstract

This study aims to investigate the association between bipolar dimension emotional model (based on band-localize fractal dimension (BLFD) feature) and Stroop colour-word test (STW). Twelve healthy participants are voluntarily took part in this study. Participants’ emotion during STW test was measured using a wireless electroencephalogram (EEG) sensor. Three STW sessions were introduced in this study based on different stress level induced. Alpha and beta frequency band were extracted from EEG signals using six-level wavelet decomposition. Then, BLFD features was computed based on Higuchi method. Lastly, valence and arousal levels were calculated and mapped to bipolar dimension model in estimating participant emotional states. Results showed that valence level was decreased at beginning of each session and increase towards the end of the session. On the other hand, decreasing trend was observed for arousal level at each session.