Synchrosqueezing transform based feature extraction from EEG signals for emotional state prediction. (July 2019)

• Record Type: Journal Article
• Authors: Ozel, Pinar; Akan, Aydin; Yilmaz, Bulent
• Is Part Of: Biomedical signal processing and control. Volume 52(2019)
• Page Start: 152
• Page End: 161
• Publication Date: 2019-07
• Subjects: Emotion recognition -- Electroencephalography -- Synchrosqueezing transform -- Multivariate synchrosqueezing transform -- VAD model; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2019.04.023
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: In this paper, emotion estimation from multichannel EEG signals is investigated. Multivariate Synchrosqueezing Transform (MSST) is applied for the detection of 4 emotional states in valance-arousal space. SST and MSST are applied for the detection of 8 emotional states in valance-arousal-dominance space. SVM, kNN, Decision Trees, and Ensemble Classifiers are used for the detection, and their performances are compared. Abstract: This paper presents a novel method for emotion recognition based on time-frequency analysis using multivariate synchrosqueezing transform (MSST) of multichannel electroencephalography (EEG) signals. With the advancements of the multichannel sensor applications, the need for multivariate algorithms has become obvious for extracting features that stem from multichannel dependency in addition to mono-channel features. In order to model the joint oscillatory structure of these multichannel signals, MSST has recently been proposed. It uses the concepts of joint instantaneous frequency and bandwidth. Electrophysiological data processing mostly requires joint time-frequency analysis in addition to both time and frequency analysis separately. The short-time Fourier transform (STFT) and wavelet transform (WT) are the main approaches utilized in time-frequency analysis. In this paper, the feasibility and performance of multivariate wavelet-based synchrosqueezing algorithm was demonstrated on EEG signals obtained from publically available DEAP database by comparing with its univariate version. Eight emotional states were considered by combining arousal-valence and dominance dimensions. Using linear support vector machines (SVM) as a classifier, MSST and its univariate version resulted in the highest prediction accuracy rates of ˜93% among all emotional states.