Emotion detection using electroencephalography signals and a zero-time windowing-based epoch estimation and relevant electrode identification

Abstract

Recognizing emotions using biological brain signals requires accurate and efficient signal processing and feature extraction methods. Existing methods use several techniques to extract useful features from a fixed number of electroencephalography (EEG) channels. The primary objective of this study was to improve the performance of emotion recognition using brain signals by applying a novel and adaptive channel selection method that acknowledges that brain activity has a unique behavior that differs from one person to another and one emotional state to another. Moreover, we propose identifying epochs, which are the instants at which excitation is maximum, during the emotion to improve the system’s accuracy. We used the zero-time windowing method to extract instantaneous spectral information using the numerator group-delay function to accurately detect the epochs in each emotional state. Different classification scheme were defined using QDC and RNN and evaluated using the DEAP database. The experimental results showed that the proposed method is highly competitive compared with existing studies of multi-class emotion recognition. The average accuracy rate exceeded 89%. Compared with existing algorithms dealing with 9 emotions, the proposed method enhanced the accuracy rate by 8%. Moreover, experiment shows that the proposed system outperforms similar approaches discriminating between 3 and 4 emotions only. We also found that the proposed method works well, even when applying conventional classification algorithms.

A feature‐based on potential and differential entropy information for electroencephalogram emotion recognition

“…Soroush et al [19] selected informative channels based on the thresholded average activity value for EEG emotion recognition, reaching the accuracy of 90.54%. Gannouni et al [20] achieved an average accuracy rate of 89.33% by applying an automatic and adaptive channel selection method using the zero-time windowing method and using QDC and RNN as classifiers. As shown in the table, the method obtained better results than the listed methods in both binary and four-class EEG emotion classification tasks.…”

“…The next step is that EEG signals in one trial of each subject are divided into m frames, and the first frame serves as a baseline frame, the remaining m−1 are trial frames. Considering Theta band's worst performance in previous works [20][21][22], the MDE feature extracted from Theta band was regarded as the baseline. Each frame is n s wide and there is no overlapping between adjacent frames.…”

Facial Expression Recognition Based on Squeeze Vision Transformer

“…Emotion recognition can be broadly divided into bio- and image-based emotional recognition. Bio-based emotion recognition is a method used to train a computer to recognise emotions through various signals from different types of biosensors, such as an electroencephalograph [ 1 ], an electrocardiogram [ 2 ], and an electromyograph [ 3 ], and has the advantage of a high recognition rate. However, there is a limit in that a complex device must be worn, and no movements should occur during the sensing process.…”

A Photoplethysmogram Dataset for Emotional Analysis

“…Likewise, emotions are also considered important factors for humancomputer interactions (HCI) [2,3]. Some robots are designed to express emotions with eye movements [4,5], while certain machines are aimed at recognizing people's emotions using facial images and bio-signals [6,7].…”