ReliefF-Based EEG Sensor Selection Methods for Emotion Recognition

Abstract

Electroencephalogram (EEG) signals recorded from sensor electrodes on the scalp can directly detect the brain dynamics in response to different emotional states. Emotion recognition from EEG signals has attracted broad attention, partly due to the rapid development of wearable computing and the needs of a more immersive human-computer interface (HCI) environment. To improve the recognition performance, multi-channel EEG signals are usually used. A large set of EEG sensor channels will add to the computational complexity and cause users inconvenience. ReliefF-based channel selection methods were systematically investigated for EEG-based emotion recognition on a database for emotion analysis using physiological signals (DEAP). Three strategies were employed to select the best channels in classifying four emotional states (joy, fear, sadness and relaxation). Furthermore, support vector machine (SVM) was used as a classifier to validate the performance of the channel selection results. The experimental results showed the effectiveness of our methods and the comparison with the similar strategies, based on the F-score, was given. Strategies to evaluate a channel as a unity gave better performance in channel reduction with an acceptable loss of accuracy. In the third strategy, after adjusting channels’ weights according to their contribution to the classification accuracy, the number of channels was reduced to eight with a slight loss of accuracy (58.51% ± 10.05% versus the best classification accuracy 59.13% ± 11.00% using 19 channels). In addition, the study of selecting subject-independent channels, related to emotion processing, was also implemented. The sensors, selected subject-independently from frontal, parietal lobes, have been identified to provide more discriminative information associated with emotion processing, and are distributed symmetrically over the scalp, which is consistent with the existing literature. The results will make a contribution to the realization of a practical EEG-based emotion recognition system.

Review and Classification of Emotion Recognition Based on EEG Brain-Computer Interface System Research: A Systematic Review

“…Although the answer to what are the most emotion-relevant EEG features is still under investigation, power features from different frequency bands are still the most popular in the context of emotion recognition. Studies [26,197,218] have shown that power spectral density (PSD) extracted from EEG signals performs well on distinguishing affective states.…”

“…These proposed systems aim to explore or improve EEG-based emotion recognition systems. [2,39,41,42,49,50,57,61,63,92,104,108,109,117,131,136,149,152,157,173,174,185,186,189,191,[195][196][197][198][199][200][201][202][203][204][205][206][207][208][209]217,219,[223][224][225]229,[262][263][264][265][266]<...>…”

Personalised, Multi-Modal, Affective State Detection for Hybrid Brain-Computer Music Interfacing

“…This resulted in two participants being excluded at this stage. The remaining twenty participants had a mean age of 22 (range [19][20][21][22][23][24][25][26][27][28][29][30]. Nine of these participants were female.…”

“…Additionally, it has been shown that a combination of EEG and other physiological signals may be used to identify an individual's affective state when visual stimuli or combinations of visual and auditory stimuli are used [24], [25], [26], [27]. However, neurological responses to affective stimuli differ according to the modality of the stimuli [28], so affective state detection methods designed for visual stimuli may not work as well for musical stimuli.…”

Wearable Vibration Based Computer Interaction and Communication System for Deaf

“…ReliefF is a widely-used feature selection algorithm [34] that carries out the process of feature selection by handling a sample from a dataset and creating a model based on its nearness to other samples in its own class and distance from other classes [35]. This study applies the ReliefF feature selection method to evaluate every feature in comparison to other features and determine which features are more effective in the classification phase.…”