Emotion recognition based on EEG features in movie clips with channel selection

Abstract

Emotion plays an important role in human interaction. People can explain their emotions in terms of word, voice intonation, facial expression, and body language. However, brain–computer interface (BCI) systems have not reached the desired level to interpret emotions. Automatic emotion recognition based on BCI systems has been a topic of great research in the last few decades. Electroencephalogram (EEG) signals are one of the most crucial resources for these systems. The main advantage of using EEG signals is that it reflects real emotion and can easily be processed by computer systems. In this study, EEG signals related to positive and negative emotions have been classified with preprocessing of channel selection. Self-Assessment Manikins was used to determine emotional states. We have employed discrete wavelet transform and machine learning techniques such as multilayer perceptron neural network (MLPNN) and k-nearest neighborhood (kNN) algorithm to classify EEG signals. The classifier algorithms were initially used for channel selection. EEG channels for each participant were evaluated separately, and five EEG channels that offered the best classification performance were determined. Thus, final feature vectors were obtained by combining the features of EEG segments belonging to these channels. The final feature vectors with related positive and negative emotions were classified separately using MLPNN and kNN algorithms. The classification performance obtained with both the algorithms are computed and compared. The average overall accuracies were obtained as 77.14 and 72.92% by using MLPNN and kNN, respectively.

Classification of Resting-State Status Based on Sample Entropy and Power Spectrum of Electroencephalography (EEG)

“…For instance, according to Zhang et al in [ 6 ], there were ten participants and they used eight electrodes, whereas in our study, there were nine participants and we used sixteen channels. In [ 12 ], the number of channels of the EEG was thirty-two with twenty participants whereas our data came from sixteen channels. According to Ahmad et al in [ 13 ], the number of channels was 128 with eight healthy participants.…”

“…Isa et al in [ 11 ], showed 70.08% KNN accuracy as the highest classification with Minkowski distance computation. Two classified conditions, which are represented in positive and negative emotions collected by EEGÖzerdem and Polat in [ 12 ], indicated 77.14% accuracy for multilayer perceptron neural network (MLPNN) and 72.92% for K-Nearest Neighborhood (KNN). Based on linear and nonlinear features derived from EEG, cognitive activity and resting-state conditions were classified by applying SVM and 92.1% was achieved applying nonlinear features whereas 87.5% of SVM was observed applying linear features [ 13 ].…”

Investigating Patterns for Self-Induced Emotion Recognition from EEG Signals

“…Time-frequency analysis is based on the spectrum of EEG signals, and the energy, power, power spectral density and differential entropy (DE) [ 17 ] of a certain subband are utilized as features. Short-time Fourier transform (STFT) [ 18 , 19 ], Hilbert-Huang transform [ 20 , 21 ] and discrete wavelet transform [ 22 , 23 , 24 , 25 ] are the most commonly used techniques for spectral calculation. Higher frequency subbands, such as Beta (16–32 Hz) and Gamma (32–64 Hz) bands, have been verified to outperform lower subbands in emotion recognition [ 3 , 26 ].…”

Survey on AI-Based Multimodal Methods for Emotion Detection

“…Özerdem and Polat used EEG signal, discrete wavelet transform and machine learning techniques (multilayer perceptron neural network -MLPNN, and k-nearest neighbors -kNN algorithms) [57].…”