Emotion recognition using Honey Badger algorithm and deep neural network methods

Nowadays, there is a high attention paid to human emotion recognition by using the electroencephalogram (EEG) signals based on machine learning technology. However, because of the high emotional variation, emotion recognition based on EEG is considered a high challenge in terms of pattern recognition. On the other hand, the Honey Badger (HB) algorithm is used to recognize several emotions such as happy, sad, angry, and others. Thus, this algorithm could attain several functions such as optimal selection of features, selection of a classifier, and setting of parameters based on various emotion datasets. Therefore, this paper presents a new method for human emotion recognition based on EEG signals. In the proposed method, the signals of the EEG are collected from the DREAMER database. Furthermore, the features of EEG signals are extracted using the Wavelet Transform (WT). The HB algorithm is used to select the most effective features of EEG signals and feed them to the classifier. For the classification part, there are several classifiers of Deep Neural Networks (DNNs) are used to classify the emotion classes. Experimental results show that the proposed method can achieve encouraging results with an accuracy of 82.5%. The proposed method using the HB algorithm demonstrates better performance than the standard features for analyzing EEG.