Deep BiLSTM neural network model for emotion detection using cross-dataset approach

• Published in: Biomedical signal processing and control Vol. 73; p. 103407
• Main Authors: Joshi, Vaishali M., Ghongade, Rajesh B., Joshi, Aditi M., Kulkarni, Rushikesh V.
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.03.2022
• Subjects: Cross-dataset; Deep RNN-BiLSTM; Electroencephalography; Emotions; Electroencephalography; Cross-dataset; Emotions; Deep RNN-BiLSTM
• ISSN: 1746-8094; 1746-8108
• DOI: 10.1016/j.bspc.2021.103407

•EEG-based cross-dataset emotion classification approach is used.•The research is carried out using two publicly available datasets, DEAP and SEED, and our own IDEA dataset.•A deep recurrent neural network (D-RNN) based on bidirectional long short-term memory (BiLSTM) used to develop network models for emotion classification.•The experimental results with deep learning outperform the classical methods. The purpose of this research is to use a cross-dataset approach to construct an EEG-based emotion recognition system. So far, numerous modeling strategies for emotion recognition have been revealed using the same dataset and subject-dependent and independent criteria. We propose EEG-based cross-dataset emotion classification in this study, where the datasets for training and testing are completely distinct. The research is carried out using two benchmark datasets, DEAP and SEED, as well as our own IDEA dataset. The three datasets differ in a variety of technical factors, including electroencephalography (EEG) devices, stimuli, methodology, subject, country, culture, and so on. Multilayer perceptron (MLP), support vector machine (SVM), k-nearest neighbors (k-NN), and deep RNNs model based on bidirectional long short-term memory (BiLSTM) network were trained in this study using features namely PSD, Hjorth parameters, DE, and LF-DE. When the DEAP dataset is used to train the model and the SEED dataset is used to test it, the recognition accuracy improves by 8.2 %, and when the model is the SEED dataset-trained and the DEAP dataset-tested, the recognition accuracy improves by 1.5 % when compared to the previous result. It has been revealed that LF-DE with BiLSTM outperforms other features and classifiers for the same input data. A deep neural network-BiLSTM gives deep features from the lowest level to the highest level from large datasets. The results of the experiments reveal that the optimization of deep neural network parameters can improve the performance of the emotion recognition system to a positive extent.