E2ENNet: An end-to-end neural network for emotional brain-computer interface

Abstract

ObjectveEmotional brain-computer interface can recognize or regulate human emotions for workload detection and auxiliary diagnosis of mental illness. However, the existing EEG emotion recognition is carried out step by step in feature engineering and classification, resulting in high engineering complexity and limiting practical applications in traditional EEG emotion recognition tasks. We propose an end-to-end neural network, i.e., E2ENNet.MethodsBaseline removal and sliding window slice used for preprocessing of the raw EEG signal, convolution blocks extracted features, LSTM network obtained the correlations of features, and the softmax function classified emotions.ResultsExtensive experiments in subject-dependent experimental protocol are conducted to evaluate the performance of the proposed E2ENNet, achieves state-of-the-art accuracy on three public datasets, i.e., 96.28% of 2-category experiment on DEAP dataset, 98.1% of 2-category experiment on DREAMER dataset, and 41.73% of 7-category experiment on MPED dataset.ConclusionExperimental results show that E2ENNet can directly extract more discriminative features from raw EEG signals.SignificanceThis study provides a methodology for implementing a plug-and-play emotional brain-computer interface system.

Comprehensive Analysis of Feature Extraction Methods for Emotion Recognition from Multichannel EEG Recordings

“…Firstly, it would be interesting to explore deep learning classifiers as an alternative for CART and SVM. In recent years, convolutional layers of deep neural networks have been found successful in EEG-based classification of emotion [ 54 , 55 ]. It was not feasible to explore this approach here due to lack of data.…”

GCF2-Net: global-aware cross-modal feature fusion network for speech emotion recognition

“…However, humans express emotions not only through speech but also in many other ways, such as text, body gestures, facial expressions (Zhang et al, 2022 ), and electroencephalography (EEG) (Chang et al, 2022 , 2023 ; Han et al, 2022 ). Chakravarthi et al ( 2022 ) proposed an automated CNN-LSTM with the ResNet-152 algorithm to identify emotional states from EEG signals.…”

Subject-Independent EEG Emotion Recognition Based on Genetically Optimized Projection Dictionary Pair Learning

“…This capability has the potential to advance the diagnosis and treatment of emotional disorders such as depression [2], anxiety [3], and post-traumatic stress disorder (PTSD) [4]. Moreover, the EEG holds promise for diverse applications, including human-computer interaction [5], affective computing [6,7], marketing research, and entertainment. Consequently, the development of reliable and accurate EEG emotion recognition systems bears great significance for the scientific community and society at large.…”

“…(5) Hidden Markov Models (HMMs) capture the temporal dynamics of EEG signals for emotion recognition [14]. (6) Multimodal emotion recognition combines EEG data with other modalities, such as facial expressions, speech, or physiological signals, to enhance the accuracy of EEG emotion recognition [15,16]. (7) Artificial Neural Networks (ANNs) are trained on the EEG signal to recognize different emotional states based on the extracted features [17].…”

“…The threshold ranges and coding methods for these parameters are provided in Table 3. FieldD 1 m τ λ γ len 2 9 9 9 9 lb 3 1 0 0 0 ub 3 310/70 * 0.1 0.01 0.001 code 4 gray gray gray gray scale 5 arithmetic arithmetic arithmetic arithmetic lbin 6 0 0 1 1 ubin 6 1 1 1 1…”