EEG Emotion Recognition Based on Temporal and Spatial Features of Sensitive signals

Abstract

Currently, there are some problems in the electrocorticogram (EEG) emotion recognition research, such as single feature, redundant signal, which make it impossible to achieve high-precision recognition accuracy when used a few channel signals. To solve the abovementioned problems, the authors proposed a method for emotion recognition based on long short-term memory (LSTM) neural network and convolutional neural network (CNN) combined with neurophysiological knowledge. First, the authors selected emotion-sensitive signals based on the physiological function of EEG regions and the active scenario of the band signals, and then merged temporal and spatial features extracted from sensitive signals by LSTM and CNN. Finally, merged features were classified to recognize emotion. The method was experimented on the DEAP dataset, the average accuracy in the valence and arousal dimensions were 92.87% and 93.23%, respectively. Compared with similar studies, it not only improved the recognition accuracy, but also greatly reduced the calculation channel, which proved the superiority of the method.

Electroencephalogram based human emotion classification for valence and arousal using machine learning approach

“…CNN gave classification accuracy of 85.27%. A method for emotion recognition from DEAP dataset was proposed by Qu and Zheng [20] based on long short-term memory (LSTM) and CNN. It considered temporal and spatial features that gave valence and arousal classification accuracies of 92.87% and 93.23% respectively.…”

“…Table 1 shows a list of various features that are identified after extensive literature review. Entropy and Higuchi's FD Qu and Zheng [20] Temporal and spatial features Gao et al [28] PSD, energy, entropy Kumar et al [21] Mean, SD, Skewness and shannon entropy Gao et al [29] Time-frequency and spatial features Kusumaningrum et al [22] HP and PSD George et al [30] Minimum, maximum, SD, variance, Skewness, Kurtosis, entropy, power bandwidth Galvão et al [23] Spectral entropy, HP, energy and entropy Mehmood et al [31] Hjorth-activity This paper attempts to identify the suitable features and methods and aims towards obtaining higher accuracy for EEG based emotion classification. Two research objectives are raised for this work: i) to extract and find appropriate features from EEG signals that can best relate to human emotions and analyze the relationships between EEG signals and human emotions for improving accuracy; and ii) to contribute in enhancement of emotion recognition technologies, that can be widely useful for applications like assessment of mental health, brain computer interfacing and responsive systems.…”

Cascaded Convolutional Recurrent Neural Networks for EEG Emotion Recognition Based on Temporal–Frequency–Spatial Features

“…Finally, the spatial-frequency information was extracted by different 2D convolutions. Researchers in [25][26][27][28] introduced a combined CNN and LSTM model that learns spatial-frequency and temporal features, respectively, from the input signal. Experimental findings reveal that the accuracy of combined multidimensional feature information surpasses that of a single dimension.…”

“…Most studies choose to remove this part of the data directly when recognizing the task and consider only the EEG signal in the stimulated state. Studies [25,30,31] demonstrated that preprocessing through the baseline signal is effective for improving experimental robustness. The difference between the signal of the subject under the emotional stimulus and the baseline signal was calculated as an indication that the segment's emotional state data could yield the expected results.…”

Retracted: EEG Emotion Recognition Based on Temporal and Spatial Features of Sensitive signals

“…Tis article has been retracted by Hindawi following an investigation undertaken by the publisher [1]. Tis investigation has uncovered evidence of one or more of the following indicators of systematic manipulation of the publication process:…”