Effects of Data Augmentation Method Borderline-SMOTE on Emotion Recognition of EEG Signals Based on Convolutional Neural Network
In recent years, with the continuous development of artificial intelligence and brain-computer interface technology, emotion recognition based on physiological signals, especially electroencephalogram signals, has become a popular research topic and attracted wide attention. However, the imbalance o...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2021-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9385376/ |
_version_ | 1798001938366726144 |
---|---|
author | Yu Chen Rui Chang Jifeng Guo |
author_facet | Yu Chen Rui Chang Jifeng Guo |
author_sort | Yu Chen |
collection | DOAJ |
description | In recent years, with the continuous development of artificial intelligence and brain-computer interface technology, emotion recognition based on physiological signals, especially electroencephalogram signals, has become a popular research topic and attracted wide attention. However, the imbalance of the data sets themselves, affective features’ extraction from electroencephalogram signals, and the design of classifiers with excellent performance, pose a great challenge to the subject. Motivated by the outstanding performance of deep learning approaches in pattern recognition tasks, we propose a method based on convolutional neural network with data augmentation method Borderline-synthetic minority oversampling technique. First, we obtain 32-channel electroencephalogram signals from DEAP data set, which is the standard data set of emotion recognition. Then, after data pre-processing, we extract features in frequency domain and data augmentation based on the data augmentation algorithm above for getting more balanced data. Finally, we train a one dimensional convolutional neural network for three classification on two emotional dimensions valence and arousal. Meanwhile, the proposed method is compared with some traditional machine learning methods and some existing methods by other researchers, which is proved to be effective in emotion recognition, and the average accuracy rate of 32 subjects on valence and arousal are 97.47% and 97.76% respectively. Compared with other existing methods, the performance of the proposed method with data augmentation algorithm Borderline-SMOTE shows its advantage in affective emotional recognition than that without Borderline-SMOTE. |
first_indexed | 2024-04-11T11:44:14Z |
format | Article |
id | doaj.art-335d52e0a1544a4ca90ba805de4d63e6 |
institution | Directory Open Access Journal |
issn | 2169-3536 |
language | English |
last_indexed | 2024-04-11T11:44:14Z |
publishDate | 2021-01-01 |
publisher | IEEE |
record_format | Article |
series | IEEE Access |
spelling | doaj.art-335d52e0a1544a4ca90ba805de4d63e62022-12-22T04:25:42ZengIEEEIEEE Access2169-35362021-01-019474914750210.1109/ACCESS.2021.30683169385376Effects of Data Augmentation Method Borderline-SMOTE on Emotion Recognition of EEG Signals Based on Convolutional Neural NetworkYu Chen0Rui Chang1https://orcid.org/0000-0001-6996-202XJifeng Guo2https://orcid.org/0000-0002-8692-6255College of Information and Computer Engineering, Northeast Forestry University, Harbin, ChinaCollege of Information and Computer Engineering, Northeast Forestry University, Harbin, ChinaCollege of Information and Computer Engineering, Northeast Forestry University, Harbin, ChinaIn recent years, with the continuous development of artificial intelligence and brain-computer interface technology, emotion recognition based on physiological signals, especially electroencephalogram signals, has become a popular research topic and attracted wide attention. However, the imbalance of the data sets themselves, affective features’ extraction from electroencephalogram signals, and the design of classifiers with excellent performance, pose a great challenge to the subject. Motivated by the outstanding performance of deep learning approaches in pattern recognition tasks, we propose a method based on convolutional neural network with data augmentation method Borderline-synthetic minority oversampling technique. First, we obtain 32-channel electroencephalogram signals from DEAP data set, which is the standard data set of emotion recognition. Then, after data pre-processing, we extract features in frequency domain and data augmentation based on the data augmentation algorithm above for getting more balanced data. Finally, we train a one dimensional convolutional neural network for three classification on two emotional dimensions valence and arousal. Meanwhile, the proposed method is compared with some traditional machine learning methods and some existing methods by other researchers, which is proved to be effective in emotion recognition, and the average accuracy rate of 32 subjects on valence and arousal are 97.47% and 97.76% respectively. Compared with other existing methods, the performance of the proposed method with data augmentation algorithm Borderline-SMOTE shows its advantage in affective emotional recognition than that without Borderline-SMOTE.https://ieeexplore.ieee.org/document/9385376/Electroencephalogramemotion recognitionBorderline-Synthetic minority oversampling techniqueconvolutional neural network |
spellingShingle | Yu Chen Rui Chang Jifeng Guo Effects of Data Augmentation Method Borderline-SMOTE on Emotion Recognition of EEG Signals Based on Convolutional Neural Network IEEE Access Electroencephalogram emotion recognition Borderline-Synthetic minority oversampling technique convolutional neural network |
title | Effects of Data Augmentation Method Borderline-SMOTE on Emotion Recognition of EEG Signals Based on Convolutional Neural Network |
title_full | Effects of Data Augmentation Method Borderline-SMOTE on Emotion Recognition of EEG Signals Based on Convolutional Neural Network |
title_fullStr | Effects of Data Augmentation Method Borderline-SMOTE on Emotion Recognition of EEG Signals Based on Convolutional Neural Network |
title_full_unstemmed | Effects of Data Augmentation Method Borderline-SMOTE on Emotion Recognition of EEG Signals Based on Convolutional Neural Network |
title_short | Effects of Data Augmentation Method Borderline-SMOTE on Emotion Recognition of EEG Signals Based on Convolutional Neural Network |
title_sort | effects of data augmentation method borderline smote on emotion recognition of eeg signals based on convolutional neural network |
topic | Electroencephalogram emotion recognition Borderline-Synthetic minority oversampling technique convolutional neural network |
url | https://ieeexplore.ieee.org/document/9385376/ |
work_keys_str_mv | AT yuchen effectsofdataaugmentationmethodborderlinesmoteonemotionrecognitionofeegsignalsbasedonconvolutionalneuralnetwork AT ruichang effectsofdataaugmentationmethodborderlinesmoteonemotionrecognitionofeegsignalsbasedonconvolutionalneuralnetwork AT jifengguo effectsofdataaugmentationmethodborderlinesmoteonemotionrecognitionofeegsignalsbasedonconvolutionalneuralnetwork |