Hybrid Deep Learning Approach for Stress Detection Using Decomposed EEG Signals
Stress has an impact, not only on a person’s physical health, but also on the ability to perform at the workplace in daily life. The well-established relation between psychological stress and its pathogeneses highlights the need for detecting psychological stress early, in order to prevent disease a...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-06-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/13/11/1936 |
| _version_ | 1797597703770734592 |
|---|---|
| author | Bishwajit Roy Lokesh Malviya Radhikesh Kumar Sandip Mal Amrendra Kumar Tanmay Bhowmik Jong Wan Hu |
| author_facet | Bishwajit Roy Lokesh Malviya Radhikesh Kumar Sandip Mal Amrendra Kumar Tanmay Bhowmik Jong Wan Hu |
| author_sort | Bishwajit Roy |
| collection | DOAJ |
| description | Stress has an impact, not only on a person’s physical health, but also on the ability to perform at the workplace in daily life. The well-established relation between psychological stress and its pathogeneses highlights the need for detecting psychological stress early, in order to prevent disease advancement and to save human lives. Electroencephalography (EEG) signal recording tools are widely used to collect these psychological signals/brain rhythms in the form of electric waves. The aim of the current research was to apply automatic feature extraction to decomposed multichannel EEG recordings, in order to efficiently detect psychological stress. The traditional deep learning techniques, namely the convolution neural network (CNN), long short-term memory (LSTM), bidirectional long short-term memory (BiLSTM), gated recurrent unit (GRU) and recurrent neural network (RNN) models, have been frequently used for stress detection. A hybrid combination of these techniques may provide improved performance, and can handle long-term dependencies in non-linear brain signals. Therefore, this study proposed an integration of deep learning models, called DWT-based CNN, BiLSTM, and two layers of a GRU network, to extract features and classify stress levels. Discrete wavelet transform (DWT) analysis was used to remove the non-linearity and non-stationarity from multi-channel (14 channel) EEG recordings, and to decompose them into different frequency bands. The decomposed signals were utilized for automatic feature extraction using the CNN, and the stress levels were classified using BiLSTM and two layers of GRU. This study compared five combinations of the CNN, LSTM, BiLSTM, GRU and RNN models with the proposed model. The proposed hybrid model performed better in classification accuracy compared to the other models. Therefore, hybrid combinations are appropriate for the clinical intervention and prevention of mental and physical problems. |
| first_indexed | 2024-03-11T03:09:15Z |
| format | Article |
| id | doaj.art-18bc96b413fe4ee29e76f163ce34c5ee |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-11T03:09:15Z |
| publishDate | 2023-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-18bc96b413fe4ee29e76f163ce34c5ee2023-11-18T07:43:05ZengMDPI AGDiagnostics2075-44182023-06-011311193610.3390/diagnostics13111936Hybrid Deep Learning Approach for Stress Detection Using Decomposed EEG SignalsBishwajit Roy0Lokesh Malviya1Radhikesh Kumar2Sandip Mal3Amrendra Kumar4Tanmay Bhowmik5Jong Wan Hu6Department of Computer Science Engineering-AI & ML, Siliguri Institute of Technology, Siliguri 734009, IndiaSchool of Computing Science and Engineering, Vellore Institute of Technology Bhopal University, Bhopal 466114, IndiaDepartment of Computer Science and Engineering, National Institute of Technology, Patna 800001, IndiaSchool of Computing Science and Engineering, Vellore Institute of Technology Bhopal University, Bhopal 466114, IndiaDepartment of Civil Engineering, Roorkee Institute of Technology, Roorkee 247667, IndiaDepartment of Computer Science and Engineering, Pandit Deendayal Energy University, Gandhinagar 382426, IndiaDepartment of Civil and Environmental Engineering, Incheon National University, Incheon 22022, Republic of KoreaStress has an impact, not only on a person’s physical health, but also on the ability to perform at the workplace in daily life. The well-established relation between psychological stress and its pathogeneses highlights the need for detecting psychological stress early, in order to prevent disease advancement and to save human lives. Electroencephalography (EEG) signal recording tools are widely used to collect these psychological signals/brain rhythms in the form of electric waves. The aim of the current research was to apply automatic feature extraction to decomposed multichannel EEG recordings, in order to efficiently detect psychological stress. The traditional deep learning techniques, namely the convolution neural network (CNN), long short-term memory (LSTM), bidirectional long short-term memory (BiLSTM), gated recurrent unit (GRU) and recurrent neural network (RNN) models, have been frequently used for stress detection. A hybrid combination of these techniques may provide improved performance, and can handle long-term dependencies in non-linear brain signals. Therefore, this study proposed an integration of deep learning models, called DWT-based CNN, BiLSTM, and two layers of a GRU network, to extract features and classify stress levels. Discrete wavelet transform (DWT) analysis was used to remove the non-linearity and non-stationarity from multi-channel (14 channel) EEG recordings, and to decompose them into different frequency bands. The decomposed signals were utilized for automatic feature extraction using the CNN, and the stress levels were classified using BiLSTM and two layers of GRU. This study compared five combinations of the CNN, LSTM, BiLSTM, GRU and RNN models with the proposed model. The proposed hybrid model performed better in classification accuracy compared to the other models. Therefore, hybrid combinations are appropriate for the clinical intervention and prevention of mental and physical problems.https://www.mdpi.com/2075-4418/13/11/1936EEGDWTCNNLSTMBiLSTMGRU |
| spellingShingle | Bishwajit Roy Lokesh Malviya Radhikesh Kumar Sandip Mal Amrendra Kumar Tanmay Bhowmik Jong Wan Hu Hybrid Deep Learning Approach for Stress Detection Using Decomposed EEG Signals Diagnostics EEG DWT CNN LSTM BiLSTM GRU |
| title | Hybrid Deep Learning Approach for Stress Detection Using Decomposed EEG Signals |
| title_full | Hybrid Deep Learning Approach for Stress Detection Using Decomposed EEG Signals |
| title_fullStr | Hybrid Deep Learning Approach for Stress Detection Using Decomposed EEG Signals |
| title_full_unstemmed | Hybrid Deep Learning Approach for Stress Detection Using Decomposed EEG Signals |
| title_short | Hybrid Deep Learning Approach for Stress Detection Using Decomposed EEG Signals |
| title_sort | hybrid deep learning approach for stress detection using decomposed eeg signals |
| topic | EEG DWT CNN LSTM BiLSTM GRU |
| url | https://www.mdpi.com/2075-4418/13/11/1936 |
| work_keys_str_mv | AT bishwajitroy hybriddeeplearningapproachforstressdetectionusingdecomposedeegsignals AT lokeshmalviya hybriddeeplearningapproachforstressdetectionusingdecomposedeegsignals AT radhikeshkumar hybriddeeplearningapproachforstressdetectionusingdecomposedeegsignals AT sandipmal hybriddeeplearningapproachforstressdetectionusingdecomposedeegsignals AT amrendrakumar hybriddeeplearningapproachforstressdetectionusingdecomposedeegsignals AT tanmaybhowmik hybriddeeplearningapproachforstressdetectionusingdecomposedeegsignals AT jongwanhu hybriddeeplearningapproachforstressdetectionusingdecomposedeegsignals |