An End-to-End Brain Computer Interface System for Mental Workload Estimation through Hybrid Deep Learning Model
Abstract In this paper, a new cascade one-dimensional convolutional neural network (1DCNN) and bidirectional long short-term memory (BLSTM) model has been developed for binary and ternary classification of mental workload (MWL). MWL assessment is important to increase the safety and efficiency in br...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer Nature
2024-11-01
|
| Series: | Human-Centric Intelligent Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s44230-024-00086-y |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841544596957429760 |
|---|---|
| author | Vipul Sharma Mitul Kumar Ahirwal |
| author_facet | Vipul Sharma Mitul Kumar Ahirwal |
| author_sort | Vipul Sharma |
| collection | DOAJ |
| description | Abstract In this paper, a new cascade one-dimensional convolutional neural network (1DCNN) and bidirectional long short-term memory (BLSTM) model has been developed for binary and ternary classification of mental workload (MWL). MWL assessment is important to increase the safety and efficiency in brain–computer interface (BCI) systems and professions, where multi-tasking is required. Keeping in mind the necessity of MWL assessment, a two-fold study is presented, firstly binary classification is done to classify MWL into low and high classes. Secondly, ternary classification is applied to classify MWL into low, moderate, and high classes. The cascaded1DCNN-BLSTM deep learning architecture has been developed and tested over the Simultaneous task EEG workload (STEW) dataset. Unlike recent research in MWL, handcrafted feature extraction and engineering are not done, rather end-to-end deep learning is used over 14 channel EEG signals for classification. Accuracies exceeding the previous state-of-the-art studies have been obtained. In binary and ternary classification accuracies of 96.77% and 95.36%have been achieved with sevenfold cross-validation, respectively. |
| format | Article |
| id | doaj-art-8274cf4cbde8485fb9714e33b636f6f7 |
| institution | Kabale University |
| issn | 2667-1336 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | Springer Nature |
| record_format | Article |
| series | Human-Centric Intelligent Systems |
| spelling | doaj-art-8274cf4cbde8485fb9714e33b636f6f72025-01-12T12:26:41ZengSpringer NatureHuman-Centric Intelligent Systems2667-13362024-11-014459960910.1007/s44230-024-00086-yAn End-to-End Brain Computer Interface System for Mental Workload Estimation through Hybrid Deep Learning ModelVipul Sharma0Mitul Kumar Ahirwal1Department of Computer Science and Engineering, Maulana Azad National Institute of TechnologyDepartment of Computer Science and Engineering, Maulana Azad National Institute of TechnologyAbstract In this paper, a new cascade one-dimensional convolutional neural network (1DCNN) and bidirectional long short-term memory (BLSTM) model has been developed for binary and ternary classification of mental workload (MWL). MWL assessment is important to increase the safety and efficiency in brain–computer interface (BCI) systems and professions, where multi-tasking is required. Keeping in mind the necessity of MWL assessment, a two-fold study is presented, firstly binary classification is done to classify MWL into low and high classes. Secondly, ternary classification is applied to classify MWL into low, moderate, and high classes. The cascaded1DCNN-BLSTM deep learning architecture has been developed and tested over the Simultaneous task EEG workload (STEW) dataset. Unlike recent research in MWL, handcrafted feature extraction and engineering are not done, rather end-to-end deep learning is used over 14 channel EEG signals for classification. Accuracies exceeding the previous state-of-the-art studies have been obtained. In binary and ternary classification accuracies of 96.77% and 95.36%have been achieved with sevenfold cross-validation, respectively.https://doi.org/10.1007/s44230-024-00086-yBidirectional long short-term memoryBrain–computer interfaceMultivariate time series classificationConvolutional neural networksDeep learningElectroencephalography |
| spellingShingle | Vipul Sharma Mitul Kumar Ahirwal An End-to-End Brain Computer Interface System for Mental Workload Estimation through Hybrid Deep Learning Model Human-Centric Intelligent Systems Bidirectional long short-term memory Brain–computer interface Multivariate time series classification Convolutional neural networks Deep learning Electroencephalography |
| title | An End-to-End Brain Computer Interface System for Mental Workload Estimation through Hybrid Deep Learning Model |
| title_full | An End-to-End Brain Computer Interface System for Mental Workload Estimation through Hybrid Deep Learning Model |
| title_fullStr | An End-to-End Brain Computer Interface System for Mental Workload Estimation through Hybrid Deep Learning Model |
| title_full_unstemmed | An End-to-End Brain Computer Interface System for Mental Workload Estimation through Hybrid Deep Learning Model |
| title_short | An End-to-End Brain Computer Interface System for Mental Workload Estimation through Hybrid Deep Learning Model |
| title_sort | end to end brain computer interface system for mental workload estimation through hybrid deep learning model |
| topic | Bidirectional long short-term memory Brain–computer interface Multivariate time series classification Convolutional neural networks Deep learning Electroencephalography |
| url | https://doi.org/10.1007/s44230-024-00086-y |
| work_keys_str_mv | AT vipulsharma anendtoendbraincomputerinterfacesystemformentalworkloadestimationthroughhybriddeeplearningmodel AT mitulkumarahirwal anendtoendbraincomputerinterfacesystemformentalworkloadestimationthroughhybriddeeplearningmodel AT vipulsharma endtoendbraincomputerinterfacesystemformentalworkloadestimationthroughhybriddeeplearningmodel AT mitulkumarahirwal endtoendbraincomputerinterfacesystemformentalworkloadestimationthroughhybriddeeplearningmodel |