A hybrid CNN model for classification of motor tasks obtained from hybrid BCI system
Abstract The Hybrid-Brain Computer Interface (BCI) has shown improved performance, especially in classifying multi-class data. Two non-invasive BCI modules are combined to achieve an improved classification which are Electroencephalogram (EEG) and functional Near Infra-red Spectroscopy (fNIRS). Clas...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-024-84883-2 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841544594817286144 |
|---|---|
| author | R. Shelishiyah Deepa Beeta Thiyam M. Jehosheba Margaret N. M. Masoodhu Banu |
| author_facet | R. Shelishiyah Deepa Beeta Thiyam M. Jehosheba Margaret N. M. Masoodhu Banu |
| author_sort | R. Shelishiyah |
| collection | DOAJ |
| description | Abstract The Hybrid-Brain Computer Interface (BCI) has shown improved performance, especially in classifying multi-class data. Two non-invasive BCI modules are combined to achieve an improved classification which are Electroencephalogram (EEG) and functional Near Infra-red Spectroscopy (fNIRS). Classifying contralateral and ipsilateral motor movements is found challenging among the other mental activity signals. The current work focuses on the performance of deep learning methods like – Convolutional Neural Networks (CNN) and Bidirectional Long-Short term memory (Bi-LSTM) in classifying a four-class motor execution of Right Hand, Left Hand, Right Arm and Left Arm taken from the CORE dataset. The model performance was evaluated using metrics such as Accuracy, F1 – score, Precision, Recall, AUC and ROC curve. The CNN and Hybrid CNN models have resulted in 98.3% and 99% accuracy respectively. |
| format | Article |
| id | doaj-art-77a427d13ae146a8b27f6cfeb54f8a60 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-77a427d13ae146a8b27f6cfeb54f8a602025-01-12T12:24:06ZengNature PortfolioScientific Reports2045-23222025-01-0115111010.1038/s41598-024-84883-2A hybrid CNN model for classification of motor tasks obtained from hybrid BCI systemR. Shelishiyah0Deepa Beeta Thiyam1M. Jehosheba Margaret2N. M. Masoodhu Banu3Vel Tech Rangarajan Dr Sagunthala R & D Institute of Science and TechnologyVel Tech Rangarajan Dr Sagunthala R & D Institute of Science and TechnologyVel Tech Rangarajan Dr Sagunthala R & D Institute of Science and TechnologyVel Tech Rangarajan Dr Sagunthala R & D Institute of Science and TechnologyAbstract The Hybrid-Brain Computer Interface (BCI) has shown improved performance, especially in classifying multi-class data. Two non-invasive BCI modules are combined to achieve an improved classification which are Electroencephalogram (EEG) and functional Near Infra-red Spectroscopy (fNIRS). Classifying contralateral and ipsilateral motor movements is found challenging among the other mental activity signals. The current work focuses on the performance of deep learning methods like – Convolutional Neural Networks (CNN) and Bidirectional Long-Short term memory (Bi-LSTM) in classifying a four-class motor execution of Right Hand, Left Hand, Right Arm and Left Arm taken from the CORE dataset. The model performance was evaluated using metrics such as Accuracy, F1 – score, Precision, Recall, AUC and ROC curve. The CNN and Hybrid CNN models have resulted in 98.3% and 99% accuracy respectively.https://doi.org/10.1038/s41598-024-84883-2EEGFNIRSHybrid BCICNNBi-LSTM |
| spellingShingle | R. Shelishiyah Deepa Beeta Thiyam M. Jehosheba Margaret N. M. Masoodhu Banu A hybrid CNN model for classification of motor tasks obtained from hybrid BCI system Scientific Reports EEG FNIRS Hybrid BCI CNN Bi-LSTM |
| title | A hybrid CNN model for classification of motor tasks obtained from hybrid BCI system |
| title_full | A hybrid CNN model for classification of motor tasks obtained from hybrid BCI system |
| title_fullStr | A hybrid CNN model for classification of motor tasks obtained from hybrid BCI system |
| title_full_unstemmed | A hybrid CNN model for classification of motor tasks obtained from hybrid BCI system |
| title_short | A hybrid CNN model for classification of motor tasks obtained from hybrid BCI system |
| title_sort | hybrid cnn model for classification of motor tasks obtained from hybrid bci system |
| topic | EEG FNIRS Hybrid BCI CNN Bi-LSTM |
| url | https://doi.org/10.1038/s41598-024-84883-2 |
| work_keys_str_mv | AT rshelishiyah ahybridcnnmodelforclassificationofmotortasksobtainedfromhybridbcisystem AT deepabeetathiyam ahybridcnnmodelforclassificationofmotortasksobtainedfromhybridbcisystem AT mjehoshebamargaret ahybridcnnmodelforclassificationofmotortasksobtainedfromhybridbcisystem AT nmmasoodhubanu ahybridcnnmodelforclassificationofmotortasksobtainedfromhybridbcisystem AT rshelishiyah hybridcnnmodelforclassificationofmotortasksobtainedfromhybridbcisystem AT deepabeetathiyam hybridcnnmodelforclassificationofmotortasksobtainedfromhybridbcisystem AT mjehoshebamargaret hybridcnnmodelforclassificationofmotortasksobtainedfromhybridbcisystem AT nmmasoodhubanu hybridcnnmodelforclassificationofmotortasksobtainedfromhybridbcisystem |