Explainable AI based neurofeedback in a CNN-BCI for motor imagery classification
The application of machine learning to brain-computer interfaces has recently garnered great interest due to the significant advancements in the areas of neural networks and deep learning. With the use of state-of-the-art convolutional neural networks, it has become possible to achieve accuracies of...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
Nanyang Technological University
2024
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/175251 |
| _version_ | 1826110349073448960 |
|---|---|
| author | Ghosh, Amitrajit |
| author2 | Guan Cuntai |
| author_facet | Guan Cuntai Ghosh, Amitrajit |
| author_sort | Ghosh, Amitrajit |
| collection | NTU |
| description | The application of machine learning to brain-computer interfaces has recently garnered great interest due to the significant advancements in the areas of neural networks and deep learning. With the use of state-of-the-art convolutional neural networks, it has become possible to achieve accuracies of up to 84.19% for subject-independent left/right motor-imagery models using deep convolutional neural networks.
The aim of this project is to interpret the classification of deep convolutional neural networks and study interrelations between classification performance and network encodings with neurophysiological features underlying motor imagery.
To achieve that goal, this project investigated the relationship between saliency maps derived from the output of a deep convolutional neural network and a subject’s event-related synchronization/desynchronization (ERDS) values.
For some electrode channels located on the motor cortex, strong positive correlations were found between ERDS and saliency values measured from those channels. These findings provide insights on the strategies employed by subjects when performing left/right motor imagery tasks. This information can be utilised in the future to further optimise the deep convolutional neural network to improve the performance of left/right motor imagery classification. |
| first_indexed | 2024-10-01T02:32:56Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/175251 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T02:32:56Z |
| publishDate | 2024 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1752512024-04-26T15:41:57Z Explainable AI based neurofeedback in a CNN-BCI for motor imagery classification Ghosh, Amitrajit Guan Cuntai School of Computer Science and Engineering CTGuan@ntu.edu.sg Computer and Information Science Engineering The application of machine learning to brain-computer interfaces has recently garnered great interest due to the significant advancements in the areas of neural networks and deep learning. With the use of state-of-the-art convolutional neural networks, it has become possible to achieve accuracies of up to 84.19% for subject-independent left/right motor-imagery models using deep convolutional neural networks. The aim of this project is to interpret the classification of deep convolutional neural networks and study interrelations between classification performance and network encodings with neurophysiological features underlying motor imagery. To achieve that goal, this project investigated the relationship between saliency maps derived from the output of a deep convolutional neural network and a subject’s event-related synchronization/desynchronization (ERDS) values. For some electrode channels located on the motor cortex, strong positive correlations were found between ERDS and saliency values measured from those channels. These findings provide insights on the strategies employed by subjects when performing left/right motor imagery tasks. This information can be utilised in the future to further optimise the deep convolutional neural network to improve the performance of left/right motor imagery classification. Bachelor's degree 2024-04-23T01:39:37Z 2024-04-23T01:39:37Z 2024 Final Year Project (FYP) Ghosh, A. (2024). Explainable AI based neurofeedback in a CNN-BCI for motor imagery classification. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/175251 https://hdl.handle.net/10356/175251 en application/pdf Nanyang Technological University |
| spellingShingle | Computer and Information Science Engineering Ghosh, Amitrajit Explainable AI based neurofeedback in a CNN-BCI for motor imagery classification |
| title | Explainable AI based neurofeedback in a CNN-BCI for motor imagery classification |
| title_full | Explainable AI based neurofeedback in a CNN-BCI for motor imagery classification |
| title_fullStr | Explainable AI based neurofeedback in a CNN-BCI for motor imagery classification |
| title_full_unstemmed | Explainable AI based neurofeedback in a CNN-BCI for motor imagery classification |
| title_short | Explainable AI based neurofeedback in a CNN-BCI for motor imagery classification |
| title_sort | explainable ai based neurofeedback in a cnn bci for motor imagery classification |
| topic | Computer and Information Science Engineering |
| url | https://hdl.handle.net/10356/175251 |
| work_keys_str_mv | AT ghoshamitrajit explainableaibasedneurofeedbackinacnnbciformotorimageryclassification |