Subject adaptation with deep convolutional neural network for EEG-based motor imagery classification
Deep learning has emerged as a powerful tool for developing Brain-Computer Interface (BCI) systems. However, the scarcity of subject-specific data results in a marginal performance increase for deep learning models trained entirely on the data from a specific individual. To overcome this, many trans...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
Nanyang Technological University
2020
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/138000 |
| _version_ | 1811685147963031552 |
|---|---|
| author | Zhang, Kaishuo |
| author2 | Guan Cuntai |
| author_facet | Guan Cuntai Zhang, Kaishuo |
| author_sort | Zhang, Kaishuo |
| collection | NTU |
| description | Deep learning has emerged as a powerful tool for developing Brain-Computer Interface (BCI) systems. However, the scarcity of subject-specific data results in a marginal performance increase for deep learning models trained entirely on the data from a specific individual. To overcome this, many transfer-based approaches have been proposed, using preexisting data from other subjects. But transfer learning faces its challenges: there are substantial inter-subject variabilities in electroencephalography (EEG) data. Therefore, adaptation is needed to fine-tune the model for the target subject. In this paper, we study 5 schemes for adapting a deep convolutional neural network (CNN) based EEG-BCI system for decoding hand motor imagery (MI). The proposed adaptation scheme improved the average accuracy of the base model by 1.93% (p<0.02). The adaptation resulted in an utmost of 35.18% increase in accuracy for a single subject, compared to a pre-trained base model. |
| first_indexed | 2024-10-01T04:39:55Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/138000 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T04:39:55Z |
| publishDate | 2020 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1380002020-04-21T09:24:12Z Subject adaptation with deep convolutional neural network for EEG-based motor imagery classification Zhang, Kaishuo Guan Cuntai School of Computer Science and Engineering ctguan@ntu.edu.sg Engineering::Computer science and engineering::Computing methodologies::Pattern recognition Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence Deep learning has emerged as a powerful tool for developing Brain-Computer Interface (BCI) systems. However, the scarcity of subject-specific data results in a marginal performance increase for deep learning models trained entirely on the data from a specific individual. To overcome this, many transfer-based approaches have been proposed, using preexisting data from other subjects. But transfer learning faces its challenges: there are substantial inter-subject variabilities in electroencephalography (EEG) data. Therefore, adaptation is needed to fine-tune the model for the target subject. In this paper, we study 5 schemes for adapting a deep convolutional neural network (CNN) based EEG-BCI system for decoding hand motor imagery (MI). The proposed adaptation scheme improved the average accuracy of the base model by 1.93% (p<0.02). The adaptation resulted in an utmost of 35.18% increase in accuracy for a single subject, compared to a pre-trained base model. Bachelor of Engineering (Computer Engineering) 2020-04-21T09:24:12Z 2020-04-21T09:24:12Z 2020 Final Year Project (FYP) https://hdl.handle.net/10356/138000 en SCSE19-0038 application/pdf Nanyang Technological University |
| spellingShingle | Engineering::Computer science and engineering::Computing methodologies::Pattern recognition Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence Zhang, Kaishuo Subject adaptation with deep convolutional neural network for EEG-based motor imagery classification |
| title | Subject adaptation with deep convolutional neural network for EEG-based motor imagery classification |
| title_full | Subject adaptation with deep convolutional neural network for EEG-based motor imagery classification |
| title_fullStr | Subject adaptation with deep convolutional neural network for EEG-based motor imagery classification |
| title_full_unstemmed | Subject adaptation with deep convolutional neural network for EEG-based motor imagery classification |
| title_short | Subject adaptation with deep convolutional neural network for EEG-based motor imagery classification |
| title_sort | subject adaptation with deep convolutional neural network for eeg based motor imagery classification |
| topic | Engineering::Computer science and engineering::Computing methodologies::Pattern recognition Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence |
| url | https://hdl.handle.net/10356/138000 |
| work_keys_str_mv | AT zhangkaishuo subjectadaptationwithdeepconvolutionalneuralnetworkforeegbasedmotorimageryclassification |