Learning temporal information for brain-computer interface using convolutional neural networks
Deep learning (DL) methods and architectures have been the state-of-the-art classification algorithms for computer vision and natural language processing problems. However, the successful application of these methods in motor imagery (MI) brain-computer interfaces (BCIs), in order to boost classific...
Saved in:
Main Authors: | , , |
---|---|
Other Authors: | |
Format: | Article |
Language: | English |
Published: |
2018
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/87699 http://hdl.handle.net/10220/45497 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-87699 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-876992020-03-07T11:48:58Z Learning temporal information for brain-computer interface using convolutional neural networks Sakhavi, Siavash Guan, Cuntai Yan, Shuicheng School of Computer Science and Engineering Brain-computer Interface (BCI) Convolutional Neural Network (CNN) Deep learning (DL) methods and architectures have been the state-of-the-art classification algorithms for computer vision and natural language processing problems. However, the successful application of these methods in motor imagery (MI) brain-computer interfaces (BCIs), in order to boost classification performance, is still limited. In this paper, we propose a classification framework for MI data by introducing a new temporal representation of the data and also utilizing a convolutional neural network (CNN) architecture for classification. The new representation is generated from modifying the filter-bank common spatial patterns method, and the CNN is designed and optimized accordingly for the representation. Our framework outperforms the best classification method in the literature on the BCI competition IV-2a 4-class MI data set by 7% increase in average subject accuracy. Furthermore, by studying the convolutional weights of the trained networks, we gain an insight into the temporal characteristics of EEG. ASTAR (Agency for Sci., Tech. and Research, S’pore) Accepted version 2018-08-07T01:42:23Z 2019-12-06T16:47:30Z 2018-08-07T01:42:23Z 2019-12-06T16:47:30Z 2018 Journal Article Sakhavi, S., Guan, C., & Yan, S. Learning Temporal Information for Brain-Computer Interface Using Convolutional Neural Networks. IEEE Transactions on Neural Networks and Learning Systems, in press. 2162-237X https://hdl.handle.net/10356/87699 http://hdl.handle.net/10220/45497 10.1109/TNNLS.2018.2789927 en IEEE Transactions on Neural Networks and Learning Systems © 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at: [http://dx.doi.org/10.1109/TNNLS.2018.2789927]. 12 p. application/pdf |
institution |
Nanyang Technological University |
building |
NTU Library |
country |
Singapore |
collection |
DR-NTU |
language |
English |
topic |
Brain-computer Interface (BCI) Convolutional Neural Network (CNN) |
spellingShingle |
Brain-computer Interface (BCI) Convolutional Neural Network (CNN) Sakhavi, Siavash Guan, Cuntai Yan, Shuicheng Learning temporal information for brain-computer interface using convolutional neural networks |
description |
Deep learning (DL) methods and architectures have been the state-of-the-art classification algorithms for computer vision and natural language processing problems. However, the successful application of these methods in motor imagery (MI) brain-computer interfaces (BCIs), in order to boost classification performance, is still limited. In this paper, we propose a classification framework for MI data by introducing a new temporal representation of the data and also utilizing a convolutional neural network (CNN) architecture for classification. The new representation is generated from modifying the filter-bank common spatial patterns method, and the CNN is designed and optimized accordingly for the representation. Our framework outperforms the best classification method in the literature on the BCI competition IV-2a 4-class MI data set by 7% increase in average subject accuracy. Furthermore, by studying the convolutional weights of the trained networks, we gain an insight into the temporal characteristics of EEG. |
author2 |
School of Computer Science and Engineering |
author_facet |
School of Computer Science and Engineering Sakhavi, Siavash Guan, Cuntai Yan, Shuicheng |
format |
Article |
author |
Sakhavi, Siavash Guan, Cuntai Yan, Shuicheng |
author_sort |
Sakhavi, Siavash |
title |
Learning temporal information for brain-computer interface using convolutional neural networks |
title_short |
Learning temporal information for brain-computer interface using convolutional neural networks |
title_full |
Learning temporal information for brain-computer interface using convolutional neural networks |
title_fullStr |
Learning temporal information for brain-computer interface using convolutional neural networks |
title_full_unstemmed |
Learning temporal information for brain-computer interface using convolutional neural networks |
title_sort |
learning temporal information for brain-computer interface using convolutional neural networks |
publishDate |
2018 |
url |
https://hdl.handle.net/10356/87699 http://hdl.handle.net/10220/45497 |
_version_ |
1681044325785403392 |