Small-Dimension Feature Matrix Construction Method for Decoding Repetitive Finger Movements From Electroencephalogram Signals
Brain computer interface (BCI) has been widely studied to allow people to control external devices as an extension of capabilities or a replacement of lost functions. The decoding algorithm of brain signals is a crucial part in BCI, since its performance determines the efficiency of the interface. D...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9043565/ |
| _version_ | 1818933047177773056 |
|---|---|
| author | Tianyu Jia Ke Liu Yijia Lu Yali Liu Chong Li Linhong Ji Chao Qian |
| author_facet | Tianyu Jia Ke Liu Yijia Lu Yali Liu Chong Li Linhong Ji Chao Qian |
| author_sort | Tianyu Jia |
| collection | DOAJ |
| description | Brain computer interface (BCI) has been widely studied to allow people to control external devices as an extension of capabilities or a replacement of lost functions. The decoding algorithm of brain signals is a crucial part in BCI, since its performance determines the efficiency of the interface. Decoding performance can be improved by generating optimal feature matrix. The objective of this paper is to propose and implement a decoding algorithm with optimized small dimension feature matrix on identifying motor intention of finger movement using electroencephalogram (EEG) signals. An experiment was designed and conducted, in which EEG was acquired from 10 healthy subjects during the left or the right index finger movement. Event-related desynchronization (ERD) topography was analyzed during motor tasks. A degree feature extraction algorithm was proposed based on the graph theory together with Support Vector Machine (SVM) to classify two kinds of index finger movement, which takes three factors into consideration: frequency bands, amplitude and range of ERD. The results showed that the algorithm can classify the finger movement effectively for 7 subjects based on a three-dimension optimized feature matrix, consisting of the maximum degree, average degree and clustering range. The proposed algorithm is not limited by the size of samples and can indicate the source area of the neural activities. Results also demonstrate that the proposed degree feature extraction algorithm can smooth signal noise and enlarge the feature differences between the contralateral and the ipsilateral hemispheres. |
| first_indexed | 2024-12-20T04:42:10Z |
| format | Article |
| id | doaj.art-f464a86dc12f480287fe80cdc3007840 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-20T04:42:10Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-f464a86dc12f480287fe80cdc30078402022-12-21T19:53:05ZengIEEEIEEE Access2169-35362020-01-018560605607110.1109/ACCESS.2020.29822109043565Small-Dimension Feature Matrix Construction Method for Decoding Repetitive Finger Movements From Electroencephalogram SignalsTianyu Jia0https://orcid.org/0000-0001-6645-509XKe Liu1Yijia Lu2Yali Liu3Chong Li4Linhong Ji5https://orcid.org/0000-0003-4533-4285Chao Qian6Division of Intelligent and Bio-mimetic Machinery, The State Key Laboratory of Tribology, Tsinghua University, Beijing, ChinaDepartment of Mathematical Sciences, Tsinghua University, Beijing, ChinaDivision of Intelligent and Bio-mimetic Machinery, The State Key Laboratory of Tribology, Tsinghua University, Beijing, ChinaDepartment of Mechanical and Electrical Engineering, Beijing Institute of Technology, Beijing, ChinaDivision of Intelligent and Bio-mimetic Machinery, The State Key Laboratory of Tribology, Tsinghua University, Beijing, ChinaDivision of Intelligent and Bio-mimetic Machinery, The State Key Laboratory of Tribology, Tsinghua University, Beijing, ChinaDivision of Intelligent and Bio-mimetic Machinery, The State Key Laboratory of Tribology, Tsinghua University, Beijing, ChinaBrain computer interface (BCI) has been widely studied to allow people to control external devices as an extension of capabilities or a replacement of lost functions. The decoding algorithm of brain signals is a crucial part in BCI, since its performance determines the efficiency of the interface. Decoding performance can be improved by generating optimal feature matrix. The objective of this paper is to propose and implement a decoding algorithm with optimized small dimension feature matrix on identifying motor intention of finger movement using electroencephalogram (EEG) signals. An experiment was designed and conducted, in which EEG was acquired from 10 healthy subjects during the left or the right index finger movement. Event-related desynchronization (ERD) topography was analyzed during motor tasks. A degree feature extraction algorithm was proposed based on the graph theory together with Support Vector Machine (SVM) to classify two kinds of index finger movement, which takes three factors into consideration: frequency bands, amplitude and range of ERD. The results showed that the algorithm can classify the finger movement effectively for 7 subjects based on a three-dimension optimized feature matrix, consisting of the maximum degree, average degree and clustering range. The proposed algorithm is not limited by the size of samples and can indicate the source area of the neural activities. Results also demonstrate that the proposed degree feature extraction algorithm can smooth signal noise and enlarge the feature differences between the contralateral and the ipsilateral hemispheres.https://ieeexplore.ieee.org/document/9043565/Brain computer interfacesevent-related desynchronization topographyfeature extractionfinger movementgraph theory |
| spellingShingle | Tianyu Jia Ke Liu Yijia Lu Yali Liu Chong Li Linhong Ji Chao Qian Small-Dimension Feature Matrix Construction Method for Decoding Repetitive Finger Movements From Electroencephalogram Signals IEEE Access Brain computer interfaces event-related desynchronization topography feature extraction finger movement graph theory |
| title | Small-Dimension Feature Matrix Construction Method for Decoding Repetitive Finger Movements From Electroencephalogram Signals |
| title_full | Small-Dimension Feature Matrix Construction Method for Decoding Repetitive Finger Movements From Electroencephalogram Signals |
| title_fullStr | Small-Dimension Feature Matrix Construction Method for Decoding Repetitive Finger Movements From Electroencephalogram Signals |
| title_full_unstemmed | Small-Dimension Feature Matrix Construction Method for Decoding Repetitive Finger Movements From Electroencephalogram Signals |
| title_short | Small-Dimension Feature Matrix Construction Method for Decoding Repetitive Finger Movements From Electroencephalogram Signals |
| title_sort | small dimension feature matrix construction method for decoding repetitive finger movements from electroencephalogram signals |
| topic | Brain computer interfaces event-related desynchronization topography feature extraction finger movement graph theory |
| url | https://ieeexplore.ieee.org/document/9043565/ |
| work_keys_str_mv | AT tianyujia smalldimensionfeaturematrixconstructionmethodfordecodingrepetitivefingermovementsfromelectroencephalogramsignals AT keliu smalldimensionfeaturematrixconstructionmethodfordecodingrepetitivefingermovementsfromelectroencephalogramsignals AT yijialu smalldimensionfeaturematrixconstructionmethodfordecodingrepetitivefingermovementsfromelectroencephalogramsignals AT yaliliu smalldimensionfeaturematrixconstructionmethodfordecodingrepetitivefingermovementsfromelectroencephalogramsignals AT chongli smalldimensionfeaturematrixconstructionmethodfordecodingrepetitivefingermovementsfromelectroencephalogramsignals AT linhongji smalldimensionfeaturematrixconstructionmethodfordecodingrepetitivefingermovementsfromelectroencephalogramsignals AT chaoqian smalldimensionfeaturematrixconstructionmethodfordecodingrepetitivefingermovementsfromelectroencephalogramsignals |