A New Approach to Separate Haemodynamic Signals for Brain-Computer Interface Using Independent Component Analysis and Least Squares
Brain-computer interface (BCI) is one technology that allows a user to communicate with external devices through detecting brain activity. As a promising noninvasive technique, functional near-infrared spectroscopy (fNIRS) has recently earned increasing attention in BCI studies. However, in practice...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2013-01-01
|
| Series: | Journal of Spectroscopy |
| Online Access: | http://dx.doi.org/10.1155/2013/950302 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850165164096094208 |
|---|---|
| author | Yan Zhang Xin Liu Chunling Yang Kuanquan Wang Jinwei Sun Peter Rolfe |
| author_facet | Yan Zhang Xin Liu Chunling Yang Kuanquan Wang Jinwei Sun Peter Rolfe |
| author_sort | Yan Zhang |
| collection | DOAJ |
| description | Brain-computer interface (BCI) is one technology that allows a user to communicate with external devices through detecting brain activity. As a promising noninvasive technique, functional near-infrared spectroscopy (fNIRS) has recently earned increasing attention in BCI studies. However, in practice fNIRS measurements can suffer from significant physiological interference, for example, arising from cardiac contraction, breathing, and blood pressure fluctuations, thereby severely limiting the utility of the method. Here, we apply the multidistance fNIRS method, with short-distance and long-distance optode pairs, and we propose the combination of independent component analysis (ICA) and least squares (LS) with the fNIRS recordings to reduce the interference. The short-distance fNIRS measurement is treated as the virtual channel and the long-distance fNIRS measurement is treated as the measurement channel. Least squares is used to optimize the reconstruction value for brain activity signal. Monte Carlo simulations of photon propagation through a five-layered slab model of a human adult head were implemented to evaluate our methodology. The results demonstrate that the ICA method can separate the brain signal and interference; the further application of least squares can significantly recover haemodynamic signals contaminated by physiological interference from the fNIRS-evoked brain activity data. |
| format | Article |
| id | doaj-art-ec14159a38ff4142b4fa74da9cbdee34 |
| institution | OA Journals |
| issn | 2314-4920 2314-4939 |
| language | English |
| publishDate | 2013-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Journal of Spectroscopy |
| spelling | doaj-art-ec14159a38ff4142b4fa74da9cbdee342025-08-20T02:21:49ZengWileyJournal of Spectroscopy2314-49202314-49392013-01-01201310.1155/2013/950302950302A New Approach to Separate Haemodynamic Signals for Brain-Computer Interface Using Independent Component Analysis and Least SquaresYan Zhang0Xin Liu1Chunling Yang2Kuanquan Wang3Jinwei Sun4Peter Rolfe5School of Electrical Engineering and Automaton, Harbin Institute of Technology, Harbin 150001, ChinaSchool of Transportation Science and Engineering, Harbin Institute of Technology, Harbin 150090, ChinaSchool of Electrical Engineering and Automaton, Harbin Institute of Technology, Harbin 150001, ChinaSchool of Computer Science and Technology, Harbin Institute of Technology, Harbin 150001, ChinaSchool of Electrical Engineering and Automaton, Harbin Institute of Technology, Harbin 150001, ChinaSchool of Electrical Engineering and Automaton, Harbin Institute of Technology, Harbin 150001, ChinaBrain-computer interface (BCI) is one technology that allows a user to communicate with external devices through detecting brain activity. As a promising noninvasive technique, functional near-infrared spectroscopy (fNIRS) has recently earned increasing attention in BCI studies. However, in practice fNIRS measurements can suffer from significant physiological interference, for example, arising from cardiac contraction, breathing, and blood pressure fluctuations, thereby severely limiting the utility of the method. Here, we apply the multidistance fNIRS method, with short-distance and long-distance optode pairs, and we propose the combination of independent component analysis (ICA) and least squares (LS) with the fNIRS recordings to reduce the interference. The short-distance fNIRS measurement is treated as the virtual channel and the long-distance fNIRS measurement is treated as the measurement channel. Least squares is used to optimize the reconstruction value for brain activity signal. Monte Carlo simulations of photon propagation through a five-layered slab model of a human adult head were implemented to evaluate our methodology. The results demonstrate that the ICA method can separate the brain signal and interference; the further application of least squares can significantly recover haemodynamic signals contaminated by physiological interference from the fNIRS-evoked brain activity data.http://dx.doi.org/10.1155/2013/950302 |
| spellingShingle | Yan Zhang Xin Liu Chunling Yang Kuanquan Wang Jinwei Sun Peter Rolfe A New Approach to Separate Haemodynamic Signals for Brain-Computer Interface Using Independent Component Analysis and Least Squares Journal of Spectroscopy |
| title | A New Approach to Separate Haemodynamic Signals for Brain-Computer Interface Using Independent Component Analysis and Least Squares |
| title_full | A New Approach to Separate Haemodynamic Signals for Brain-Computer Interface Using Independent Component Analysis and Least Squares |
| title_fullStr | A New Approach to Separate Haemodynamic Signals for Brain-Computer Interface Using Independent Component Analysis and Least Squares |
| title_full_unstemmed | A New Approach to Separate Haemodynamic Signals for Brain-Computer Interface Using Independent Component Analysis and Least Squares |
| title_short | A New Approach to Separate Haemodynamic Signals for Brain-Computer Interface Using Independent Component Analysis and Least Squares |
| title_sort | new approach to separate haemodynamic signals for brain computer interface using independent component analysis and least squares |
| url | http://dx.doi.org/10.1155/2013/950302 |
| work_keys_str_mv | AT yanzhang anewapproachtoseparatehaemodynamicsignalsforbraincomputerinterfaceusingindependentcomponentanalysisandleastsquares AT xinliu anewapproachtoseparatehaemodynamicsignalsforbraincomputerinterfaceusingindependentcomponentanalysisandleastsquares AT chunlingyang anewapproachtoseparatehaemodynamicsignalsforbraincomputerinterfaceusingindependentcomponentanalysisandleastsquares AT kuanquanwang anewapproachtoseparatehaemodynamicsignalsforbraincomputerinterfaceusingindependentcomponentanalysisandleastsquares AT jinweisun anewapproachtoseparatehaemodynamicsignalsforbraincomputerinterfaceusingindependentcomponentanalysisandleastsquares AT peterrolfe anewapproachtoseparatehaemodynamicsignalsforbraincomputerinterfaceusingindependentcomponentanalysisandleastsquares AT yanzhang newapproachtoseparatehaemodynamicsignalsforbraincomputerinterfaceusingindependentcomponentanalysisandleastsquares AT xinliu newapproachtoseparatehaemodynamicsignalsforbraincomputerinterfaceusingindependentcomponentanalysisandleastsquares AT chunlingyang newapproachtoseparatehaemodynamicsignalsforbraincomputerinterfaceusingindependentcomponentanalysisandleastsquares AT kuanquanwang newapproachtoseparatehaemodynamicsignalsforbraincomputerinterfaceusingindependentcomponentanalysisandleastsquares AT jinweisun newapproachtoseparatehaemodynamicsignalsforbraincomputerinterfaceusingindependentcomponentanalysisandleastsquares AT peterrolfe newapproachtoseparatehaemodynamicsignalsforbraincomputerinterfaceusingindependentcomponentanalysisandleastsquares |