A New Approach for Motor Imagery Classification Based on Sorted Blind Source Separation, Continuous Wavelet Transform, and Convolutional Neural Network
Brain-Computer Interfaces (BCI) are systems that allow the interaction of people and devices on the grounds of brain activity. The noninvasive and most viable way to obtain such information is by using electroencephalography (EEG). However, these signals have a low signal-to-noise ratio, as well as...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-10-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/19/20/4541 |
| _version_ | 1811308156918169600 |
|---|---|
| author | César J. Ortiz-Echeverri Sebastián Salazar-Colores Juvenal Rodríguez-Reséndiz Roberto A. Gómez-Loenzo |
| author_facet | César J. Ortiz-Echeverri Sebastián Salazar-Colores Juvenal Rodríguez-Reséndiz Roberto A. Gómez-Loenzo |
| author_sort | César J. Ortiz-Echeverri |
| collection | DOAJ |
| description | Brain-Computer Interfaces (BCI) are systems that allow the interaction of people and devices on the grounds of brain activity. The noninvasive and most viable way to obtain such information is by using electroencephalography (EEG). However, these signals have a low signal-to-noise ratio, as well as a low spatial resolution. This work proposes a new method built from the combination of a Blind Source Separation (BSS) to obtain estimated independent components, a 2D representation of these component signals using the Continuous Wavelet Transform (CWT), and a classification stage using a Convolutional Neural Network (CNN) approach. A criterion based on the spectral correlation with a Movement Related Independent Component (MRIC) is used to sort the estimated sources by BSS, thus reducing the spatial variance. The experimental results of 94.66% using a k-fold cross validation are competitive with techniques recently reported in the state-of-the-art. |
| first_indexed | 2024-04-13T09:18:08Z |
| format | Article |
| id | doaj.art-b92f1712c5df473da9afa72c36d088d1 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-13T09:18:08Z |
| publishDate | 2019-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-b92f1712c5df473da9afa72c36d088d12022-12-22T02:52:42ZengMDPI AGSensors1424-82202019-10-011920454110.3390/s19204541s19204541A New Approach for Motor Imagery Classification Based on Sorted Blind Source Separation, Continuous Wavelet Transform, and Convolutional Neural NetworkCésar J. Ortiz-Echeverri0Sebastián Salazar-Colores1Juvenal Rodríguez-Reséndiz2Roberto A. Gómez-Loenzo3Facultad de Informática, Universidad Autónoma de Querétaro, C.P. 76230 Querétaro, MexicoFacultad de Informática, Universidad Autónoma de Querétaro, C.P. 76230 Querétaro, MexicoFacultad de Ingniería, Universidad Autónoma de Querétaro, C.P. 76010 Querétaro, MexicoFacultad de Ingniería, Universidad Autónoma de Querétaro, C.P. 76010 Querétaro, MexicoBrain-Computer Interfaces (BCI) are systems that allow the interaction of people and devices on the grounds of brain activity. The noninvasive and most viable way to obtain such information is by using electroencephalography (EEG). However, these signals have a low signal-to-noise ratio, as well as a low spatial resolution. This work proposes a new method built from the combination of a Blind Source Separation (BSS) to obtain estimated independent components, a 2D representation of these component signals using the Continuous Wavelet Transform (CWT), and a classification stage using a Convolutional Neural Network (CNN) approach. A criterion based on the spectral correlation with a Movement Related Independent Component (MRIC) is used to sort the estimated sources by BSS, thus reducing the spatial variance. The experimental results of 94.66% using a k-fold cross validation are competitive with techniques recently reported in the state-of-the-art.https://www.mdpi.com/1424-8220/19/20/4541brain-computer interfaceblind source separationmovement related independent componentwavelet transformconvolutional neural network |
| spellingShingle | César J. Ortiz-Echeverri Sebastián Salazar-Colores Juvenal Rodríguez-Reséndiz Roberto A. Gómez-Loenzo A New Approach for Motor Imagery Classification Based on Sorted Blind Source Separation, Continuous Wavelet Transform, and Convolutional Neural Network Sensors brain-computer interface blind source separation movement related independent component wavelet transform convolutional neural network |
| title | A New Approach for Motor Imagery Classification Based on Sorted Blind Source Separation, Continuous Wavelet Transform, and Convolutional Neural Network |
| title_full | A New Approach for Motor Imagery Classification Based on Sorted Blind Source Separation, Continuous Wavelet Transform, and Convolutional Neural Network |
| title_fullStr | A New Approach for Motor Imagery Classification Based on Sorted Blind Source Separation, Continuous Wavelet Transform, and Convolutional Neural Network |
| title_full_unstemmed | A New Approach for Motor Imagery Classification Based on Sorted Blind Source Separation, Continuous Wavelet Transform, and Convolutional Neural Network |
| title_short | A New Approach for Motor Imagery Classification Based on Sorted Blind Source Separation, Continuous Wavelet Transform, and Convolutional Neural Network |
| title_sort | new approach for motor imagery classification based on sorted blind source separation continuous wavelet transform and convolutional neural network |
| topic | brain-computer interface blind source separation movement related independent component wavelet transform convolutional neural network |
| url | https://www.mdpi.com/1424-8220/19/20/4541 |
| work_keys_str_mv | AT cesarjortizecheverri anewapproachformotorimageryclassificationbasedonsortedblindsourceseparationcontinuouswavelettransformandconvolutionalneuralnetwork AT sebastiansalazarcolores anewapproachformotorimageryclassificationbasedonsortedblindsourceseparationcontinuouswavelettransformandconvolutionalneuralnetwork AT juvenalrodriguezresendiz anewapproachformotorimageryclassificationbasedonsortedblindsourceseparationcontinuouswavelettransformandconvolutionalneuralnetwork AT robertoagomezloenzo anewapproachformotorimageryclassificationbasedonsortedblindsourceseparationcontinuouswavelettransformandconvolutionalneuralnetwork AT cesarjortizecheverri newapproachformotorimageryclassificationbasedonsortedblindsourceseparationcontinuouswavelettransformandconvolutionalneuralnetwork AT sebastiansalazarcolores newapproachformotorimageryclassificationbasedonsortedblindsourceseparationcontinuouswavelettransformandconvolutionalneuralnetwork AT juvenalrodriguezresendiz newapproachformotorimageryclassificationbasedonsortedblindsourceseparationcontinuouswavelettransformandconvolutionalneuralnetwork AT robertoagomezloenzo newapproachformotorimageryclassificationbasedonsortedblindsourceseparationcontinuouswavelettransformandconvolutionalneuralnetwork |