Combining robust level extraction and unsupervised adaptive classification for high-accuracy fNIRS-BCI: An evidence on single-trial differentiation between mentally arithmetic- and singing-tasks
Functional near-infrared spectroscopy (fNIRS) is a safe and non-invasive optical imaging technique that is being increasingly used in brain-computer interfaces (BCIs) to recognize mental tasks. Unlike electroencephalography (EEG) which directly measures neural activation, fNIRS signals reflect neuro...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-10-01
|
| Series: | Frontiers in Neuroscience |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fnins.2022.938518/full |
| _version_ | 1828726756566106112 |
|---|---|
| author | Yao Zhang Dongyuan Liu Pengrui Zhang Tieni Li Zhiyong Li Feng Gao Feng Gao |
| author_facet | Yao Zhang Dongyuan Liu Pengrui Zhang Tieni Li Zhiyong Li Feng Gao Feng Gao |
| author_sort | Yao Zhang |
| collection | DOAJ |
| description | Functional near-infrared spectroscopy (fNIRS) is a safe and non-invasive optical imaging technique that is being increasingly used in brain-computer interfaces (BCIs) to recognize mental tasks. Unlike electroencephalography (EEG) which directly measures neural activation, fNIRS signals reflect neurovascular-coupling inducing hemodynamic response that can be slow in time and varying in the pattern. The established classifiers extend the EEG-ones by mostly employing the feature based supervised models such as the support vector machine (SVM) and linear discriminant analysis (LDA), and fail to timely characterize the level-sensitive hemodynamic pattern. A dedicated classifier is desired for intentional activity recognition of fNIRS-BCI, including the adaptive acquisition of response relevant features and accurate discrimination of implied ideas. To this end, we herein propose a specifically-designed joint adaptive classification method that combines a Kalman filtering (KF) for robust level extraction and an adaptive Gaussian mixture model (a-GMM) for enhanced pattern recognition. The simulative investigations and paradigm experiments have shown that the proposed KF/a-GMM classification method can effectively track the random variations of task-evoked brain activation patterns, and improve the accuracy of single-trial classification task of mental arithmetic vs. mental singing, as compared to the conventional methods, e.g., those that employ combinations of the band-pass filtering (BPF) based feature extractors (mean, slope, and variance, etc.) and the classical recognizers (GMM, SVM, and LDA). The proposed approach paves a promising way for developing the real-time fNIRS-BCI technique. |
| first_indexed | 2024-04-12T13:47:51Z |
| format | Article |
| id | doaj.art-d9b7d10c6983453fbfc3c6c550f0b6e7 |
| institution | Directory Open Access Journal |
| issn | 1662-453X |
| language | English |
| last_indexed | 2024-04-12T13:47:51Z |
| publishDate | 2022-10-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neuroscience |
| spelling | doaj.art-d9b7d10c6983453fbfc3c6c550f0b6e72022-12-22T03:30:38ZengFrontiers Media S.A.Frontiers in Neuroscience1662-453X2022-10-011610.3389/fnins.2022.938518938518Combining robust level extraction and unsupervised adaptive classification for high-accuracy fNIRS-BCI: An evidence on single-trial differentiation between mentally arithmetic- and singing-tasksYao Zhang0Dongyuan Liu1Pengrui Zhang2Tieni Li3Zhiyong Li4Feng Gao5Feng Gao6College of Precision Instrument and Optoelectronics Engineering, Tianjin University, Tianjin, ChinaCollege of Precision Instrument and Optoelectronics Engineering, Tianjin University, Tianjin, ChinaCollege of Precision Instrument and Optoelectronics Engineering, Tianjin University, Tianjin, ChinaCollege of Precision Instrument and Optoelectronics Engineering, Tianjin University, Tianjin, ChinaCollege of Precision Instrument and Optoelectronics Engineering, Tianjin University, Tianjin, ChinaCollege of Precision Instrument and Optoelectronics Engineering, Tianjin University, Tianjin, ChinaTianjin Key Laboratory of Biomedical Detecting Techniques and Instruments, Tianjin University, Tianjin, ChinaFunctional near-infrared spectroscopy (fNIRS) is a safe and non-invasive optical imaging technique that is being increasingly used in brain-computer interfaces (BCIs) to recognize mental tasks. Unlike electroencephalography (EEG) which directly measures neural activation, fNIRS signals reflect neurovascular-coupling inducing hemodynamic response that can be slow in time and varying in the pattern. The established classifiers extend the EEG-ones by mostly employing the feature based supervised models such as the support vector machine (SVM) and linear discriminant analysis (LDA), and fail to timely characterize the level-sensitive hemodynamic pattern. A dedicated classifier is desired for intentional activity recognition of fNIRS-BCI, including the adaptive acquisition of response relevant features and accurate discrimination of implied ideas. To this end, we herein propose a specifically-designed joint adaptive classification method that combines a Kalman filtering (KF) for robust level extraction and an adaptive Gaussian mixture model (a-GMM) for enhanced pattern recognition. The simulative investigations and paradigm experiments have shown that the proposed KF/a-GMM classification method can effectively track the random variations of task-evoked brain activation patterns, and improve the accuracy of single-trial classification task of mental arithmetic vs. mental singing, as compared to the conventional methods, e.g., those that employ combinations of the band-pass filtering (BPF) based feature extractors (mean, slope, and variance, etc.) and the classical recognizers (GMM, SVM, and LDA). The proposed approach paves a promising way for developing the real-time fNIRS-BCI technique.https://www.frontiersin.org/articles/10.3389/fnins.2022.938518/fullactivation leveladaptive Gaussian mixture modelbrain-computer interfaceclassification accuracyfNIRSfeature extraction |
| spellingShingle | Yao Zhang Dongyuan Liu Pengrui Zhang Tieni Li Zhiyong Li Feng Gao Feng Gao Combining robust level extraction and unsupervised adaptive classification for high-accuracy fNIRS-BCI: An evidence on single-trial differentiation between mentally arithmetic- and singing-tasks Frontiers in Neuroscience activation level adaptive Gaussian mixture model brain-computer interface classification accuracy fNIRS feature extraction |
| title | Combining robust level extraction and unsupervised adaptive classification for high-accuracy fNIRS-BCI: An evidence on single-trial differentiation between mentally arithmetic- and singing-tasks |
| title_full | Combining robust level extraction and unsupervised adaptive classification for high-accuracy fNIRS-BCI: An evidence on single-trial differentiation between mentally arithmetic- and singing-tasks |
| title_fullStr | Combining robust level extraction and unsupervised adaptive classification for high-accuracy fNIRS-BCI: An evidence on single-trial differentiation between mentally arithmetic- and singing-tasks |
| title_full_unstemmed | Combining robust level extraction and unsupervised adaptive classification for high-accuracy fNIRS-BCI: An evidence on single-trial differentiation between mentally arithmetic- and singing-tasks |
| title_short | Combining robust level extraction and unsupervised adaptive classification for high-accuracy fNIRS-BCI: An evidence on single-trial differentiation between mentally arithmetic- and singing-tasks |
| title_sort | combining robust level extraction and unsupervised adaptive classification for high accuracy fnirs bci an evidence on single trial differentiation between mentally arithmetic and singing tasks |
| topic | activation level adaptive Gaussian mixture model brain-computer interface classification accuracy fNIRS feature extraction |
| url | https://www.frontiersin.org/articles/10.3389/fnins.2022.938518/full |
| work_keys_str_mv | AT yaozhang combiningrobustlevelextractionandunsupervisedadaptiveclassificationforhighaccuracyfnirsbcianevidenceonsingletrialdifferentiationbetweenmentallyarithmeticandsingingtasks AT dongyuanliu combiningrobustlevelextractionandunsupervisedadaptiveclassificationforhighaccuracyfnirsbcianevidenceonsingletrialdifferentiationbetweenmentallyarithmeticandsingingtasks AT pengruizhang combiningrobustlevelextractionandunsupervisedadaptiveclassificationforhighaccuracyfnirsbcianevidenceonsingletrialdifferentiationbetweenmentallyarithmeticandsingingtasks AT tienili combiningrobustlevelextractionandunsupervisedadaptiveclassificationforhighaccuracyfnirsbcianevidenceonsingletrialdifferentiationbetweenmentallyarithmeticandsingingtasks AT zhiyongli combiningrobustlevelextractionandunsupervisedadaptiveclassificationforhighaccuracyfnirsbcianevidenceonsingletrialdifferentiationbetweenmentallyarithmeticandsingingtasks AT fenggao combiningrobustlevelextractionandunsupervisedadaptiveclassificationforhighaccuracyfnirsbcianevidenceonsingletrialdifferentiationbetweenmentallyarithmeticandsingingtasks AT fenggao combiningrobustlevelextractionandunsupervisedadaptiveclassificationforhighaccuracyfnirsbcianevidenceonsingletrialdifferentiationbetweenmentallyarithmeticandsingingtasks |