Multiple Kernel Stein Spatial Patterns for the Multiclass Discrimination of Motor Imagery Tasks
| Autor: | Álvaro Orozco-Gutiérrez, David Cárdenas-Peña, Steven Galindo-Noreña |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Computer science
02 engineering and technology Electroencephalography lcsh:Technology Matrix decomposition lcsh:Chemistry 03 medical and health sciences Kernel (linear algebra) motor imagery 0302 clinical medicine Motor imagery 0202 electrical engineering electronic engineering information engineering medicine General Materials Science multiple kernel learning lcsh:QH301-705.5 Instrumentation Brain–computer interface Interpretability Fluid Flow and Transfer Processes Multiple kernel learning medicine.diagnostic_test lcsh:T business.industry Process Chemistry and Technology brain–computer interface General Engineering Pattern recognition Covariance lcsh:QC1-999 Computer Science Applications lcsh:Biology (General) lcsh:QD1-999 lcsh:TA1-2040 020201 artificial intelligence & image processing Artificial intelligence lcsh:Engineering (General). Civil engineering (General) business electroencephalography lcsh:Physics 030217 neurology & neurosurgery |
| Zdroj: | Applied Sciences, Vol 10, Iss 8628, p 8628 (2020) Applied Sciences Volume 10 Issue 23 |
| ISSN: | 2076-3417 |
| DOI: | 10.3390/app10238628 |
| Popis: | Brain&ndash computer interface (BCI) systems communicate the human brain and computers by converting electrical activity into commands to use external devices. Such kind of system has become an alternative for interaction with the environment for people suffering from motor disabilities through the motor imagery (MI) paradigm. Despite being the most widespread, electroencephalography (EEG)-based MI systems are highly sensitive to noise and artifacts. Further, spatially close brain activity sources and variability among subjects hampers the system performance. This work proposes a methodology for the classification of EEG signals, termed Multiple Kernel Stein Spatial Patterns (MKSSP) dealing with noise, raveled brain activity, and subject variability issues. Firstly, a bank of bandpass filters decomposes brain activity into spectrally independent multichannel signals. Then, Multi-Kernel Stein Spatial Patterns (MKSSP) maps each signal into low-dimensional covariance matrices preserving the nonlinear channel relationships. The Stein kernel provides a parameterized similarity metric for covariance matrices that belong to a Riemannian manifold. Lastly, the multiple kernel learning assembles the similarities from each spectral decomposition into a single kernel matrix that feeds the classifier. Experimental evaluations in the well-known four-class MI dataset 2a BCI competition IV proves that the methodology significantly improves state-of-the-art approaches. Further, the proposal is interpretable in terms of data distribution, spectral relevance, and spatial patterns. Such interpretability demonstrates that MKSSP encodes features from different spectral bands into a single representation improving the discrimination of mental tasks. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|