A novel channel selection method for optimal classification in different motor imagery BCI paradigms

Abstract

BackgroundFor sensorimotor rhythms based brain-computer interface (BCI) systems, classification of different motor imageries (MIs) remains a crucial problem. An important aspect is how many scalp electrodes (channels) should be used in order to reach optimal performance classifying motor imaginations. While the previous researches on channel selection mainly focus on MI tasks paradigms without feedback, the present work aims to investigate the optimal channel selection in MI tasks paradigms with real-time feedback (two-class control and four-class control paradigms).MethodsIn the present study, three datasets respectively recorded from MI tasks experiment, two-class control and four-class control experiments were analyzed offline. Multiple frequency-spatial synthesized features were comprehensively extracted from every channel, and a new enhanced method IterRelCen was proposed to perform channel selection. IterRelCen was constructed based on Relief algorithm, but was enhanced from two aspects: change of target sample selection strategy and adoption of the idea of iterative computation, and thus performed more robust in feature selection. Finally, a multiclass support vector machine was applied as the classifier. The least number of channels that yield the best classification accuracy were considered as the optimal channels. One-way ANOVA was employed to test the significance of performance improvement among using optimal channels, all the channels and three typical MI channels (C3, C4, Cz).ResultsThe results show that the proposed method outperformed other channel selection methods by achieving average classification accuracies of 85.2, 94.1, and 83.2 % for the three datasets, respectively. Moreover, the channel selection results reveal that the average numbers of optimal channels were significantly different among the three MI paradigms.ConclusionsIt is demonstrated that IterRelCen has a strong ability for feature selection. In addition, the results have shown that the numbers of optimal channels in the three different motor imagery BCI paradigms are distinct. From a MI task paradigm, to a two-class control paradigm, and to a four-class control paradigm, the number of required channels for optimizing the classification accuracy increased. These findings may provide useful information to optimize EEG based BCI systems, and further improve the performance of noninvasive BCI.

Subject-specific time-frequency selection for multi-class motor imagery-based BCIs using few Laplacian EEG channels

“…Multi-channel EEG recording reduces the portability of daily use BCI and therefore constitutes a main drawback for end users [21,22]. Thus, many methods have been developed to reduce the number of channels in MI-based BCI by using machine learning techniques to select an optimal channel subset [21][22][23][24][25][26][27]. Due to individual differences between subjects, the estimated optimal subsets of channels usually vary with subjects.…”

Amplitude Modulation Index as Feature in a Brain Computer Interface

“…For the Osman database, our outcomes are compared with the reported results in [39][40][41]. In [39], where a new adaptive time-frequency feature extraction strategy is investigated, for subject 1, classification rates in the range of 74.2 -81.1 % with LDA classifier were achieved.…”

Neurological Classifier Committee Based on Artificial Neural Networks and Support Vector Machine for Single-Trial EEG Signal Decoding

“…Thus, [21] applied the common spatial pattern method, [22] implicated modified regression algorithm, [4] used coefficient of determination for the evaluation of spectral features topographies. The mapping method realized in this work allowed obtaining decoding accuracies for each channel that makes the selection of informative channels numerically validated but requires computational resources.…”