CSP-TSM: Optimizing the performance of Riemannian tangent space mapping using common spatial pattern for MI-BCI

et al. 2020

Front. Hum. Neurosci.

Common spatial pattern (CSP) method is widely used for spatial filtering and brain pattern extraction from electroencephalogram (EEG) signals in motor imagery (MI)-based brain-computer interfaces (BCIs). The participant-specific time window relative to the visual cue has a significant impact on the effectiveness of the CSP. However, the time window is usually selected experientially or manually. To solve this problem, we propose a novel feature selection approach for MI-based BCIs. Specifically, multiple time segments were obtained by decomposing each EEG sample of the MI task. Furthermore, the features were extracted by CSP from each time segment and were combined to form a new feature vector. Finally, the optimal temporal combination patterns for the new feature vector were selected based on four feature selection algorithms, i.e., mutual information, least absolute shrinkage and selection operator, principal component analysis and stepwise linear discriminant analysis (denoted as MUIN, LASSO, PCA, and SWLDA, respectively), and the classification algorithm was employed to evaluate the average classification accuracy. With three BCI competition datasets, the results of the four proposed algorithms were compared with traditional CSP algorithm in classification accuracy. Experimental results show that compared with traditional algorithm, the proposed methods significantly improve performance. Specifically, the LASSO achieved the highest accuracy (88.58%) among the proposed methods. Importantly, the average classification accuracies using the proposed approaches significantly improved 10.14% (MUIN), 11.40% (LASSO), 6.08% (PCA), and 10.25% (SWLDA) compared to that using CSP. These results indicate that the proposed approach is expected to be practical in MI-based BCIs.

Section: Discussionmentioning

confidence: 99%

Temporal Combination Pattern Optimization Based on Feature Selection Method for Motor Imagery BCIs

Jiang

et al. 2020

Front. Hum. Neurosci.

“…Our previous study has also shown that choosing the optimal time window for each subject can indeed improve the classification accuracy [40]. Although the optimal time windows of each subject's MI are different, it is found that the time between 0-2.5 s after the onset of visual cue can benefit the classification considering adequate sample points for subsequent data processing [41]. In this study, data between 0.5-2.5s (Subject 3 takes 0.5-2.7 s, Subject 5 takes 0.5-2.6 s) after the onset of the visual cue direction were used.…”

Section: A Time Window Selectionmentioning

confidence: 99%

Diverse Feature Blend Based on Filter-Bank Common Spatial Pattern and Brain Functional Connectivity for Multiple Motor Imagery Detection

Tang

et al. 2020

IEEE Access

Motor imagery (MI) based brain-computer interface (BCI) is a research hotspot and has attracted lots of attention. Within this research topic, multiple MI classification is a challenge due to the difficulties caused by time-varying spatial features across different individuals. To deal with this challenge, we tried to fuse brain functional connectivity (BFC) and one-versus-the-rest filter-bank common spatial pattern (OVR-FBCSP) to improve the robustness of classification. The BFC features were extracted by phase locking value (PLV), representing the brain interregional interactions relevant to the MI, whilst the OVR-FBCSP is used to extract the spatial-frequency features related to the MI. These diverse features were then fed into a multi-kernel relevance vector machine (MK-RVM). The dataset with three motor imagery tasks (left hand MI, right hand MI, and feet MI) was used to assess the proposed method. Experimental results not only showed that the cascade structure of diverse feature fusion and MK-RVM achieved satisfactory classification performance (average accuracy: 83.81%, average kappa: 0.76), but also demonstrated that BFC plays a supplementary role in the MI classification. Moreover, the proposed method has a potential to be integrated into multiple MI online detection owing to the advantage of strong timeefficiency of RVM. INDEX TERMS Multiple motor imagery, filter-bank common spatial pattern (FBCSP), phase locking value (PLV), brain functional connectivity (BFC), multi-kernel relevance vector machine (MK-RVM).

“…A fixed time window (0.5-2.5 s with respect to the onset of cues) was usually used in the CSP for feature extraction [44], [45]. This is not very reasonable because the temporal course of brain activity responding to motor imagery is not exact the same and varies from one subject to another.…”

Section: A Time Windows For Spatial Patternsmentioning

confidence: 99%

An Approach of One-vs-Rest Filter Bank Common Spatial Pattern and Spiking Neural Networks for Multiple Motor Imagery Decoding

Tang

et al. 2020

IEEE Access

Motor imagery (MI) is a typical BCI paradigm and has been widely applied into many aspects (e.g. brain-driven wheelchair and motor function rehabilitation training). Although significant achievements have been achieved, multiple motor imagery decoding is still unsatisfactory. To deal with this challenging issue, firstly, a segment of electroencephalogram was extracted and preprocessed. Secondly, we applied a filter bank common spatial pattern (FBCSP) with one-vs-rest (OVR) strategy to extract the spatio-temporal-frequency features of multiple MI. Thirdly, the F-score was employed to optimise and select these features. Finally, the optimized features were fed to the spiking neural networks (SNN) for classification. Evaluation was conducted on two public multiple MI datasets (Dataset IIIa of the BCI competition III and Dataset IIa of the BCI competition IV). Experimental results showed that the average accuracy of the proposed framework reached up to 90.09% (kappa: 0.868) and 81.33% (kappa: 0.751) on the two public datasets, respectively. The achieved performance (accuracy and kappa) was comparable to the best one of the compared methods. This study demonstrated that the proposed method can be used as an alternative approach for multiple MI decoding and it provided a potential solution for online multiple MI detection. INDEX TERMS Electroencephalogram, motor imagery (MI), filter bank common spatial pattern (FBCSP), spiking neural networks (SNN). I. INTRODUCTION Electroencephalography (EEG) signal is usually used in brain-computer interface (BCI) systems due to its high temporal resolution [1]. Motor imagery (MI)-based BCI is one of classical paradigms and has been employed to restore the communication pathway or movement function for disabled, paralyzed, and stroke patients [2], [3]. Patients are able to The associate editor coordinating the review of this manuscript and approving it for publication was Li He .