NIRS-based classification of clench force and speed motor imagery with the use of empirical mode decomposition for BCI. Issue 3 (March 2015)

• Record Type: Journal Article
• Authors: Yin, Xuxian; Xu, Baolei; Jiang, Changhao; Fu, Yunfa; Wang, Zhidong; Li, Hongyi; Shi, Gang
• Is Part Of: Medical engineering & physics. Volume 37:Issue 3(2015:Mar.)
• Page Start: 280
• Page End: 286
• Publication Date: 2015-03
• Subjects: Brain–computer interface (BCI) -- Near-infrared spectroscopy (NIRS) -- Empirical mode decomposition (EMD) -- Joint mutual information (JMI); Biomedical engineering -- Periodicals; Biomedical Engineering -- Periodicals; Physics -- Periodicals; Génie biomédical -- Périodiques; Biomedical engineering; Electronic journals; Periodicals; 610.28
• DOI: 10.1016/j.medengphy.2015.01.005
• Languages: English
• ISSNs: 1350-4533

Abstract

Abstract: Near-infrared spectroscopy (NIRS) is a non-invasive optical technique used for brain–computer interface (BCI). This study aims to investigate the brain hemodynamic responses of clench force and speed motor imagery and extract task-relevant features to obtain better classification performance. Given the non-stationary characteristics of real hemodynamic measurements, empirical mode decomposition (EMD) was applied to reduce the physiological noise overwhelmed in the task-relevant NIRS signals. Compared with continuous wavelet decomposition, EMD does not require a pre-determined basis function. EMD decomposes the original signals into a set of intrinsic mode functions (IMFs). In this study, joint mutual information was applied to select the optimal features, and support vector machine was used as a classifier. Offline and pseudo-online analyses showed that the most feasible classification accuracy can be obtained using IMFs as input features. Accordingly, an alternative feature is provided to develop the NIRS–BCI system. Highlights: We classified NIRS-based clench force and speed motor imagery for BCI. EMD algorithm is employed to reduce physiological noise. JMI is used to select the optimal features for classification. Using IMFs as input features can obtain the most feasible accuracy.