Classification of Electroencephalogram Data from Hand Grasp and Release Movements for BCI Controlled Prosthesis. (2016)

• Record Type: Journal Article
• Authors: Lange, Gerrit; Low, Cheng Yee; Johar, Khairunnisa; Hanapiah, Fazah Akthar; Kamaruzaman, Fadhlan
• Is Part Of: Procedia technology. Volume 26(2016)
• Page Start: 374
• Page End: 381
• Publication Date: 2016
• Subjects: BCI -- EEG -- EMG -- prosthetics control -- mechatronic development; Technology -- Congresses; Technology -- Periodicals; Engineering -- Congresses; Engineering -- Periodicals; Engineering; Technology; Conference proceedings; Periodicals; 605
• DOI: 10.1016/j.protcy.2016.08.048
• Languages: English
• ISSNs: 2212-0173

Abstract

Abstract: The use of body-powered prostheses can be tiring and lead to further problems with compliance and prosthetic restoration. Brain-Computer-Interfaces (BCI) offers a mean of controlling prostheses for patients that otherwise are unable to operate such devices due to physical limitations. An issue with BCIs is that they tend to either require invasive recording methods, posing a surgical risk, or work by generating control signals from not task related brain activity patterns such as right vs. left hand, hand vs. leg or visual stimulation and therefore are not intuitive in their control. This research aims to test the possibility of controlling the grasp and release of an upper limb prosthetic terminal device by classifying Electroencephalogram (EEG) data from real hand grasping and releasing movement. Data from five healthy subjects were recorded using a consumer grade non-invasive Emotiv EPOC headset. During the measurement the subjects were asked to perform isometric finger extension and flexion of their right hand. In order to bring the EEG data into correlation with the executed movement a simultaneous electromyogram (EMG) recording is proposed as an alternative method to recordings of visual cued movement. Classified EMG data was used to generate markers in the EEG data and to epoch the data. In order to increase the signal to noise ratio and allow better classification, the EEG data was filtered and spectrally weighted common spatial patterns (spec-CSP) were used for feature extraction. Using linear discriminant analysis a classification rate of up to 73.2% between grasp and release was achieved. In this work, a novel EMG-assisted approach has been developed for classification of EEG data from hand grasp and release movements. It shows feasibility for a more intuitive control of upper limb prosthetic terminal device using low-cost BCI without the risk associated with invasive measurement.