BCI Based Wheelchair Control using Steady State Visual Evoked Potentials and Support Vector Machines
Rajesh Singla1, Haseena B. A.2
1Rajesh Singla is with the Instrumentation and Control Engineering Department, National Institute of Technology, Jalandhar, India.
2Haseena B.A. is with the Instrumentation and Control Engineering Department, National Institute of Technology, Jalandhar, India.
Manuscript received on June 05, 2013. | Revised Manuscript received on June 27, 2013. | Manuscript published on July 05, 2013. | PP: 46-52 | Volume-3 Issue-3, July 2013. | Retrieval Number: C1621073313/2013©BEIESP
Open Access | Ethics and Policies | Cite
© The Authors. Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: This paper presents a Steady State Visual Evoked Potential (SSVEP) based Brain Computer Interface (BCI) system to control a wheelchair in forward, backward, left, right and in stop positions. Four different flickering frequencies in low frequency region were used to elicit the SSVEPs and were displayed on a Liquid Crystal Display (LCD) monitor using LabVIEW. The Electroencephalogram (EEG) signals recorded from the occipital region were first segmented into 1 second window and features were extracted by using Fast Fourier Transform (FFT). Three different classifiers, two based on Artificial Neural Network (ANN) and one based on Support Vector Machine (SVM) were designed and compared to yield better accuracy. Ten subjects were participated in the experiment and the accuracy was calculated by considering the number of correct detections produced while performing a predefined movement sequence. One-Against-All (OAA) based multiclass SVM classifier showed better accuracy than the ANN classifiers.
Keywords: ANN; Brain Computer Interface; Steady State Visual Evoked Potential; Support Vector Machines.