The Performance Evaluation of SSVEP-BCI Actuated Wheelchair with Parameter Setting of Time-Window Length and Stimulation Layout

Due to the advantages of prominent brain responses, less training duration, and robustness to artifacts, steady-state visual evoked potential (SSVEP) based braincomputer interface (BCI) has been recently applied to intelligent wheelchair navigation. Recent researches mainly focused on the implementation of a specific recognition method to analyze the wheelchair navigation performance under fixed stimulation target number. The navigation performance evaluation under different recognition methods and different BCI target numbers is rarely compared. In this paper, the navigation performance comparison between different numbers of stimulation targets and different recognition methods was carried out. The multichannel integrated GT2circ and canonical correlation analysis (CCA) recognition methods were used to compare the wheelchair navigation performance under different time-window (TW) lengths. And the 3-target and 4-target arrangement layouts were adopted to compare the navigation performance between the “No feedback” and the “Feedback” conditions. Experimental results showed that the GT2circ recognition method with TW length of 2 s would promote the navigation efficiency and different stimulation target number could be tailored for different wheelchair application purposes, which would bring tutorial instructions to the applicable navigation of the BCI-actuated wheelchair.

[1]  A. Cichocki,et al.  Steady-state visually evoked potentials: Focus on essential paradigms and future perspectives , 2010, Progress in Neurobiology.

[2]  Gernot R. Müller-Putz,et al.  Self-Paced (Asynchronous) BCI Control of a Wheelchair in Virtual Environments: A Case Study with a Tetraplegic , 2007, Comput. Intell. Neurosci..

[3]  Haihong Zhang,et al.  A Brain-Controlled Wheelchair Based on P300 and Path Guidance , 2006, The First IEEE/RAS-EMBS International Conference on Biomedical Robotics and Biomechatronics, 2006. BioRob 2006..

[4]  Xiaorong Gao,et al.  An online multi-channel SSVEP-based brain–computer interface using a canonical correlation analysis method , 2009, Journal of neural engineering.

[5]  Kazuo Tanaka,et al.  Electroencephalogram-based control of an electric wheelchair , 2005, IEEE Transactions on Robotics.

[6]  Cuntai Guan,et al.  Controlling a wheelchair using a BCI with low information transfer rate , 2007, 2007 IEEE 10th International Conference on Rehabilitation Robotics.

[7]  Jing Wang,et al.  Steady-State Motion Visual Evoked Potentials Produced by Oscillating Newton's Rings: Implications for Brain-Computer Interfaces , 2012, PloS one.

[8]  Gert Pfurtscheller,et al.  Brain-computer interface: a new communication device for handicapped persons , 1993 .

[9]  G Pfurtscheller,et al.  EEG-based communication: improved accuracy by response verification. , 1998, IEEE transactions on rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society.

[10]  José del R. Millán,et al.  Context-Based Filtering for Assisted Brain-Actuated Wheelchair Driving , 2007, Comput. Intell. Neurosci..

[11]  Guanghua Xu,et al.  Recognition of SSMVEP signals based on multi-channel integrated GT2circ statistic method , 2017, 2017 14th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI).

[12]  Wei Wu,et al.  Frequency recognition based on canonical correlation analysis for SSVEP-based BCIs , 2007, IEEE Transactions on Biomedical Engineering.

[13]  C. E. Davila,et al.  A new multi-harmonic statistic for the detection of steady-state evoked potentials , 1997, Proceedings of the 1997 16 Southern Biomedical Engineering Conference.