A P300-Based Threshold-Free Brain Switch and Its Application in Wheelchair Control

• Published in: IEEE transactions on neural systems and rehabilitation engineering 2017-06, Vol.25 (6), p.715-725
• Main Authors: He, Shenghong, Zhang, Rui, Wang, Qihong, Chen, Yang, Yang, Tingyan, Feng, Zhenghui, Zhang, Yuandong, Shao, Ming, Li, Yuanqing
• Format: Article
• Language: English
• Subjects: Adult; Autonomous navigation; Biofeedback, Psychology - instrumentation; Biofeedback, Psychology - methods; Brain; Brain injury; Brain switch; Brain-Computer Interfaces; Classifiers; Diagnosis, Differential; EEG; Electroencephalography; electroencephalography (EEG); Electroencephalography - instrumentation; Electroencephalography - methods; Equipment Design; Equipment Failure Analysis; Event-related potentials; Event-Related Potentials, P300; Feature extraction; Flashing; Graphical user interface; Graphical user interfaces; Humans; Injuries; Male; Man-Machine Systems; P300; Patients; Psychomotor Performance; Reproducibility of Results; Rope; Sensitivity and Specificity; Spinal cord injuries; Spinal Cord Injuries - physiopathology; Spinal Cord Injuries - rehabilitation; spinal cord injury (SCI); Support vector machines; Switches; Training; User-Computer Interface; Variability; wheelchair; Wheelchairs; Young Adult
• ISSN: 1534-4320; 1558-0210
• DOI: 10.1109/TNSRE.2016.2591012

The key issue of electroencephalography (EEG)-based brain switches is to detect the control and idle states in an asynchronous manner. Most existing methods rely on a threshold. However, it is often time consuming to select a satisfactory threshold, and the chosen threshold might be inappropriate over a long period of time due to the variability of the EEG signals. This paper presents a new P300-based threshold-free brain switch. Specifically, one target button and three pseudo buttons, which are intensified in a random order to produce P300 potential, are set in the graphical user interface. The user can issue a switch command by focusing on the target button. Two support vector machine (SVM) classifiers, namely, SVM1 and SVM2, are used in the detection algorithm. During detection, we first obtained four SVM scores, corresponding to the four flashing buttons, by applying SVM1 to the ongoing EEG. If the SVM score corresponding to the target button was negative or not at the maximum, then an idle state was determined. Moreover, if the target button had a maximum and positive score, then we fed the four SVM scores as features into SVM2 to further discriminate the control and idle states. As an application, this brain switch was used to produce a start/stop command for an intelligent wheelchair, of which the left, right, forward, backward functions were carried out by an autonomous navigation system. Several experiments were conducted with eight healthy subjects and five patients with spinal cord injuries (SCIs). The experimental results not only demonstrated the effectiveness of our approach but also illustrated the potential application for patients with SCIs.