A spatiotemporal approach to N170 detection with application to brain-computer interfaces

Over the past decade, many laboratories have begun to explore brain-computer interface (BCI) technology as a radically new communication option. BCI can help users send messages and commands to the external world without using their brain´s normal output channels or muscles. The central element in each BCI system is to find a reliable method to detect the specific feature patterns extracted from the raw brain signals, and then translate it into usable control signals. In this paper, we introduce our approach to detect N170 component of the event-related brain potential (ERP) based on its spatiotemporal patterns in single-trial EEG signals. Common spatial pattern (CSP) method and machine-learning technique support vector machine (SVM) are adopted for N170 feature extraction and translation, i.e. they convert electrophysiological input from the user into on-off signal to control external devices. Our results indicate that the CSP can effectively extract discriminatory information, and SVM has an efficient performance for N170 classification. Comparing to several other methods, high performances of our framework show that the temporal and spatial features of N170 are very stable and it is promising for new type BCI applications.