A Wearable Home BCI system: preliminary results with SSVEP protocol

This paper presents and discusses the realization and the performances of a wearable system for EEG-based BCI applications. The system (called Kimera) consists of a two-layer hardware architecture (the wireless acquisition and transmission board based on a BluetoothregARM chip, and a low power miniaturized biosignal acquisition analog front end) together with a software suite (called Bellerophonte) for the graphic user interface management, protocol execution, data recording, transmission and processing. The implemented BCI system was based on the SSVEP protocol, applied to a two state selection by using standards display/monitor with a couple of high efficiency LEDs. The frequency features of the signal were computed and used in the intention detection. The BCI algorithm is based on a supervised classifier implemented through a multi-class canonical discriminant analysis (CDA) with a continuous real-time feedback based on the mahalanobis distance parameter. Five healthy subjects participated in the first phase for a preliminary device validation. The obtained results are very interesting and promising, being lined out to the most recent performance reported in literature with a significant improvement both in system and in classification capabilities. The user-friendliness and low cost of the Kimera & Bellerophonte platform make it suitable for the development of home BCI applications