Design and implementation of a brain-computer interface with high transfer rates

TLDR

The paper presents a BCI that enables users to input phone numbers via gaze and discusses ways to improve its performance. The system uses a steady‑state visual evoked potential (SSVEP) interface with twelve rate‑coded buttons forming a virtual telephone keypad, where gaze‑based frequency decoding selects the desired digit. Eight of thirteen users successfully called a mobile phone, achieving an average transfer rate of 27.15 bits/min, with the system offering noninvasive recording, minimal training, and high information transfer.

Abstract

This paper presents a brain-computer interface (BCI) that can help users to input phone numbers. The system is based on the steady-state visual evoked potential (SSVEP). Twelve buttons illuminated at different rates were displayed on a computer monitor. The buttons constituted a virtual telephone keypad, representing the ten digits 0-9, BACKSPACE, and ENTER. Users could input phone number by gazing at these buttons. The frequency-coded SSVEP was used to judge which button the user desired. Eight of the thirteen subjects succeeded in ringing the mobile phone using the system. The average transfer rate over all subjects was 27.15 bits/min. The attractive features of the system are noninvasive signal recording, little training required for use, and high information transfer rate. Approaches to improve the performance of the system are discussed.