Research and development of brain-computer interface for visual field assessment

Abstract

The assessment of visual function loss due to eye diseases such as Glaucoma using Steady-state visual evoked potentials (SSVEPs) has been an emerging area of research. This project involves the development of an SSVEP-based Brain Computer Interface (BCI) system, and a novel study on the system’s performance under covert orienting using a specially designed display interface. Canonical Correlation Analysis (CCA) was used due to its effectiveness and ease of implementation. The performance of different methods of calculating canonical coefficients were evaluated using a 16-target display interface (frequency from 8.0Hz – 17.2Hz broken into 3 ranges, frequency interval: 0.2Hz). The best performing method achieved an accuracy of 80.2 ± 7.3% for the frequency range of 11.2Hz – 14.2Hz. The display interface used in the study of covert orienting presented 4 stimuli arranged in a circle at 12,3,6, and 9 O’clock positions. The results from 2 angles, 3° and 6° from the focal view, were found to have an accuracy of 34.3% and 25% respectively.