Abstract:
A versatile Brain Computer Interface (BCI) system is designed and implemented to help severely disabled people achieve a fair level of autonomy. The proposed BCI is versatile in the sense it can flexibly be custom-tailored to individual users while not only mitigating deleterious artefacts, but also putting them to an advantage for an asynchronous, interactive, real-time, and fault-tolerant assistive system. It integrates, in a novel way, Independent Component Analysis (ICA) and correlation-based Template Matching (TM) in order to detect and intelligently deal with the artefacts. Hence, this BCI differentiates between involuntary eye blinks (considered artefacts, hence removed) and deliberate rapid eye blinks (considered synchronizing signals) used for distress calling, start/stop signalling, as well as fault-tolerance owing to the confirmation/cancellation of commands before their execution. Two classes of brain activities, optimized to suit the capabilities of each patient, are used to navigate through a flexible menu of commands intended to individually meet the users’ needs. The Wavelet Transform (WT) is used to extract sub-band-power-based features that are input to a Neural Network used as the classifier with a success rate reaching 90%. The system can flexibly be adapted to suit various scenarios involving binary load control (on/off of TV, light, A/C, etc…) as well as multilevel control (up/down level of bed, TV volume, room temperature…etc.). The merits of this system have been successfully demonstrated in practice, showing its potential contribution to smart hospitals and patient-care facilities.