Developing an SSVEP-Based BCI System for Multi-Objective Control via IoT Integration

This paper explores the integration of Electroencephalography (EEG) with Brain-Computer Interface (BCI) technologies, highlighting the application in facilitating communication and control for individuals with severe motor disabilities. We focus on the capabilities of EEG to decode brain signals using modalities such as SSVEP, which is enhanced through Canonical Correlation Analysis (CCA) algorithm to improve classification accuracy. Additionally, we discuss the merging of these technologies with the Internet of Things (IoT) to extend BCI applications into daily activities through multi-device control system. Traditional BCI systems are typically designed for fixed, single-task scenarios, and often do not account for the complexities of multi-objective, cross-device tasks encountered in real-world environments. By integrating BCI technology with IoT, we address the limitations of single-task scenarios, enabling the use of independent BCI systems to perform tasks such as making phone dialing, moving wheelchairs, controlling robots, and transporting objects across different devices. This advancement provides effective support for the deployment of BCI technology in real-world applications. Our study demonstrates the implementation of a robust SSVEP-based BCI system that achieves a 97.0% classification accuracy across 500 trials, proving its efficacy in real-world scenarios. This research addresses the challenges of adapting BCI system to complex, varied environments and provides a viable solution for improving the quality of life for those with severe motor disabilities.