A Robust Brain-Computer Interface for Reliable Cognitive State Classification and Device Control

Brain-Computer Interfaces (BCIs) offer promising solutions for direct communication between the brain and external devices, with applications spanning from cognitive state classification to the device control. Despite their potential, ensuring high reliability and robustness in these systems remains a major challenge due to the non-stationary nature of EEG signals. In this paper, we introduce a novel framework for improving the reliability of EEG-based BCIs, with a focus on cognitive state classification and device control. Our approach utilizes Welch’s method to address EEG signal variability, producing more stable power spectral density (PSD) estimates through signal segmentation and periodogram averaging. While Welch’s method is computationally intensive, our pipeline optimizes the trade-off between accuracy and speed, ensuring real-time or near-real-time performance. The effectiveness of our method is validated through the experiments with open-source dataset and device control in real-time scenarios. The results highlight the robustness of our framework and its potential to advance BCI technology, paving the way for more reliable and user-friendly applications across various domains.