Abstract
Human eye blinks are considered a significant contaminant or artifact in electroencephalogram (EEG), which impacts EEG-based medical or scientific applications. However, eye blink detection can instead be transformed into a potential application of brain-computer interfaces (BCI). This study introduces a novel real-time EEG-based framework for classifying three blink states: no blink, single blink, and two consecutive blinks in one model. EEG data were collected from ten healthy participants using an 8-channel wearable headset under controlled blinking conditions. The data were preprocessed and analyzed using four feature extraction techniques: basic statistical, time-domain, amplitude-driven, and frequency-domain methods. The most significant features were selected to develop three machine learning models: XGBoost, support vector machine (SVM), and neural network (NN). We achieved the highest accuracy of 89.0% for classifying multiple-eye blink detection. To further enhance the model's capacity and suitability for real-life BCI applications, we trained and employed the You Only Look Once (YOLO) model, achieving a recall of 98.67%, a precision of 95.39%, and mAP50 of 99.5%, demonstrating its superior accuracy and robustness in classifying two consecutive eye blinks. In conclusion, this study will be the first groundwork and open a new dimension in EEG-based BCI research by classifying multiple-eye blink detection.