 This paper proposes a novel approach for detecting eye blinks in EEG recordings of epileptic patients. The authors developed a multi-dimensional feature optimization algorithm based on smooth non-linear energy operator, SNEO, and variational mode extraction, VME. This algorithm was then combined with a variance filtering method to select discriminative features and a machine learning model was trained to perform detection. The results showed that their method achieved higher accuracy than five other existing approaches. This article was authored by Meng Wang, Jianhui Wang, Xiaoran Shui, and others.