Biomedical Signals Classification with Transformer Based Model

Seizures are caused by abnormal neuronal activity and are a common chronic brain disease. It is estimated that around 60 million people have epileptic seizures worldwide. Having an epileptic seizure can have serious consequences for the patient. Surface electroencephalogram (EEG) is a non-intrusive method frequently used to detect epileptic brain action. Nevertheless, graphic inspection of the EEG is biased, time-taken, and tedious for the neurologist. This paper proposes an automatic epileptic seizure classification technique using transformer based deep learning. Fast Fourier Transform (FFT) is first used to extract features from EEG data, and features are then used as inputs to a classifier for selection and classification. The suggested technique successfully gave 100% accuracy in the tested EEG readings. The effectiveness of the proposed method could vary across different EEG databases.