Epilepsy detection with artificial neural network based on as-fabricated neuromorphic chip platform

Epilepsy is a serious neurological condition caused by sudden abnormality of brain neurons. An accurate epilepsy detection based on electroencephalogram (EEG) signals can provide vital information for diagnosis and treatment. In this study, we propose lightweight automatic system with artificial neural network our as-fabricated neuromorphic chip. The proposed utilizes model to achieve high-accuracy without the need epilepsy-related prior knowledge. uses filter module convolutional preprocess raw EEG signal long short-term memory recurrent fully connected as classifier. examination, classification accuracy normal cases seizures approaches 99.10%, cases, interictal seizure reach 94.46%. This design provides possible in wearable or portable devices.