Online Test-Time Adaptation for Patient-Independent Seizure Prediction
Tingting Mao, Chang Li, Yuchang Zhao, Rencheng Song, Xun Chen
Abstract
Existing domain adaptation (DA) methods typically require access to source domain data, which raises privacy concerns due to the sensitive information contained in electroencephalogram (EEG) data. Moreover, test data generally arrive in a sequential or batch manner in real-world scenarios. To this end, we adopt online test-time adaptation (OTTA) paradigm, which adapts a pretrained source model, instead of the source data, to the target data stream at test time. OTTA is very useful in the epilepsy prediction task, which can protect patient privacy and achieve online prediction for seizures. Specifically, we introduce a novel teacher–student OTTA (TSOTTA) approach based on knowledge distillation (KD) and exponential moving average (EMA) strategy. Experiments on two public seizure datasets demonstrate that TSOTTA can enhance the generalization ability of the pretrained source model in cross-patient online seizure prediction.