Online Test-Time Adaptation for Patient-Independent Seizure Prediction
- 25 August 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 23 (19) , 23133-23144
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 pre-trained 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 online test-time adaptation (TSOTTA) approach based on knowledge distillation and exponential moving average (EMA) strategy. Experiments on two public seizure datasets demonstrated that TSOTTA can enhance the generalization ability of the pre-trained source model in cross-patient online seizure prediction.Keywords
Funding Information
- National Key Research and Development Program of China (2021YFF1200600)
- National Natural Science Foundation of China (41901350, 32271431, 62271186, 62071165)
- Fundamental Research Funds for the Central Universities of China (PA2023IISL0095)
This publication has 40 references indexed in Scilit:
- Efficient Epileptic Seizure Prediction Based on Deep LearningIEEE Transactions on Biomedical Circuits and Systems, 2019
- Epileptic seizure prediction based on local mean decomposition and deep convolutional neural networkThe Journal of Supercomputing, 2018
- Convolutional neural networks for seizure prediction using intracranial and scalp electroencephalogramNeural Networks, 2018
- Seizure Classification From EEG Signals Using Transfer Learning, Semi-Supervised Learning and TSK Fuzzy SystemIEEE Transactions on Neural Systems and Rehabilitation Engineering, 2017
- Crowdsourcing reproducible seizure forecasting in human and canine epilepsyBrain, 2016
- Sequence-Level Knowledge Distillation2016
- A novel STFT-ranking feature of multi-channel EMG for motion pattern recognitionExpert Systems with Applications, 2015
- Seizure prediction using EEG spatiotemporal correlation structureEpilepsy & Behavior, 2012
- Comparison of STFT and wavelet transform methods in determining epileptic seizure activity in EEG signals for real-time applicationComputers in Biology and Medicine, 2005
- Comparison of three nonlinear seizure prediction methods by means of the seizure prediction characteristicPhysica D: Nonlinear Phenomena, 2004