Unsupervised Online Learning for Long-Term High Sensitivity Seizure Detection
Unsupervised Online Learning for Long-Term High Sensitivity Seizure Detection
复制标题
用于长期高灵敏度癫痫发作检测的无监督在线学习
DOI：
10.1109/embc44109.2020.9176122
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
Muller, Rikky
中科院分区：
文献类型：
--
作者：
Chua, Adelson;Jordan, Michael I.;Muller, Rikky
目前的癫痫检测系统依赖于机器学习分类器，这些分类器是离线训练的，随后需要人工再训练，以保持长时间的高检测准确性。对于一个真正的“部署即忘”的植入式癫痫检测系统，可以采用低功耗、边缘、在线学习算法来动态适应神经信号随时间的漂移。这项工作提出了SOUL：基于随机梯度下降的在线无监督逻辑回归分类器，该分类器提供连续的无监督在线模型更新，该模型最初是用离线标签训练的。SOUL在两个数据集上进行了测试，一个是CHB-MIT头皮脑电图数据集，另一个是来自墨尔本大学的长（bbb250小时）人类脑电图数据集。SOUL对两个数据集的平均累积灵敏度分别达到97.5%和97.9%，同时每天保持<1.2个假警报。与最先进的技术相比，在大多数受试者中观察到1-3%的中度灵敏度提高，在特异性影响<1%的三个受试者中观察到bb0 - 12%的大灵敏度提高。
Current seizure detection systems rely on machine learning classifiers that are trained offline and subsequently require manual retraining to maintain high detection accuracy over long periods of time. For a true deploy-and-forget implantable seizure detection system, a low power, at-the-edge, online learning algorithm can be employed to dynamically adapt to the neural signal drifts over time. This work proposes SOUL: Stochastic-gradient-descent-based Online Unsupervised Logistic regression classifier, which provides continuous unsupervised online model updates that was initially trained with labels offline. SOUL was tested on two datasets, the CHB-MIT scalp EEG dataset, and a long (>250 hours) human ECoG dataset from the University of Melbourne. SOUL achieves an average cumulative sensitivity of 97.5% and 97.9% for the two datasets respectively, while maintaining <1.2 false alarms per day. When compared with state-of-the-art, a moderate sensitivity improvement of 1-3% is observed on the majority of subjects and a large sensitivity improvement of >12% is observed on three subjects with <1% impact on specificity.
基于 MEMD 的自动伪影减少 - 用于癫痫发作预测
DOI：
--
发表时间：
2018
期刊：
Biomedical Circuits and Systems Conference
影响因子：
--
作者：
Lihan Tang;Menglian Zhao;Yizhao Zhou;Xiaobo Wu
通讯作者：
Xiaobo Wu