MetaSleepLearner A Pilot Study on Fast Adaptation of Bio signals Based Sleep Stage Classifier to New Individual Subject Using Meta Learning

Identifying bio-signals based-sleep stages requires time-consuming and tedious labor of skilled clinicians . We propose the transfer learning framework, entitled MetaSleepLearner, based on Model Agnostic Meta-Learning (MAML) in order to transfer the acquired sleep staging knowledge from a large dataset to new individual subjects . The framework was demonstrated to require the labelling of only a few sleep epochs by the clinicians and allow the remainder to be handled by the system . In all acquired datasets, in comparison to the conventional approach, MetaSleep Learner achieved a range of 5.4\% to 17.7\% improvement with statistical difference in the mean of both approaches . This is the first work that investigated a non-conventional pre-training method, MAML, resulting in a possibility for human-machine collaboration in sleep stage classification in sleep stages. This is a possibility of human-human collaboration in the sleep stage . The work is published in the journal journal journal, The Open Neurological Institute for Neurological Research, published by Mediomedomedia, is published on Springer Springer Springer, Springer, on Tuesday, Springer and Springer . Springer, by Springer, at Springer. Springer, the journal, on Springer, published on the Springer, and Springer, is on the Open Neurologic Institute for Medical Innovation, on the journal.

Links: PDF - Abstract

Code :


Keywords : springer - sleep - journal - learning - based -

Leave a Reply

Your email address will not be published. Required fields are marked *