Please use this identifier to cite or link to this item:
Title: Using Under-Trained Deep Ensembles to Learn under Extreme Label Noise: A Case Study for Sleep Apnea Detection
Authors: Nikolaidis, Konstantinos
Plagemann, Thomas
Kristiansen, Stein
Goebel, Vera
Kankanhalli, Mohan 
Keywords: Biomedical informatics
label noise
machine learning
sleep apnea
supervised learning
Issue Date: 1-Jan-2021
Publisher: Institute of Electrical and Electronics Engineers Inc.
Citation: Nikolaidis, Konstantinos, Plagemann, Thomas, Kristiansen, Stein, Goebel, Vera, Kankanhalli, Mohan (2021-01-01). Using Under-Trained Deep Ensembles to Learn under Extreme Label Noise: A Case Study for Sleep Apnea Detection. IEEE Access 9 : 45919-45934. ScholarBank@NUS Repository.
Rights: Attribution 4.0 International
Abstract: Improper or erroneous labelling can pose a hindrance to reliable generalization for supervised learning. This can have negative consequences, especially for critical fields such as healthcare. We propose an effective new approach for learning under extreme label noise for medical applications like sleep apnea, that is based on under-trained deep ensembles. Each ensemble member is trained with a subset of the training data, to acquire a general overview of the decision boundary separation, without focusing on potentially erroneous details. The accumulated knowledge of the ensemble is combined to form new labels, that determine a better class separation than the original labels. A new model is trained with these labels to generalize reliably despite the label noise. We evaluate our approach on the tasks of sleep apnea detection and sleep apnea severity classification, and observe performance improvement in kappa from 0.02 up-to 0.55. © 2013 IEEE.
Source Title: IEEE Access
ISSN: 2169-3536
DOI: 10.1109/access.2021.3067455
Rights: Attribution 4.0 International
Appears in Collections:Elements
Staff Publications

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
10_1109_access_2021_3067455.pdf1.26 MBAdobe PDF



Google ScholarTM



This item is licensed under a Creative Commons License Creative Commons