Näytä suppeat kuvailutiedot

dc.contributor.authorXu, Qi
dc.contributor.authorZhou, Dongdong
dc.contributor.authorWang, Jian
dc.contributor.authorShen, Jiangrong
dc.contributor.authorKettunen, Lauri
dc.contributor.authorCong, Fengyu
dc.date.accessioned2023-02-20T11:27:34Z
dc.date.available2023-02-20T11:27:34Z
dc.date.issued2022
dc.identifier.citationXu, Q., Zhou, D., Wang, J., Shen, J., Kettunen, L., & Cong, F. (2022). Convolutional Neural Network Based Sleep Stage Classification with Class Imbalance. In <i>IJCNN 2022 : Proceedings of the 2022 International Joint Conference on Neural Networks</i>. IEEE. Proceedings of International Joint Conference on Neural Networks. <a href="https://doi.org/10.1109/ijcnn55064.2022.9892741" target="_blank">https://doi.org/10.1109/ijcnn55064.2022.9892741</a>
dc.identifier.otherCONVID_156990634
dc.identifier.urihttps://jyx.jyu.fi/handle/123456789/85542
dc.description.abstractAccurate sleep stage classification is vital to assess sleep quality and diagnose sleep disorders. Numerous deep learning based models have been designed for accomplishing this labor automatically. However, the class imbalance problem existing in polysomnography (PSG) datasets has been barely investigated in previous studies, which is one of the most challenging obstacles for the real-world sleep staging application. To address this issue, this paper proposes novel methods with signal-driven and image-driven ways of noise addition to balance the imbalanced relationship in the training dataset samples. We evaluate the effectiveness of the proposed methods which are integrated into a convolutional neural network (CNN) based model. Experimental results evaluated on Sleep-EDF-V1, Sleep-EDF and CCSHS databases demonstrate that the proposed balancing approaches with specific tensity Gaussian white noise could enhance the overall or stage N1 recognition to some degree, especially the combination of two types of Data augmentation (DA) strategies shows the superiority of overall accuracy improvement.en
dc.format.mimetypeapplication/pdf
dc.language.isoeng
dc.publisherIEEE
dc.relation.ispartofIJCNN 2022 : Proceedings of the 2022 International Joint Conference on Neural Networks
dc.relation.ispartofseriesProceedings of International Joint Conference on Neural Networks
dc.rightsIn Copyright
dc.subject.othertraining
dc.subject.otherdeep learning
dc.subject.otherdatabases
dc.subject.otherneural networks
dc.subject.otherwhite noise
dc.subject.otherconvolutional neural networks
dc.subject.othersleep stage classification
dc.subject.otherclass imbalance problem
dc.subject.otherdata augmentation
dc.subject.othertime-frequency image
dc.titleConvolutional Neural Network Based Sleep Stage Classification with Class Imbalance
dc.typeconferenceObject
dc.identifier.urnURN:NBN:fi:jyu-202302201801
dc.contributor.laitosInformaatioteknologian tiedekuntafi
dc.contributor.laitosFaculty of Information Technologyen
dc.contributor.oppiaineLaskennallinen tiedefi
dc.contributor.oppiaineSecure Communications Engineering and Signal Processingfi
dc.contributor.oppiaineComputing, Information Technology and Mathematicsfi
dc.contributor.oppiaineTietotekniikkafi
dc.contributor.oppiaineTekniikkafi
dc.contributor.oppiaineComputational Scienceen
dc.contributor.oppiaineSecure Communications Engineering and Signal Processingen
dc.contributor.oppiaineComputing, Information Technology and Mathematicsen
dc.contributor.oppiaineMathematical Information Technologyen
dc.contributor.oppiaineEngineeringen
dc.type.urihttp://purl.org/eprint/type/ConferencePaper
dc.relation.isbn978-1-7281-8671-9
dc.type.coarhttp://purl.org/coar/resource_type/c_5794
dc.description.reviewstatuspeerReviewed
dc.relation.issn2161-4393
dc.type.versionacceptedVersion
dc.rights.copyright© 2022, IEEE
dc.rights.accesslevelopenAccessfi
dc.relation.conferenceInternational Joint Conference on Neural Networks
dc.subject.ysosyväoppiminen
dc.subject.ysounihäiriöt
dc.subject.ysouni (lepotila)
dc.subject.ysomallintaminen
dc.subject.ysoneuroverkot
dc.subject.ysoluokitus (toiminta)
dc.subject.ysotietokannat
dc.format.contentfulltext
jyx.subject.urihttp://www.yso.fi/onto/yso/p39324
jyx.subject.urihttp://www.yso.fi/onto/yso/p4600
jyx.subject.urihttp://www.yso.fi/onto/yso/p8299
jyx.subject.urihttp://www.yso.fi/onto/yso/p3533
jyx.subject.urihttp://www.yso.fi/onto/yso/p7292
jyx.subject.urihttp://www.yso.fi/onto/yso/p12668
jyx.subject.urihttp://www.yso.fi/onto/yso/p3056
dc.rights.urlhttp://rightsstatements.org/page/InC/1.0/?language=en
dc.relation.doi10.1109/ijcnn55064.2022.9892741
jyx.fundinginformationThis work was supported by National Key R&D Program of China National (No.2021ZD0109803), Natural Science Foundation of China (No.91748105), National Foundation in China (No. JCKY2019110B009, 2020-JCJQ-JJ-252), the Fundamental Research Funds for the Central Universities [DUT20LAB303, DUT20LAB308, DUT21RC(3)091] in Dalian University of Technology in China, Open Research Fund from Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ, No. GML-KF-22-11), CAAI-Huawei Mindspore Open Fund (CAAIXSJLJJ-2021-003A) and the Scholarships from China Scholarship Council (No.201806060164, No.202006060226).
dc.type.okmA4


Aineistoon kuuluvat tiedostot

Thumbnail

Aineisto kuuluu seuraaviin kokoelmiin

Näytä suppeat kuvailutiedot

In Copyright
Ellei muuten mainita, aineiston lisenssi on In Copyright