dc.contributor.author | Zhou, Dongdong | |
dc.contributor.author | Xu, Qi | |
dc.contributor.author | Wang, Jian | |
dc.contributor.author | Xu, Hongming | |
dc.contributor.author | Kettunen, Lauri | |
dc.contributor.author | Chang, Zheng | |
dc.contributor.author | Cong, Fengyu | |
dc.date.accessioned | 2023-02-20T11:25:09Z | |
dc.date.available | 2023-02-20T11:25:09Z | |
dc.date.issued | 2022 | |
dc.identifier.citation | Zhou, D., Xu, Q., Wang, J., Xu, H., Kettunen, L., Chang, Z., & Cong, F. (2022). Alleviating Class Imbalance Problem in Automatic Sleep Stage Classification. <i>IEEE Transactions on Instrumentation and Measurement</i>, <i>71</i>, Article 4006612. <a href="https://doi.org/10.1109/TIM.2022.3191710" target="_blank">https://doi.org/10.1109/TIM.2022.3191710</a> | |
dc.identifier.other | CONVID_151777995 | |
dc.identifier.uri | https://jyx.jyu.fi/handle/123456789/85541 | |
dc.description.abstract | For real-world automatic sleep-stage classification tasks, various existing deep learning-based models are biased toward the majority with a high proportion. Because of the unique sleep structure, most of the current polysomnography (PSG) datasets suffer an inherent class imbalance problem (CIP), in which the number of each sleep stage is severely unequal. In this study, we first define the class imbalance factor (CIF) to describe the level of CIP quantitatively. Afterward, we propose two balancing methods to alleviate this problem from the dataset quantity and the relationship between the class distribution and the applied model, respectively. The first one is to employ the data augmentation (DA) with the generative adversarial network (GAN) model and different intensities of Gaussian white noise (GWN) to balance samples, thereinto, GWN addition is specifically tailored to deep learning-based models, which can work on raw electroencephalogram (EEG) data while preserving their properties. In addition, we try to balance the relationship between the imbalanced class and biased network model to achieve a balanced state with the help of class distribution and neuroscience principles. We further propose an effective deep convolutional neural network (CNN) model utilizing bidirectional long short-term memory (Bi-LSTM) with single-channel EEG as the baseline. It is used for evaluating the efficiency of two balancing approaches on three imbalanced PSG datasets (CCSHS, Sleep-EDF, and Sleep-EDF-V1). The qualitative and quantitative evaluation of experimental results demonstrates that the proposed methods could not only show the superiority of class balancing through the confusion matrix and classwise metrics, but also get better N1 stage and whole stages classification accuracies compared to other state-of-the-art approaches. | en |
dc.format.mimetype | application/pdf | |
dc.language.iso | eng | |
dc.publisher | Institute of Electrical and Electronics Engineers (IEEE) | |
dc.relation.ispartofseries | IEEE Transactions on Instrumentation and Measurement | |
dc.rights | In Copyright | |
dc.subject.other | Class imbalance problem (CIP) | |
dc.subject.other | data augmentation (DA) | |
dc.subject.other | deep neural network | |
dc.subject.other | generative adversarial network (GAN) | |
dc.subject.other | network connection | |
dc.subject.other | sleep-stage classification | |
dc.title | Alleviating Class Imbalance Problem in Automatic Sleep Stage Classification | |
dc.type | research article | |
dc.identifier.urn | URN:NBN:fi:jyu-202302201800 | |
dc.contributor.laitos | Informaatioteknologian tiedekunta | fi |
dc.contributor.laitos | Faculty of Information Technology | en |
dc.contributor.oppiaine | Laskennallinen tiede | fi |
dc.contributor.oppiaine | Tekniikka | fi |
dc.contributor.oppiaine | Secure Communications Engineering and Signal Processing | fi |
dc.contributor.oppiaine | Computing, Information Technology and Mathematics | fi |
dc.contributor.oppiaine | Tietotekniikka | fi |
dc.contributor.oppiaine | Computational Science | en |
dc.contributor.oppiaine | Engineering | en |
dc.contributor.oppiaine | Secure Communications Engineering and Signal Processing | en |
dc.contributor.oppiaine | Computing, Information Technology and Mathematics | en |
dc.contributor.oppiaine | Mathematical Information Technology | en |
dc.type.uri | http://purl.org/eprint/type/JournalArticle | |
dc.type.coar | http://purl.org/coar/resource_type/c_2df8fbb1 | |
dc.description.reviewstatus | peerReviewed | |
dc.relation.issn | 0018-9456 | |
dc.relation.volume | 71 | |
dc.type.version | acceptedVersion | |
dc.rights.copyright | © 2022, IEEE | |
dc.rights.accesslevel | openAccess | fi |
dc.type.publication | article | |
dc.subject.yso | EEG | |
dc.subject.yso | signaalianalyysi | |
dc.subject.yso | uni (lepotila) | |
dc.subject.yso | koneoppiminen | |
dc.subject.yso | unitutkimus | |
dc.subject.yso | syväoppiminen | |
dc.subject.yso | neuroverkot | |
dc.format.content | fulltext | |
jyx.subject.uri | http://www.yso.fi/onto/yso/p3328 | |
jyx.subject.uri | http://www.yso.fi/onto/yso/p26805 | |
jyx.subject.uri | http://www.yso.fi/onto/yso/p8299 | |
jyx.subject.uri | http://www.yso.fi/onto/yso/p21846 | |
jyx.subject.uri | http://www.yso.fi/onto/yso/p21988 | |
jyx.subject.uri | http://www.yso.fi/onto/yso/p39324 | |
jyx.subject.uri | http://www.yso.fi/onto/yso/p7292 | |
dc.rights.url | http://rightsstatements.org/page/InC/1.0/?language=en | |
dc.relation.doi | 10.1109/TIM.2022.3191710 | |
jyx.fundinginformation | This work was supported in part by the National Key Research and Development Program of China under Grant 2021ZD0109803; in part by the National Natural Science Foundation of China under Grant 91748105; in part by the Youth Fund of the National Natural Science Foundation of China under Grant 82102135; in part by the National Foundation in China under Grant JCKY2019110B009 and Grant 2020-JCJQ-JJ-252; in part by the Fundamental Research Funds for Central Universities in the Dalian University of Technology in China under Grant DUT2019, Grant DUT20LAB303, and Grant DUT21RC(3)091; in part by the Open Project of Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, Anhui University under Grant MMC202104; in part by the Open Research Fund from the Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ) under Grant GML-KF-22-11; in part by the CAAI-Huawei Mindspore Open Fund under Grant CAAIXSJLJJ-2021-003A; and in part by the Scholarships from the China Scholarship Council under Grant 201806060164 and Grant 202006060226 | |
dc.type.okm | A1 | |