ORIGINAL RESEARCH article
Front. Bioinform.
Sec. Computational BioImaging
This article is part of the Research TopicAdvanced Computational Approaches For Data And Model Integration In Bioinformatic and Biomedical ResearchView all articles
SimpleKANSleepNet: A Kolmogorov–Arnold Network based Sleep Stage Classification Method
Provisionally accepted
- China University of Mining and Technology, Xuzhou, China
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
A novel Kolmogorov–Arnold Network (KAN) based machine learning model is proposed for the automatic sleep stage classification task. The redefined architecture of the Multilayer Perceptron (MLP) aims to build a more flexible model by using learnable activation functions. In this study, an effective KAN model named SimpleKANSleepNet is evaluated on two different datasets with temporal features and frequency features extracted from electroencephalography (EEG), electromyogram (EMG), electrooculogram (EOG), and electrocardiogram (ECG) signals through a dual-stream convolutional neural network (CNN). Compared with existing CNN-based methods and graph convolutional networks (GCNs), the proposed model achieves an overall classification accuracy, F1-score, and Cohen's kappa on the ISRUC-S1 and the Sleep-EDF-153 datasets of 0.812, 0.793, 0.757, 0.928, 0.929, and 0.910, respectively, which demonstrates its competitive classification performance and generality. Moreover, several data balancing methods are tested on Sleep-EDF-153 to further evaluate the potential for achieving the best results. Finally, the factors that may affect the classification ability are tested on the ISRUC-S1 dataset.
Keywords: Artificial intelligence (AI), deep learning, Electroencephalography (EEG), Kolmogorov–Arnold Network, sleep stage classification
Received: 03 Nov 2025; Accepted: 28 Jan 2026.
Copyright: © 2026 Ji, Wang and Zhou. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Xiaopeng Ji
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.