A federated semi-supervised automatic sleep staging method based on relationship knowledge sharing

被引:3
作者
Ma, Bian [1 ,2 ,3 ]
Duan, Lijuan [1 ,2 ,3 ,7 ]
Huang, Zhaoyang [4 ,5 ]
Qiao, Yuanhua [6 ]
Gong, Bei [1 ,2 ]
机构
[1] Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China
[2] Beijing Key Lab Trusted Comp, Beijing 100124, Peoples R China
[3] China Natl Engn Lab Crit Technol Informat Secur Cl, Beijing 100124, Peoples R China
[4] Capital Med Univ, Xuanwu Hosp, Dept Neurol, Beijing 100053, Peoples R China
[5] Beijing Key Lab Neuromodulat, Beijing 100053, Peoples R China
[6] Beijing Univ Technol, Coll Appl Sci, Beijing 100124, Peoples R China
[7] Beijing Univ Technol, 100 Pingleyuan, Beijing, Peoples R China
基金
中国国家自然科学基金;
关键词
Automatic sleep staging; Federated semi-supervised learning; Relationship knowledge; Prototype-contrastive learning; Pseudo-labeling optimization; CLASSIFICATION;
D O I
10.1016/j.eswa.2023.121427
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Sleep staging is essential in assessing sleep quality and diagnosing sleep-related disorders, but the lack of labeled data impedes the development of automatic sleep staging models. Generally, institutions rely on semi-supervised approaches to enhance the utilization of their own unlabeled data. However, the task knowledge obtained from a limited amount of labeled data is often insufficient to guide the learning based on large amounts of unlabeled data, which may even lead to catastrophic forgetting and further degrade the performance of most existing methods. In this paper, we propose a novel strategy of building secure collaboration among multiple institutions, to achieve the implicit augmentation of labeled data and expansion of task knowledge for each participating institution by acquiring external knowledge from others. We adopt the Federated Learning (FL) to facilitate secure collaboration and propose a federated semi-supervised sleep staging method based on knowledge sharing, which enables the automatic scoring of sleep stages using only single-channel EEG data. The task knowledge in our method is contained in relationships, which exist naturally among sleep stages and can be extracted from both local labeled and unlabeled data. Furthermore, the knowledge sharing among participating institutions can be achieved by aligning the local relationships to the aggregated global relationships. Additionally, we employ prototype-contrastive learning to enhance the clarity of relationships extracted from labeled data, and propose pseudo-labeling optimization to generate reliable pseudo-labels for subsequent relationship extraction from unlabeled data. Our method is shown to be effective and outperforms compared methods in extensive experiments conducted on two publicly available datasets.
引用
收藏
页数:14
相关论文
共 50 条
[41]   A batch-mode active learning SVM method based on semi-supervised clustering [J].
Fu, Chun-Jiang ;
Yang, Yu-Pu .
INTELLIGENT DATA ANALYSIS, 2015, 19 (02) :345-358
[42]   A semi-supervised self-training method based on density peaks and natural neighbors [J].
Zhao, Suwen ;
Li, Junnan .
JOURNAL OF AMBIENT INTELLIGENCE AND HUMANIZED COMPUTING, 2021, 12 (02) :2939-2953
[43]   Semi-Supervised Remote Sensing Image Semantic Segmentation Method Based on Deep Learning [J].
Li, Linhui ;
Zhang, Wenjun ;
Zhang, Xiaoyan ;
Emam, Mahmoud ;
Jing, Weipeng .
ELECTRONICS, 2023, 12 (02)
[44]   A comprehensive evaluation method for frailty based on semi-supervised learning and transfer-learning [J].
Li, Jiaxi ;
Wang, Zhelong ;
Wang, Zheng ;
Qiu, Sen ;
Peng, Daoyong ;
Zhang, Ke ;
Lin, Fang .
INFORMATION FUSION, 2024, 111
[45]   Semi-Supervised Self-Training Method Based on an Optimum-Path Forest [J].
Li, Junnan ;
Zhu, Qingsheng .
IEEE ACCESS, 2019, 7 :36388-36399
[46]   Semi-supervised time series classification method for quantum computing [J].
Sheir Yarkoni ;
Andrii Kleshchonok ;
Yury Dzerin ;
Florian Neukart ;
Marc Hilbert .
Quantum Machine Intelligence, 2021, 3
[47]   A semi-supervised resampling method for class-imbalanced learning [J].
Jiang, Zhen ;
Zhao, Lingyun ;
Lu, Yu ;
Zhan, Yongzhao ;
Mao, Qirong .
EXPERT SYSTEMS WITH APPLICATIONS, 2023, 221
[48]   Bootstrapping semi-supervised annotation method for potential suicidal messages [J].
Acuna Caicedo, Roberto Wellington ;
Gomez Soriano, Jose Manuel ;
Melgar Sasieta, Hector Andres .
INTERNET INTERVENTIONS-THE APPLICATION OF INFORMATION TECHNOLOGY IN MENTAL AND BEHAVIOURAL HEALTH, 2022, 28
[49]   Generative Adversarial Networks-Based Semi-Supervised Automatic Modulation Recognition for Cognitive Radio Networks [J].
Li, Mingxuan ;
Li, Ou ;
Liu, Guangyi ;
Zhang, Ce .
SENSORS, 2018, 18 (11)
[50]   A recursive feature retention method for semi-supervised feature selection [J].
Pang, Qingqing ;
Zhang, Li .
INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS, 2021, 12 (09) :2639-2657