Home > Research > Publications & Outputs > Federated learning-based private medical knowle...

Links

Text available via DOI:

View graph of relations

Federated learning-based private medical knowledge graph for epidemic surveillance in internet of things

Research output: Contribution to Journal/MagazineJournal articlepeer-review

E-pub ahead of print

Standard

Federated learning-based private medical knowledge graph for epidemic surveillance in internet of things. / Wu, Xiaotong; Gao, Jiaquan; Bilal, Muhammad et al.
In: Expert Systems, Vol. 42, No. 1, e13372, 31.01.2025.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

APA

Wu, X., Gao, J., Bilal, M., Dai, F., Xu, X., Qi, L., & Dou, W. (2025). Federated learning-based private medical knowledge graph for epidemic surveillance in internet of things. Expert Systems, 42(1), Article e13372. Advance online publication. https://doi.org/10.1111/exsy.13372

Vancouver

Wu X, Gao J, Bilal M, Dai F, Xu X, Qi L et al. Federated learning-based private medical knowledge graph for epidemic surveillance in internet of things. Expert Systems. 2025 Jan 31;42(1):e13372. Epub 2023 Jun 11. doi: 10.1111/exsy.13372

Author

Bibtex

@article{4f9f9c00344243499e4cfbeab0a5bc3a,
title = "Federated learning-based private medical knowledge graph for epidemic surveillance in internet of things",
abstract = "With the explosive development of the Internet of Things (IoT), it is convenient and important to collect health data from medical sensors and smart devices and construct medical knowledge graph. The knowledge graph contributes to investigating the connection between patient and disease, especially for epidemic surveillance. However, it is possible to cause the leakage of sensitive health information due to the untrusted data collector or various malicious attackers. In this paper, we attempt to utilise federated learning to construct a special knowledge graph, that is, individual-symptom relationship diagram with local differential privacy (LDP-ISRD), for epidemic risk surveillance, which presents the underlying infectious relationship among individuals. At first, we propose a federated learning-based framework of LDP-ISRD by utilising individuals' smart devices in IoT. Then, we leverage locations to determine the connection among individuals in terms of physical contact. Next, we propose a randomised algorithm PrivISRD to implement federated learning-based LDP-ISRD, which consists of symptom perturbation and aggregation. Finally, extensive experiments evaluate the impact of various parameters and results demonstrate that LDP-ISRD has good performance.",
keywords = "epidemic surveillance, federated learning, knowledge graph, privacy protection, symptom onset",
author = "Xiaotong Wu and Jiaquan Gao and Muhammad Bilal and Fei Dai and Xiaolong Xu and Lianyong Qi and Wanchun Dou",
year = "2023",
month = jun,
day = "11",
doi = "10.1111/exsy.13372",
language = "English",
volume = "42",
journal = "Expert Systems",
issn = "0266-4720",
publisher = "Wiley-Blackwell",
number = "1",

}

RIS

TY - JOUR

T1 - Federated learning-based private medical knowledge graph for epidemic surveillance in internet of things

AU - Wu, Xiaotong

AU - Gao, Jiaquan

AU - Bilal, Muhammad

AU - Dai, Fei

AU - Xu, Xiaolong

AU - Qi, Lianyong

AU - Dou, Wanchun

PY - 2023/6/11

Y1 - 2023/6/11

N2 - With the explosive development of the Internet of Things (IoT), it is convenient and important to collect health data from medical sensors and smart devices and construct medical knowledge graph. The knowledge graph contributes to investigating the connection between patient and disease, especially for epidemic surveillance. However, it is possible to cause the leakage of sensitive health information due to the untrusted data collector or various malicious attackers. In this paper, we attempt to utilise federated learning to construct a special knowledge graph, that is, individual-symptom relationship diagram with local differential privacy (LDP-ISRD), for epidemic risk surveillance, which presents the underlying infectious relationship among individuals. At first, we propose a federated learning-based framework of LDP-ISRD by utilising individuals' smart devices in IoT. Then, we leverage locations to determine the connection among individuals in terms of physical contact. Next, we propose a randomised algorithm PrivISRD to implement federated learning-based LDP-ISRD, which consists of symptom perturbation and aggregation. Finally, extensive experiments evaluate the impact of various parameters and results demonstrate that LDP-ISRD has good performance.

AB - With the explosive development of the Internet of Things (IoT), it is convenient and important to collect health data from medical sensors and smart devices and construct medical knowledge graph. The knowledge graph contributes to investigating the connection between patient and disease, especially for epidemic surveillance. However, it is possible to cause the leakage of sensitive health information due to the untrusted data collector or various malicious attackers. In this paper, we attempt to utilise federated learning to construct a special knowledge graph, that is, individual-symptom relationship diagram with local differential privacy (LDP-ISRD), for epidemic risk surveillance, which presents the underlying infectious relationship among individuals. At first, we propose a federated learning-based framework of LDP-ISRD by utilising individuals' smart devices in IoT. Then, we leverage locations to determine the connection among individuals in terms of physical contact. Next, we propose a randomised algorithm PrivISRD to implement federated learning-based LDP-ISRD, which consists of symptom perturbation and aggregation. Finally, extensive experiments evaluate the impact of various parameters and results demonstrate that LDP-ISRD has good performance.

KW - epidemic surveillance

KW - federated learning

KW - knowledge graph

KW - privacy protection

KW - symptom onset

U2 - 10.1111/exsy.13372

DO - 10.1111/exsy.13372

M3 - Journal article

AN - SCOPUS:85161656085

VL - 42

JO - Expert Systems

JF - Expert Systems

SN - 0266-4720

IS - 1

M1 - e13372

ER -