Title: An abnormal node location method of industrial internet of things based on feature fuzzy clustering

Authors: Qiaoyun Chen; Chunmeng Lu

Addresses: School of Information Engineering, Jiaozuo University, Jiaozuo 454000, China ' School of Artificial Intelligence, Jiaozuo University, Jiaozuo 454000, China

Abstract: In order to overcome the problems of low positioning accuracy and long time-consuming of traditional anomaly node location methods, a new anomaly node location method of industrial internet of things based on feature fuzzy clustering is proposed in this paper. Firstly, collect the operation data of all nodes in the coverage area of the industrial internet of things. Secondly, according to the node operation data collection results, the standard deviation method is used to standardise the industrial internet of things node data, and extract the characteristics of abnormal nodes. Finally, the fuzzy clustering method is used to cluster the abnormal nodes, and the trilateral localisation method is used to locate the abnormal nodes according to the clustering results. The experimental results show that this method can reduce the positioning time on the premise of improving the positioning accuracy, and the average positioning accuracy reaches 99.11%.

Keywords: feature extraction; fuzzy clustering; industrial internet of things; abnormal node location.

DOI: 10.1504/IJIMS.2024.136711

International Journal of Internet Manufacturing and Services, 2024 Vol.10 No.1, pp.15 - 26

Received: 04 Aug 2022
Accepted: 01 Mar 2023
Published online: 19 Feb 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article