Detection algorithm of abnormal characteristics of urban domestic water quality based on K-means clustering

Xiaoying Huang

International Journal of Environmental Technology and Management, 2023, vol. 26, issue 3/4/5, 226-237

Abstract: In order to solve the problem of low detection accuracy in water quality anomaly detection, an urban domestic water quality anomaly detection algorithm based on K-means clustering is proposed. Firstly, by constructing the water quality feature extraction system and calculating the pollutant content by fluorescence method, the water quality feature extraction and pollutant content determination are completed. Then, normalise the data and introduce root mean square error to remove redundancy and complete the preprocessing. Finally, taking the pH value, ammonia nitrogen, oxygen consumption, chromaticity and turbidity of urban domestic water quality as abnormal values, the trust degree and data cluster distance between data are calculated through K-means clustering, and the abnormal characteristic detection model of urban domestic water quality is constructed to complete the detection. The results show that the proposed method has high accuracy in detecting the abnormal characteristics of urban domestic water quality.

Keywords: K-means clustering; urban domestic water; abnormal characteristics of water quality; DBN model; degree of trust; cluster distance. (search for similar items in EconPapers)
Date: 2023
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.inderscience.com/link.php?id=130795 (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:ids:ijetma:v:26:y:2023:i:3/4/5:p:226-237

Access Statistics for this article

More articles in International Journal of Environmental Technology and Management from Inderscience Enterprises Ltd
Bibliographic data for series maintained by Sarah Parker ().