Communication science et technologie
Volume 23, Numéro 1, Pages 1-12
2025-07-23
A Clustering-driven Strategy Utilizing Dbscan For Detecting Outliers In Water Quality Data.
Authors : Khelil Mohamed Imed . Laadjal Mohamed . Ouali Mohammed Assam . Bennacer Hamza .
Abstract
Monitoring environmental data to ensure the safety and reliability of public resources has become a crucial task in data-driven systems. One key aspect of this monitoring is the detection of anomalies—data points or behaviors that significantly diverge from the norm. This study explores the use of a density-based clustering method, DBSCAN, to identify such anomalies within datasets collected from drinking water treatment facilities. DBSCAN's capability to recognize dense regions and isolate noise makes it well suited for flagging irregularities in complex, real-world data. By applying this method to extensive datasets with diverse attributes, the research aims to enhance the consistency and safety of drinking water production processes, contributing to improved public health outcomes and operational resilience in water management systems.
Keywords
Anomaly detection ; DBSCAN ; water treatment ; clustering algorithms ; environmental data analysis.
Les articles similaires
Hadj-tayeb Karima
.
Belbachir Hafida
.
pages 29-35.
Loucif Leila
.
Chelli Saliha
.
pages 736-755.
محمد ريضا جعفاري
.
طيب موسلي
.
ص 21-45.
Ziani Abdelhak
.
Medjdoub Kheira
.
pages 99-117.
Ghodbane M.
.
Boumeddane B.
.
Said N.
.
pages 804-825.
