Sensor Anomaly Detection using Self Features Organizing Maps and Hierarchical-Clustring for Water Quality Assessment

Abstract

Sensor fault, outlier, and anomaly detection are essential in many fields and applications to identify anomalies, abnormal data, or outliers that are different from the usual sensor data streams, effectively guaranteeing the validity of the measurements obtained by multiple sensors. Water quality assessment applications often frequently depend on multiple sensors that are situated in remote areas. It is necessary to account for apparent sensor failures and insufficient input data to obtain useful and powerful information from evaluating the corresponding measurements. In this paper, self-organizing features maps (SFOM)-based methods and hierarchical clustering (HC) are applied to several physicochemical parameters data anomaly detection in water quality assessment. In this study, the surface water quality from Mostaganem's Cheliff Dam was advanced assessed (Algeria). The performances and the efficacy of the proposed approaches in feature selection using SFOM and sensor anomaly detection process by SFOM and HC techniques were demonstrated successfully involved in water quality assessment. This result has a major impact on our monitoring system's performance both technically (lower learning times and anomaly detection) and economically (some less sensors required).