Open AccessAnomaly Detection for Water Supply Data using Machine Learning Technique
Author(s) -
Shu Fang,
Weize Sun,
Lei Huang
Publication year - 2019
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1345/2/022054
Subject(s) - anomaly detection , christian ministry , data set , support vector machine , computer science , anomaly (physics) , big data , set (abstract data type) , water supply , resource (disambiguation) , data mining , water resources , artificial intelligence , class (philosophy) , machine learning , engineering , political science , computer network , ecology , physics , environmental engineering , biology , law , programming language , condensed matter physics
The advent of the era of big data brings new challenges and opportunities to water data processing. Abnormal detection or authenticity verification of water supply data becomes an urgent problem in natural resource data processing. This article addresses the issue of anomaly detection for a set of measured water supply data that provided by the Ministry of Water Resources of China. The machine learning technique, namely, One-Class support vector machine, is used for anomaly detection, and a detailed analysis of the features of anomalies is also provided. Experiments on three situations, namely, one dimensional situation, three dimensional situation and seven dimensional situation are carried out to analyse the features of anomalies. The experiment results revealed that the cases with entries of large values more than 10 times of median, zero entries together with some large values and ascending or descending sequences tend to have high abnormality scores.