Detection of specific contamination events in water distribution system using ultraviolet spectra

Yin, Hang; Yu, Qiaojun; Dong, Hui; Hou, Dibo; Huang, Pingjie; Zhang, Guanxin

doi:10.1109/i2mtc.2018.8409760

Cited by 1 publication

(3 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Organic contaminants are major threats to water distribution systems because they affect the safety of drinking water [13][14][15][16]. Several organic aromatic compounds exhibit fingerprint characteristics for the UV-Vis spectrum.…”

Section: Organic Contaminant Selection and Dataset Acquisitionmentioning

confidence: 99%

“…Thus, the spectral dataset collected at different times has varying ranges of drift. The interference of baseline drift on the training and test datasets should be reduced [14][15][16]. If the raw data are modeled directly, then the detection results generate a large number of FPs and negatives.…”

Section: Effect Of Dynamic Orthogonal Projection Correctionmentioning

confidence: 99%

“…Unsupervised models lack prior knowledge, which results in a high detection limit and numerous false negatives and positives. By contrast, supervised learning models can maximize the fingerprint characteristics of the UV-Vis spectrum of special organic contaminants; this spectrum can detect lower concentrations of organic contaminants, increase detection rate, and reduce FAR [16]. However, the UV-Vis spectrum changes with the environment.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Adaptive Detection Method for Organic Contamination Events in Water Distribution Systems Using the UV-Vis Spectrum Based on Semi-Supervised Learning

Yin

Wang

et al. 2018

Water

Self Cite

View full text Add to dashboard Cite

A method that uses the ultraviolet-visible (UV-Vis) spectrum to detect organic contamination events in water distribution systems exhibits the advantages of rapid detection, low cost, and no need for reagents. The speed, accuracy, and comprehensive analysis of such a method meet the requirements for online water quality monitoring. However, the UV-Vis spectrum is easily disturbed by environmental factors that cause fluctuations of the spectrum and result in false alarms. This study proposes an adaptive method for detecting organic contamination events in water distribution systems that uses the UV-Vis spectrum based on a semi-supervised learning model. This method modifies the baseline using dynamic orthogonal projection correction and adjusts the support vector regression model in real time. Thus, an adaptive online anomaly detection model that maximizes the use of unlabeled data is obtained. Experimental results demonstrate that the proposed method is adaptive to baseline drift and exhibits good performance in detecting organic contamination events in water distribution systems.

show abstract

Section: Organic Contaminant Selection and Dataset Acquisitionmentioning

confidence: 99%

Section: Effect Of Dynamic Orthogonal Projection Correctionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation