Automated Detection of Anomalies in High Frequency Water Quality Sensor Data using Machine Learning. Wang, X., Sekerinski, E., & Copp, J. In 48th Annual WEAO Technical Symposium & OPCEA Exhibition, pages –116, April, 2019. Water Environment Association of Ontario. ![Automated Detection of Anomalies in High Frequency Water Quality Sensor Data using Machine Learning [pdf]](https://bibbase.org/img/filetypes/pdf.svg "pdf")
Paper abstract bibtex 1 download Wastewater treatment facilities are increasingly installing high frequency water quality sensors, which has created a need for automated tools to assess the quality of that data and signal for maintenance as the need arises. As these datasets have increased in size and complexity, it has become difficult to identify problems in a timely manner either manually or using simple rules that might have been sufficient previously. Two high frequency ammonia sensors were installed in November 2017 by Primodal in the primary effluent of the Dundas Wastewater Treatment Plant. Primary effluent ammonia is influenced by daily, seasonal and weather issues and thus exhibits typical stochastic behaviour. The algorithms developed in this project consider periodicity and make use of machine learning techniques to distinguish these issues, with the predicted anomalous data flagged and qualitatively ranked based on the severity and likelihood that the data are faulty.
@inproceedings{WangSekerinskiCopp19AnomalyDetection,
title = {Automated {Detection} of {Anomalies} in {High} {Frequency} {Water} {Quality} {Sensor} {Data} using {Machine} {Learning}},
shorttitle = {{WangSekerinskiCopp19AnomalyDetection}.pdf},
url = {https://www.cas.mcmaster.ca/~emil/pubs/WangSekerinskiCopp19AnomalyDetection.pdf},
abstract = {Wastewater treatment facilities are increasingly installing high frequency water quality sensors, which has created a need for automated tools to assess the quality of that data and signal for maintenance as the need arises. As these datasets have increased in size and complexity, it has become difficult to identify problems in a timely manner either manually or using simple rules that might have been sufficient previously. Two high frequency ammonia sensors were installed in November 2017 by Primodal in the primary effluent of the Dundas Wastewater Treatment Plant. Primary effluent ammonia is influenced by daily, seasonal and weather issues and thus exhibits typical stochastic behaviour. The algorithms developed in this project consider periodicity and make use of machine learning techniques to distinguish these issues, with the predicted anomalous data flagged and qualitatively ranked based on the severity and likelihood that the data are faulty.},
booktitle = {48th {Annual} {WEAO} {Technical} {Symposium} \& {OPCEA} {Exhibition}},
publisher = {Water Environment Association of Ontario},
author = {Wang, Xi and Sekerinski, Emil and Copp, John},
month = apr,
year = {2019},
pages = {--116},
}
Downloads: 1
{"_id":"dSZAr9viZHgg5g75Y","bibbaseid":"wang-sekerinski-copp-automateddetectionofanomaliesinhighfrequencywaterqualitysensordatausingmachinelearning-2019","author_short":["Wang, X.","Sekerinski, E.","Copp, J."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","title":"Automated Detection of Anomalies in High Frequency Water Quality Sensor Data using Machine Learning","shorttitle":"WangSekerinskiCopp19AnomalyDetection.pdf","url":"https://www.cas.mcmaster.ca/~emil/pubs/WangSekerinskiCopp19AnomalyDetection.pdf","abstract":"Wastewater treatment facilities are increasingly installing high frequency water quality sensors, which has created a need for automated tools to assess the quality of that data and signal for maintenance as the need arises. As these datasets have increased in size and complexity, it has become difficult to identify problems in a timely manner either manually or using simple rules that might have been sufficient previously. Two high frequency ammonia sensors were installed in November 2017 by Primodal in the primary effluent of the Dundas Wastewater Treatment Plant. Primary effluent ammonia is influenced by daily, seasonal and weather issues and thus exhibits typical stochastic behaviour. The algorithms developed in this project consider periodicity and make use of machine learning techniques to distinguish these issues, with the predicted anomalous data flagged and qualitatively ranked based on the severity and likelihood that the data are faulty.","booktitle":"48th Annual WEAO Technical Symposium & OPCEA Exhibition","publisher":"Water Environment Association of Ontario","author":[{"propositions":[],"lastnames":["Wang"],"firstnames":["Xi"],"suffixes":[]},{"propositions":[],"lastnames":["Sekerinski"],"firstnames":["Emil"],"suffixes":[]},{"propositions":[],"lastnames":["Copp"],"firstnames":["John"],"suffixes":[]}],"month":"April","year":"2019","pages":"–116","bibtex":"@inproceedings{WangSekerinskiCopp19AnomalyDetection,\n\ttitle = {Automated {Detection} of {Anomalies} in {High} {Frequency} {Water} {Quality} {Sensor} {Data} using {Machine} {Learning}},\n\tshorttitle = {{WangSekerinskiCopp19AnomalyDetection}.pdf},\n\turl = {https://www.cas.mcmaster.ca/~emil/pubs/WangSekerinskiCopp19AnomalyDetection.pdf},\n\tabstract = {Wastewater treatment facilities are increasingly installing high frequency water quality sensors, which has created a need for automated tools to assess the quality of that data and signal for maintenance as the need arises. As these datasets have increased in size and complexity, it has become difficult to identify problems in a timely manner either manually or using simple rules that might have been sufficient previously. Two high frequency ammonia sensors were installed in November 2017 by Primodal in the primary effluent of the Dundas Wastewater Treatment Plant. Primary effluent ammonia is influenced by daily, seasonal and weather issues and thus exhibits typical stochastic behaviour. The algorithms developed in this project consider periodicity and make use of machine learning techniques to distinguish these issues, with the predicted anomalous data flagged and qualitatively ranked based on the severity and likelihood that the data are faulty.},\n\tbooktitle = {48th {Annual} {WEAO} {Technical} {Symposium} \\& {OPCEA} {Exhibition}},\n\tpublisher = {Water Environment Association of Ontario},\n\tauthor = {Wang, Xi and Sekerinski, Emil and Copp, John},\n\tmonth = apr,\n\tyear = {2019},\n\tpages = {--116},\n}\n\n","author_short":["Wang, X.","Sekerinski, E.","Copp, J."],"key":"WangSekerinskiCopp19AnomalyDetection","id":"WangSekerinskiCopp19AnomalyDetection","bibbaseid":"wang-sekerinski-copp-automateddetectionofanomaliesinhighfrequencywaterqualitysensordatausingmachinelearning-2019","role":"author","urls":{"Paper":"https://www.cas.mcmaster.ca/~emil/pubs/WangSekerinskiCopp19AnomalyDetection.pdf"},"metadata":{"authorlinks":{}},"downloads":1},"bibtype":"inproceedings","biburl":"https://api.krunk.cn/emil/bib.php","dataSources":["HEdahWqKBpmSGmDwq","Nbe8oQSLcMDKvKKWt","MF5eGzpJnqf6bSAoG","ienufKdnmJs49AsjR","So4gmSWFmbQRNEuFs","ezsmw4w22u9JFLNYJ","CvQYP6Tmpapx74Mgr","RWydLHbBJqgdeh5jr"],"keywords":[],"search_terms":["automated","detection","anomalies","high","frequency","water","quality","sensor","data","using","machine","learning","wang","sekerinski","copp"],"title":"Automated Detection of Anomalies in High Frequency Water Quality Sensor Data using Machine Learning","year":2019,"downloads":1}