A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Detection of Water Meter Under-Registration Using Statistical Algorithms
AbstractMeter tampering is an important problem for utilities (both power and water distribution) to address because they represent an important loss of income. The authors’ group at the Electronic Technology Department of the University of Seville worked with the Empresa Metropolitana de Abastecimiento y Saneamiento de Aguas de Sevilla (EMASESA Company, a water distribution company in Seville and one of the most important of the country) to develop a methodology consisting of three algorithms that makes it possible to jointly detect this type of manipulations among its customers. The algorithms were generated and programmed after a data mining process using the database of the company. In addition, these algorithms were supplemented with a study of the geographical information of the customer supply points to improve the results. To test the results, the Emasesa Company performed in situ inspections of the customers selected by the algorithms for several areas in the province of Seville. The success rate of the algorithms was approximately 9%, which is considered satisfactory owing to the nature of the problem, in which fraud is easy to hide and infrequently detected.
Detection of Water Meter Under-Registration Using Statistical Algorithms
AbstractMeter tampering is an important problem for utilities (both power and water distribution) to address because they represent an important loss of income. The authors’ group at the Electronic Technology Department of the University of Seville worked with the Empresa Metropolitana de Abastecimiento y Saneamiento de Aguas de Sevilla (EMASESA Company, a water distribution company in Seville and one of the most important of the country) to develop a methodology consisting of three algorithms that makes it possible to jointly detect this type of manipulations among its customers. The algorithms were generated and programmed after a data mining process using the database of the company. In addition, these algorithms were supplemented with a study of the geographical information of the customer supply points to improve the results. To test the results, the Emasesa Company performed in situ inspections of the customers selected by the algorithms for several areas in the province of Seville. The success rate of the algorithms was approximately 9%, which is considered satisfactory owing to the nature of the problem, in which fraud is easy to hide and infrequently detected.
Detection of Water Meter Under-Registration Using Statistical Algorithms
Peña, Manuel (author) / Roldán, Moisés / Monedero, Iñigo / Guerrero, Juan I / Biscarri, Félix / León, Carlos
2016
Article (Journal)
English
Detection of Water Meter Under-Registration Using Statistical Algorithms
| British Library Online Contents | 2016
Domestic flow as affecting meter registration and water revenue
| Engineering Index Backfile | 1932