25 Oct 2018
 | 25 Oct 2018
Status: this preprint was under review for the journal DWES but the revision was not accepted.

Hybridisation of brownboost classifier and glowworm swarm based optimal sensor placement for water leakage detection

Rejeesh Rayaroth and Sivaradje Gopalakrishnan

Abstract. Water Distribution System distributes the water to customer with the better quality and pressure. Distribution system supplies the water from their source to usage point. Due to the leakage, the sufficient amount of water is not delivered to the consumer. Many researchers introduced the techniques for detecting the water leakage in distribution system. But, the water leakage detection accuracy was not improved and time consumption was also not reduced. To improve the water leakage detection performance, Enhanced BrownBoost Classifier based Glowworm Swarm Optimization (EBBC-GWO) Method is introduced. EBBC-GWO method introduces two models namely, Enhanced BrownBoost Classifier model and Glowworm Swarm Optimization model. Enhanced BrownBoost Classifier model considers k-Nearest Neighbor (k-NN) classifier as weak classifier. It classifies the training samples with neighbor's majority vote for allocating the object to the class. Brownboost classifier combines all k-NN classifier to construct strong classifier. By this way, data are classified as the normal data or abnormal data with higher accuracy. After classification, optimization process is executed where every solution corresponds to the glowworm (i.e., abnormal pressure data node) in search space. Every glowworm has objective function for addressing the optimization problem. Every glowworm operates in probabilistic means to choose the neighbor with higher luciferin value and transmit to it. Glowworm updates its location to the glowworm in dynamic decision space and optimal one is selected for water leakage detection. By this way, water leakage detection accuracy is improved with lesser false positive rate. Experimental evaluation of proposed EBBC-GWO method is carried out with respect to number of pressure data and sensor placement nodes. The results demonstrated that EBBC-GWO method is higher in case of classification accuracy, false positive rate, classification time and water leakage detection accuracy. The simulation results show that EBBC-GWO method increases the performance of water leakage detection accuracy and reduces classification time when compared to state-of-the-art works.

Publisher's note: Copernicus Publications remains neutral with regard to jurisdictional claims made in the text, published maps, institutional affiliations, or any other geographical representation in this preprint. The responsibility to include appropriate place names lies with the authors.
Rejeesh Rayaroth and Sivaradje Gopalakrishnan
Status: closed
Status: closed
AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment
Printer-friendly Version - Printer-friendly version Supplement - Supplement
Status: closed
Status: closed
AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment
Printer-friendly Version - Printer-friendly version Supplement - Supplement
Rejeesh Rayaroth and Sivaradje Gopalakrishnan
Rejeesh Rayaroth and Sivaradje Gopalakrishnan


Total article views: 1,476 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
1,200 224 52 1,476 86 102
  • HTML: 1,200
  • PDF: 224
  • XML: 52
  • Total: 1,476
  • BibTeX: 86
  • EndNote: 102
Views and downloads (calculated since 25 Oct 2018)
Cumulative views and downloads (calculated since 25 Oct 2018)

Viewed (geographical distribution)

Total article views: 1,289 (including HTML, PDF, and XML) Thereof 1,275 with geography defined and 14 with unknown origin.
Country # Views %
  • 1
Latest update: 17 Jul 2024
Short summary
Leaks are major concern for a water distribution network. Leak detection and optimal sensor placement for localisation of leaks are discussed. By increasing the number of sensors leak detection accuracy can be improved but cost of deployment increases. So we have to place optimal number of sensors at optimal places. Classification of water distribution network as normal and abnormal data are done with high accuracy. Optimisation,placing optimal sensors at optimal places also done with high accuracy.