The use of hybrid manifold learning and support vector machines in the pipe failure rates prediction dataset
Paper ID : 1234-IST
1Moosa Kalanaki *, 2Mahdi Kalanaki
1Malek Ashtar University of Technology
2University of Zabol
This paper proposes a hybrid manifold learning approach model which combines both isometric feature mapping algorithm and support vector machines to predict the failure of pipes based on collected dataset. In this paper used PSO algorithm to get optimal SVM coefficients. By making use of the ISOMAP algorithm to perform dimension reduction, is then utilized as a preprocessor to improve pipes failure prediction capability by SVM. Analytic results demonstrate that our hybrid approach shows the best prediction rate, and is capable of achieving an improved predictive accuracy and of providing guidance for decision makers to detect and prevent failure rates in water distribution network.
Manifold learning; ISOMAP; Support vector machine; PSO; Pipes failure rate