Decision Tree Analysis Approaches to Classify Sensors Data in a Water Pumping Station

Abstract

Water pumping stations play a vital role in the lives of citizens, where a failure in the pumping schedule or the quality of the pumping may affect their lives. The data of the water pumping station may expose the weaknesses in the system of the station, which can be overcome using machine learning approaches. In this paper, six decision tree algorithms are examined to find the optimal one for classifying the data of water pumping stations. The main goal is to determine the fault in the sensors to control the pumping process and overcome future failures. Six algorithms, namely J48, Rep Tree, Random Forest, Decision Stump, Hoeffding Tree, and Random Tree, are examined before and after implementing the feature selection (FS) process. FS is implemented to find the most correlated sensors and remove the less correlated sensors. The FS process affects the accuracies of the algorithms and enhances the resulting accuracies of the algorithms. Random Forest and Random Tree algorithms prove their accuracy in data classification with 100% accuracy after implementing FS and removing the less correlated sensor data. The model can be used as an assistant tool for classifying and predicting the failure of a water pumping station.