Zeki Sistemler Teori ve Uygulamaları Dergisi

Öz

In this study, it is predicted that there may be a certain order in the consumption of an important need such as drinking water by the household, as well as irregular consumption depending on different factors. Increasing population, limited drinking water resources, developing infrastructure and technology have increased the demand for drinking and utility water. There is a search for alternative water sources to meet this demand, but it is foreseen that these demands can be met by not wasting existing water and using it more efficiently. By using machine learning (ML) methods, which is a sub-branch of artificial intelligence (AI), drinking water consumption data in the past periods were analyzed, and ordinary and unusual consumption behavior models were extracted. It is envisaged that by detecting abnormal consumptions that may occur in drinking water consumption and informing the subscribers about this issue, it will be ensured that the consumption in the household remains within the normal consumption range. Although the amount of data collected, recorded and processed in today's IT world has increased significantly, it is known that the exact analysis is difficult in terms of time and cost. In this study, subscriber, meter, consumption, bill and payment data of 8,224 residential subscribers, whose water meter index reading is more than 160 periods throughout the province of Kayseri, between 2006 and 2022 (first 6 months) were taken into account. The data are combined on a spatial subscriber basis and a 41-features dataset is obtained. The dataset was transformed into a dataset
Journal of Intelligent Systems: Theory and Applications 6(2) (2023) 159-172 160
with 24 features as a result of data preprocessing. In the study, 6 sub-datasets were obtained by using information gain (IG), gain ratio (GR), symmetric uncertainty coefficient (SU), pearson correlation coefficient (r), f-score and random forest (RF) feature selection methods. The 7th sub-dataset was obtained from the intersections of the selected features in the sub-datasets. In all datasets, abnormal and normal drinking water consumptions were determined by using 7 different ML anomaly analysis methods: tukey outlier labeling (TOL), forest of isolation (IF), z-score, copula-based outlier detection (COPOD), median absolute deviation (MAD), local outlier factor (LOF), and elliptical envelope (EE). At the beginning of the study were unsupervised drinking water consumption data at the end of the study, labeled as 4 different classes and the dataset was made supervised. Using the finally obtained supervised dataset, decision trees (DT), gaussian naive bayes (NB), k-nearest neighbors (KNN), logistic regression (LJR), multilayer perceptron neural network (MLP-NN), RF and gradient boosting (GB) have been developed consumption class estimation models with 7 different ML methods.
As a result of the study, it has been proven that abnormal drinking water consumption can be detected by ML methods, and it has been revealed that necessary policies can be created for more efficient use of water without wasting water and measures can be taken for this.