Classification of domestic water consumption using an Anfis model

This work presents classification results of different water outputs in a house. Input variables are time and flow measurements in a point of the network distribution, and the identified classes are relevant consumptions as sink consumption, shower consumption, etc. Due to human influence on consumption data, we selected a classifier based on an interpretable model; that allows the incorporation of knowledge provided by users or experts. Thus, this study is based on the well known Anfis model and AGUA (real data taken for a project being developed in Guadalajara, Mexico) the data set corresponding to a supervised case. The result shows that the proposed algorithm works well, with recognition above 91%, and it could be used for a better profit of domestic water management.