Systems, Man, and Cybernetics

 

Home

• [P1017] Identification of domestic water consumption in a house based on fuzzy clustering algorithms
  Author(s): Ruben Ruelas, M. Adriana Corona-Nakamura
  
  

  Abstract
  This work presents classification results from time and flow measurements in a particular point of the water distribution network in a house. The FCM and Gustafson-Kessel models are used for the classifier and its parameter estimation. The data set is called AGUA and it corresponds to real data for a project being developed in Guadalajara, Mexico. Models were trained in an unsupervised way. So, the classifier learns the consumption at each output from time and flow patterns. The identified classes are relevant consumptions as sink consumption, shower consumption, etc. The results show that the proposed models work well, with 91.6 % of the examples classified correctly, and it could be used as part of a supervisor system in order to get a better profit of domestic water consumption

  
   

Full Text (PDF)