Analysis of the Consumption of Household Appliances for the Detection of Anomalies in the Behaviour of Older People

  • Miguel A. PatricioEmail author
  • Daniel González
  • José M. Molina
  • Antonio Berlanga
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11486)


Nowadays, modern societies are facing the important problem of ageing of their population. On many occasions, older people must leave their homes to be cared for by their relatives or to enter specialised centres for the elderly. On the other hand, something similar happens with disabled people who need the support of other people for their daily activity. This phenomenon brings with it important social and economic consequences. In the activities of the daily life of the elderly it is necessary to have the monitoring of different aspects of their physical activity, such as the detection of critical situations (such as falls) or dangerous situations (such as flooding or gas leaks). The aim of this paper is to analyse the consumption of the different household appliances in order to model a normal behaviour within the daily activities of a house. By means of the consumption of the electrical appliances the aim is to detect anomalous behaviours that induce the appearance of possible problems due to the change in the consumption pattern.


Anomaly detection Support for daily activities Elderly Behaviour analysis 



This work was funded by private research project of Company BQ and public research projects of Spanish Ministry of Economy and Competitivity (MINECO), references TEC2017-88048-C2-2-R, RTC-2016-5595-2, RTC-2016-5191-8 and RTC-2016-5059-8.


  1. 1.
    Baldi, P.: Autoencoders, unsupervised learning, and deep architectures. J. Mach. Learn. Res. (2012). Scholar
  2. 2.
    Belley, C., Gaboury, S., Bouchard, B., Bouzouane, A.: An efficient and inexpensive method for activity recognition within a smart home based on load signatures of appliances. Pervasive Mob. Comput. (2014). Scholar
  3. 3.
    Breiman, L.: Random forests LEO. Mach. Learn. (2001). Scholar
  4. 4.
    Davis, J., Goadrich, M.: The relationship between Precision-Recall and ROC curves. In: Proceedings of the 23rd International Conference on Machine Learning - ICML 2006 (2006).
  5. 5.
    Evans, L.K.: Sundown syndrome in institutionalized elderly. J. Am. Geriatr. Soc. (1987). Scholar
  6. 6.
    Goutte, C., Gaussier, E.: A probabilistic interpretation of precision, recall and F-score, with implication for evaluation. In: Losada, D.E., Fernández-Luna, J.M. (eds.) ECIR 2005. LNCS, vol. 3408, pp. 345–359. Springer, Heidelberg (2005). Scholar
  7. 7.
    Kelly, J., Knottenbelt, W.: The UK-DALE dataset, domestic appliance-level electricity demand and whole-house demand from five UK homes. Sci. Data (2015). Scholar
  8. 8.
    Martinelli, M., Tronci, E., Dipoppa, G., Balducelli, C.: Electric power system anomaly detection using neural networks. In: Negoita, M.G., Howlett, R.J., Jain, L.C. (eds.) KES 2004. LNCS (LNAI), vol. 3213, pp. 1242–1248. Springer, Heidelberg (2004). Scholar
  9. 9.
    Pedregosa, F., et al.: Scikitlearn: machine learning in Python. J. Mach. Learn. Res. (2011).
  10. 10.
    United Nations: World Population Ageing 2015. Technical report (2015). ST/ESA/SER.A/390Google Scholar
  11. 11.
    Yuan, Y., Jia, K.: A distributed anomaly detection method of operation energy consumption using smart meter data. In: 2015 International Conference on Intelligent Information Hiding and Multimedia Signal Processing (IIH-MSP), pp. 310–313 (2015)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Applied Artificial Intelligence GroupUniversidad Carlos III de MadridMadridSpain
  2. 2.BQ EngineeringMadridSpain

Personalised recommendations