Skip to main content
SpringerLink
Log in

Nonparametric user activity modelling and prediction

  • Published:
User Modeling and User-Adapted Interaction Aims and scope Submit manuscript

Abstract

Modelling the occupancy of buildings, rooms or the usage of machines has many applications in varying fields, exemplified by the fairly recent emergence of smart, self-learning thermostats. Typically, the aim of such systems is to provide insight into user behaviour and incentivise energy savings or to automatically reduce consumption while maintaining user comfort. This paper presents a nonparametric user activity modelling algorithm, i.e. a Dirichlet process mixture model implemented by Gibbs sampling and the stick-breaking process, to infer the underlying patterns in user behaviour from the data. The technique deals with multiple activities, such as <present, absent, sleeping>, of multiple users. Furthermore, it can also be used for modelling and predicting appliance usage (e.g. <on, standby, off>). The algorithm is evaluated, both on cluster validity and predictive performance, using three case studies of varying complexity. The obtained results indicate that the method is able to properly assign the activity data into well-defined clusters. Moreover, the high prediction accuracy demonstrates that these clusters can be exploited to anticipate future behaviour, facilitating the development of intelligent building management systems.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Similar content being viewed by others

Notes

  1. As some activities, such as eating, occur multiple times per day, scarceness could possibly be attributed to sensor failures or missing annotations. However, given it is an external data set, this could not be investigated. Additionally, these activities are typically very short and since the data are segmented into 15-min time slots, for which only one activity can be in effect (the one that was started the last in that time slot), some occurrences might be lost.

  2. http://www-sop.inria.fr/members/Francois.Bremond/topicsText/gerhomeProject.html.

References

  • Antoniak, C.E.: Mixtures of Dirichlet processes with applications to Bayesian nonparametric problems. Ann. Stat. 2, 1152–1174 (1974)

    Article  MathSciNet  MATH  Google Scholar 

  • Barbato, A., Borsani, L., Capone, A., Melzi, S.: Home energy saving throug a user profiling system based on wireless sensors. In: Proceedings of ACM Workshop on Embedded Sensing Systems for Energy-Efficiency in Buildings, pp. 49–54 (2009)

  • Barbato, A., Capone, A., Rodolfi, M.: Tagliaferri, D: Forecasting the usage of household appliances through power meter sensors for demand management in the smart grid. In: Proceedings of IEEE SmartGridComm, pp. 404–409 (2011)

  • Basu, K., Hawarah, L., Arghira, N.N., Joumaa, H., Ploix, S.: A prediction system for home appliance usage. Energy Build. 67, 668–679 (2013)

    Article  Google Scholar 

  • Beltran, A., Erickson, V.L., Cerpa, A.E.: ThermoSense: occupancy thermal based sensing for HVAC control. In: Proceedings of ACM Workshop on Embedded Systems for Energy-Efficient Buildings, pp. 1–8 (2013)

  • Bouchachia, A.: Fuzzy classification in dynamic environments. Soft. Comput. 15(5), 1009–1022 (2011)

    Article  Google Scholar 

  • Capozzoli, A., Lauro, F., Khan, I.: Fault detection analysis using data mining techniques for a cluster of smart office buildings. Expert Syst. Appl. 42(9), 4324–4338 (2015)

    Article  Google Scholar 

  • Chang, C., Verhaegen, P.A., Duflou, J.R.: A comparison of classifiers for intelligent machine usage prediction. In: Proceedings of IEEE IE, pp. 198–201 (2014)

  • Cook, D.J., Scmitter-Edgecombe, M.: Assessing the quality of activities in a smart environment. Methods Inf. Med. 48(5), 480–485 (2009)

    Article  Google Scholar 

  • Crites, R.H., Barto, A.G.: Elevator group control using multiple reinforcement learning agents. Mach. Learn. 33(2), 235–262 (1998)

    Article  MATH  Google Scholar 

  • Duflou, J., Auquilla, A., De Bock, Y., Nowé, A., Kellens, K.: Impact reduction potential by usage anticipation under comfort trade-off conditions. CIRP Ann. 65(1), 33–36 (2016)

    Article  Google Scholar 

  • De Bock, Y., Auquilla, A., Kellens, K., Vandevenne, D., Nowé, A., Duflou, J.R.: User adapting system design for improved energy efficiency during the use phase of products: case study of an occupancy-driven, self-learning thermostat. Sustainability through innovation in product life cycle design, pp. 883–898 (2016a)

  • De Bock, Y., Auquilla, A., Kellens, K., Nowé, A., Duflou, J.R.: Intelligent occupancy-driven thermostat by dynamic user profiling. In Electronics Goes Green 2016+ (EGG), IEEE, pp. 1–8 (2016b)

  • De Hauwere, Y.M., Van Moffaert, K., Verhaegen, P.A., Nowé, A.: Networks as a tool to save energy while keeping up general user comfort in buildings. In: Proceedings of IEEE LANMAN, pp. 1–6 (2013)

  • Energy Information Administration, Residential Energy Consumption Survey, https://www.eia.gov/consumption/residential/data/2009/index.php?view=consumption#end-use (2009). Accessed 1 June 2017

  • Energy Information Administration, Commercial Buildings Energy Consumption Survey, https://www.eia.gov/consumption/commercial/data/2012/c&e/cfm/e1.php (2012). Accessed 1 June 2017

  • Erickson, V.L., Achleitner, S., Cera, A.E.: POEM: Power-efficient occupancy-based energy management system. In: Proceedings of ACM/IEEE IPSN, pp. 203–216 (2013)

  • European Environment Agency, Household energy consumption by end-use in the EU-27, www.eea.europa.eu/data-and-maps/figures/households-energy-consumption-by-end-uses-4 (2012). Accessed 1 June 2017

  • Ferguson, T.S.: A Bayesian analysis of some nonparametric problems. Ann. Stat. 1, 209–230 (1973)

    Article  MathSciNet  MATH  Google Scholar 

  • Fischer, J.E., Ramchurn, S.D., Osborne, M., Parson, O., Huynh, T.D., Alam, M., Pantidi, N., Moran, S., Bachour, K., Reece, S., Costanza, E.: Recommending energy tariffs and load shifting based on smart household usage profiling. In: Proceedings of ACM IUI, pp. 383–394 (2013)

  • Frye, A., Goraczko, M., Liu, J., Prodhan, A., Whitehouse, K.: Circulo: saving energy with just-in-time hot water recirculation. In: Proceedings of ACM Buildsys, pp. 1–8 (2013)

  • Garg, V., Bansal, N.K.: Smart occupancy sensors to reduce energy consumption. Energy Build. 32(1), 81–87 (2000)

    Article  Google Scholar 

  • Global e-Sustainability Initiative, #SMARTer2030: ICT solutions for 21st century challenges, Brussels (2015), http://www.smarter2030.org. Accessed 1 June 2017

  • Gupta, M., Intille, S.S., Larson, K.: Adding GPS-control to traditional thermostats: an exploration of potential energy savings and design challenges. In: Proceedings of PerCom, pp. 95–114 (2009)

  • Halkidi, M., Batistakis, Y., Vazirgiannis, M.: Cluster validity methods: Part I. ACM Sigmod Record 31(2), 40–45 (2002a)

    Article  Google Scholar 

  • Halkidi, M., Batistakis, Y., Vazirgiannis, M.: Clustering validity checking methods: Part II. ACM Sigmod Record 31(3), 19–27 (2002b)

    Article  MATH  Google Scholar 

  • Ishwaran, H., James, L.F.: Gibbs sampling methods for stick-breaking priors. J. Am. Stat. Assoc. 96, 161–173 (2001)

    Article  MathSciNet  MATH  Google Scholar 

  • Iversen, E.B., Morales, J.M., Madsen, H.: Optimal charging of an electric vehicle using a markov decision process. APP. Energy. 123, 1–12 (2014)

    Article  Google Scholar 

  • Kalksma, M., Setz, B., Pratama, A.R., Georgievski, I., Aiello, M.: Mining sequential patterns for appliance usage prediction. In: Proceedings of Smartgreens, pp. 23–33 (2018)

  • Kim, S.H., Moon, H.J., Yoon, Y.R.: Improved occupancy detection accuracy using PIR and door sensors for a smart thermostat. Build. Simul. 15, 2753–2758 (2017)

    Google Scholar 

  • Kleiminger, W., Beckel, C., Staake, T. Santini, S.: Occupancy detection from electricity consumption data. In: Proceedings of ACM Workshop on Embedded Systems for Energy-Efficient Buildings, pp. 1–8 (2013)

  • Kleiminger, W., Mattern, F., Santini, S.: Predicting household occupancy for smart heating control: a comparative performance analysis of state-of-the-art approaches. Energy Build. 85, 493–505 (2014)

    Article  Google Scholar 

  • Krumm, J., Bush, A.B.: Learning time-based presence probabilities. In: Proceedings of PerCom, pp. 79–96 (2011)

  • Lara, O.D., Labrador, M.A.: A survey on human activity recognition using wearable sensors. IEEE Commun. Surv. Tutor. 15(3), 1192–1209 (2013)

    Article  Google Scholar 

  • Lee, S., Ryu, G., Chon, Y., Ha, R., Cha, H.: Automatic standby power management using usage profiling and prediction. IEEE Trans. Hum.-Mach. Syst. 43(6), 535–46 (2013)

    Article  Google Scholar 

  • Li, J., Yang, L., Shum, H., Sexton, G., Tan, Y.: Intelligent home heating controller using fuzzy rule interpolation. In: UK Workshop on Computational Intelligence (2015)

  • Lopez, K.L., Gagne, C., Gardner, M.-A.: Demand-side management using deep learning for smart charging of electric vehicles. IEEE Trans. Smart Grid. 10(3), 2683–2691 (2019)

    Article  Google Scholar 

  • Lu, J., Sookoor, T., Srinivasan, V., Gao, G., Holben, B., Stankovic, J., Field, E., Whitehouse, K.: The smart thermostat: using occupancy sensors to save energy in homes. In: Proceedings of ACM Sensys, pp. 211–224 (2010)

  • Mamidi, S., Chang, Y.H., Maheswaran, R.: Improving building energy efficiency with a network of sensing, learning and prediction agents. Proc. AAMAS. 1, 45–52 (2012)

    Google Scholar 

  • Mellit, A., Tina, G.M., Kalogirou, S.A.: Fault detection and diagnosis methods for photovoltaic systems: A review. Renew. Sustain. Energy Rev. 91, 1–17 (2018)

    Article  Google Scholar 

  • Mozer, M.C., Vidmar, L., Dodier, R.H.: The neurothermostat: predictive optimal control of residential heating systems. In: Proceedings of NIPS, pp. 953–959 (1997)

  • Müller, M.E.: Can user models be learned at all? Inherent problems in machine learning for user modelling. Knowl. Eng. Rev. 19(1), 61–88 (2004)

    Article  Google Scholar 

  • Nacer, A., Marhic, B., Delahoche, L., Masson, J.: ALOS: Automatic learning of an occupancy schedule based on a new prediction model for a smart heating management system. Build. Environ. 142, 484–501 (2018)

    Article  Google Scholar 

  • Nguyen, T.A., Aiello, M.: Energy intelligent buildings based on user activity: a survey. Energy Build. 56, 244–257 (2013)

    Article  Google Scholar 

  • Ozkan, H.A.: A new real time home power management system. Energy Build. 97, 56–64 (2015)

    Article  Google Scholar 

  • Ozkan, H.A.: Appliance based control for home power management systems. Energy 114, 693–707 (2016)

    Article  Google Scholar 

  • Peffer, T., Pritoni, M., Meier, A., Aragon, C., Perry, D.: How people use thermostats in homes: a review. Build. Environ. 43(12), 2529–2541 (2011)

    Article  Google Scholar 

  • Prodhan, M.A., Whitehouse, K.: Hot water DJ: saving energy by pre-mixing hot water. In: Proceedings of ACM Workshop on Embedded Sensing Systems for Energy-Efficiency in Buildings, pp. 91–98 (2012)

  • Purarjomandlangrudi, A., Ghapanchi, A.H., Esmalifalak, M.: A data mining approach for fault diagnosis: an application of anomaly detection algorithm. Measurement 55, 343–352 (2014)

    Article  Google Scholar 

  • Rana, R., Kusy, B., Wall, J., Hu, W.: Novel activity classification and occupancy estimation methods for intelligent HVAC (heating, ventilation and air conditioning) systems. Energy 93(1), 245–255 (2015)

    Article  Google Scholar 

  • Roy, S., Mishra, K., Maulik, U., Basu, S.: A distributed multilabel classification approach towards mining appliance usage in smart homes. In: Proceedings of IEEE Calcutta Conference (2017)

  • Sandhu, J.S., Agogino, A.M., Agogino, A.K.: Wireless sensor networks for commercial lighting control: decision making with multi-agent systems. In: Proceedings of AAAI, pp. 131–140 (2004)

  • Scott, J., Brush, A.B., Krumm, J., Meyers, B., Hazas, M., Hodges, S., Villar, N.: PreHeat: controlling home heating using occupancy prediction. In: Proceedings of UbiCom, pp. 281–290 (2011)

  • Sethuraman, J.: A constructive definition of Dirichlet priors. Stat. Sinica. 4, 639–650 (1994)

    MathSciNet  MATH  Google Scholar 

  • Si, H., Saruwatari, S., Minami, M., Morikawa, H.: A ubiquitous power management system to balance energy savings and response time based on device-level usage prediction. Inf. Proc. 18, 147–163 (2010)

    Google Scholar 

  • Singhvi, V., Krause, A., Guestrin, C., Garrett Jr., J.H., Matthews, H.S.: Intelligent light control using sensor networks. In: Proceedings of ACM Sensys, pp. 218–229 (2005)

  • Tapia, E.M., Intille, S.S., Larson, K.: Activity recognition in the home using simple and ubiquitous sensors. In: Proceedings of Springer PerCom, pp. 158–175 (2004)

  • Tominaga, S., Shimosaka, M., Fukui, R., Sato, T.: A unified framework for modeling and predicting going-out behavior. In: Proceedings of PerCom, pp. 73–90 (2012)

  • Trasarti, R., Pinelli, F., Nanni, M., Giannotti, F.: Mining mobility user profiles for car pooling. In: Proceedings of ACM SIGKDD, pp. 1190–1198 (2011)

  • Truong, N.C., McInerney, J., Tran-Thanh, L., Costanza, E., Ramchurn, S.D.: Forecasting multi-appliance usage for smart home energy management. In: Proceedings of IJCAI, pp. 2908–2914 (2013)

  • Truong, N.C., Baarslag, T., Ramchurn, G., Tran-Thanh, L.: Interactive scheduling of appliance usage in the home. In: Proceedings of IJCAI (2016)

  • van der Ham, W., Klein, M., Tabatabaei, S.A., Thilakarathne, D.J., Treur, J.: Methods for a smart thermostat to estimate the characteristics of a house based on sensor data. Energy Proc. 95, 467–474 (2016)

    Article  Google Scholar 

  • Van Kasteren, T., Noulas, A., Englebienne, G., Kröse, B.: Accurate activity recognition in a home setting. In: Proceedings of ACM UbiComp, pp. 1–9 (2008)

  • Vázquez, F.I., Kastner, W.: Usage profiles for sustainable buildings. In: Proceedings of ETFA, pp. 1–8 (2010)

  • Vázquez, F.I., Kastner, W.: Clustering methods for occupancy prediction in smart home control. In: Proceedings od IEEE ISIE, pp. 1321–1328 (2011)

  • Ventä, O.: Intelligent products and systems: Technology theme-final report. Technical report, VTT Technical research centre of Finland (2007)

  • Wenninger, M., Schmidt, J., Goeller, T.: Appliance usage prediction for the smart home with an application to energy demand side management. And why accuracy is not a good performance metric for this problem. In: Proceedings of smartgreens, pp. 143–150 (2017)

  • Yan, R., Ma, Z., Kokogiannakis, G., Zhao, Y.: A sensor fault detection strategy for air handling units using cluster analysis. Autom. Constr. 70, 77–88 (2016)

    Article  Google Scholar 

Download references

Acknowledgements

The authors would like to recognise the financial support from Flanders Innovation and Entrepreneurship (VLAIO).

Author information

Authors and Affiliations

  1. Department of Mechanical Engineering, KU Leuven - Flanders Make, Celestijnenlaan 300, 3001, Leuven, Belgium

    Yannick De Bock, Andres Auquilla & Joost R. Duflou

  2. Department of Computer Science, University of Cuenca, Cuenca, Ecuador

    Andres Auquilla

  3. Computational Modeling Lab, Vrije Universiteit Brussel, Pleinlaan 2, Brussels, Belgium

    Ann Nowé

Authors
  1. Yannick De Bock
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Andres Auquilla
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Ann Nowé
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Joost R. Duflou
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Yannick De Bock.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

De Bock, Y., Auquilla, A., Nowé, A. et al. Nonparametric user activity modelling and prediction. User Model User-Adap Inter 30, 803–831 (2020). https://doi.org/10.1007/s11257-020-09259-3

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11257-020-09259-3

Keywords

Search

Navigation