Download PDF
Methods Inf Med 2015; 54(03): 262-270
DOI: 10.3414/ME14-01-0061
Original Articles
Schattauer GmbH

A Time Series Based Sequence Prediction Algorithm to Detect Activities of Daily Living in Smart Home

M. Marufuzzaman
1   Department of Electrical, Electronic and Systems Engineering, Faculty of Engineering and Built Environment, Universiti Kebangsaan, Bangi, Selangor, Malaysia
,
M. B. I. Reaz
1   Department of Electrical, Electronic and Systems Engineering, Faculty of Engineering and Built Environment, Universiti Kebangsaan, Bangi, Selangor, Malaysia
,
M. A. M. Ali
1   Department of Electrical, Electronic and Systems Engineering, Faculty of Engineering and Built Environment, Universiti Kebangsaan, Bangi, Selangor, Malaysia
,
L. F. Rahman
1   Department of Electrical, Electronic and Systems Engineering, Faculty of Engineering and Built Environment, Universiti Kebangsaan, Bangi, Selangor, Malaysia
› Author Affiliations
Further Information

Publication History

received: 07 June 2014

accepted: 07 January 2015

Publication Date:
22 January 2018 (online)

    Permissions and Reprints

Summary

Objectives: The goal of smart homes is to create an intelligent environment adapting the inhabitants need and assisting the person who needs special care and safety in their daily life. This can be reached by collecting the ADL (activities of daily living) data and further analysis within existing computing elements. In this research, a very recent algorithm named sequence prediction via enhanced episode discovery (SPEED) is modified and in order to improve accuracy time component is included.

Methods: The modified SPEED or M-SPEED is a sequence prediction algorithm, which modified the previous SPEED algorithm by using time duration of appliance’s ON-OFF states to decide the next state. M-SPEED discovered periodic episodes of inhabitant behavior, trained it with learned episodes, and made decisions based on the obtained knowledge.

Results: The results showed that M-SPEED achieves 96.8% prediction accuracy, which is better than other time prediction algorithms like PUBS, ALZ with temporal rules and the previous SPEED.

Conclusions: Since human behavior shows natural temporal patterns, duration times can be used to predict future events more accurately. This inhabitant activity prediction system will certainly improve the smart homes by ensuring safety and better care for elderly and handicapped people.

Keywords

M-SPEED - sequence prediction - ADL - machine learning - smart home
 

  • References

  • 1 Tordrup D, Bertollini R. Research Agenda for Health Economic Evaluation. 2013
    Google Scholar
  • 2 Jakkula V, Cook DJ. Anomaly detection using temporal data mining in a smart home environment. Methods Inf Med 2008; 47 (01) 70-75.
    Article in Thieme ConnectPubMedGoogle Scholar
  • 3 Vainio A-M, Valtonen M, Vanhala J. Proactive Fuzzy Control and Adaptation Methods for Smart Homes. IEEE Intelligent Systems 2008; 23 (02) 42-49.
    PubMedGoogle Scholar
  • 4 Das SK, Cook DJ Battacharya, Heierman III EO, Lin T-Y. The role of prediction algorithms in the MavHome smart home architecture. IEEE Wireless Communications 2002; 9 (06) 77-84.
    CrossrefPubMedGoogle Scholar
  • 5 Marufuzzaman M, Reaz MBI, Islam MT. FPGA based Distributed Task Organizing Agents in Smart Home. Proc. of the 2nd International Conference on Research in Science, Engineering and Technology (ICRSET’2014), Dubai, March 21–22. 2014: 1-5.
    Google Scholar
  • 6 Marufuzzaman M, Reaz MBI, Ali MAM, Rahman LF. Classification and Detection of Intelligent House Resident Activities using Multiagent. Proc. of the 4th International Conference on Computing and Informatics. Sarwak: Aug 28–29. 2013: 195-200.
    Google Scholar
  • 7 Marufuzzaman M. Reaz MBI. Hardware Simulation of Pattern Matching and Reinforcement Learning to Predict the User next Action of Smart Home Device Usage. World Applied Sciences Journal 2013; 22 (09) 1302-1309.
    PubMedGoogle Scholar
  • 8 Alam MR, Reaz MBI, Ali MAM. SPEED: An Inhabitant Activity Prediction Algorithm for Smart Homes, IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans. 2012; 42 (04) 985-990.
    PubMedGoogle Scholar
  • 9 Gopalratnam K, Cook DJ. Online sequential prediction via incremental parsing: The active LeZi algorithm. IEEE Intelligent Systems 2007; 22 (01) 52-58.
    PubMedGoogle Scholar
  • 10 Bhattacharya Das SK. LeZi-update: An information-theoretic framework for personal mobility tracking in PCS networks. Wireless Networks 2002; 8 2/3 121-135.
    CrossrefPubMedGoogle Scholar
  • 11 Zhang LS, Yang MJ, Lei DJ. An Improved PAM Clustering Algorithm Based on Initial Clustering Centers. Applied Mechanics and Materials. 2012: 135-136 244–249.
    Google Scholar
  • 12 Venkatesh A. Smart Home Concepts: Current Trends, Center for Research on Information Technology and Organizations I.T. in the Home. University of California; Irvine: Year 2003. Paper 377.
    Google Scholar
  • 13 Jakkula V, Cook DJ. Mining Sensor Data in Smart Environment for Temporal Activity Prediction. Poster session of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining Workshop on Knowledge Discovery from Sensor Data (sensor-KDD 2007) San Jose, August 12. 2007
    Google Scholar
  • 14 Rao SP, Cook DJ. Predicting Inhabitant Action and Task Models with Application to Smart Homes. International Journal on Artificial Intelligence Tools 2004; 13 (01) 81-99.
    CrossrefPubMedGoogle Scholar
  • 15 Aztiria A, Augusto JC, Basagoiti R, Izaguirre A, Cook DJ. Discovering frequent user-environment interactions in intelligent environments. Personal Ubiquitous Computer 2012; 16 (01) 91-103.
    PubMedGoogle Scholar
  • 16 Nazerfard E, Cook D.J. CRAFFT: an activity prediction model based on Bayesian networks. Journal of Ambient Intelligence and Humanized Computing. 2014. Available http://dx.doi.org/10.1007/s12652-014-0219-x.
    CrossrefGoogle Scholar
  • 17 Smart Home Datasets. Washington State University [Online]. Available. http://ailab.eecs.wsu.edu/casas/datasets.html.
    PubMedGoogle Scholar