Advertisement

Unsupervised Detection and Analysis of Changes in Everyday Physical Activity Data

  • Gina SprintEmail author
  • Diane J. Cook
  • Maureen Schmitter-Edgecombe
Chapter
Part of the Intelligent Systems Reference Library book series (ISRL, volume 137)

Abstract

Sensor-based time series data can be utilized to monitor changes in human behavior as a person makes a significant lifestyle change, such as progress toward a fitness goal. Recently, wearable sensors have increased in popularity as people aspire to be more conscientious of their physical health. Automatically detecting and tracking behavior changes from wearable sensor-collected physical activity data can provide a valuable monitoring and motivating tool. In this paper, we formalize the problem of unsupervised physical activity change detection and address the problem with our Physical Activity Change Detection (PACD) approach. PACD is a framework that detects changes between time periods, determines significance of the detected changes, and analyzes the nature of the changes. We compare the abilities of three change detection algorithms from the literature and one proposed algorithm to capture different types of changes as part of PACD. We illustrate and evaluate PACD on synthetic data and using Fitbit data collected from older adults who participated in a health intervention study. Results indicate PACD detects several changes in both datasets. The proposed change algorithms and analysis methods are useful data mining techniques for unsupervised, window-based change detection with potential to track users’ physical activity and motivate progress toward their health goals.

Keywords

Physical activity monitoring Wearable sensors Unsupervised learning Change point detection Data mining 

Notes

Acknowledgements

We wish to thank the Department of Psychology at Washington State University for their insights and help with data collection. This material is based upon work supported by the National Science Foundation under Grant No. 0900781.

References

  1. 1.
    Albregtsen, F., et al.: Statistical texture measures computed from gray level coocurrence matrices. Image processing laboratory, Department of informatics, university of oslo pp. 1–14. http://www.uio.no/studier/emner/matnat/ifi/INF4300/h08/undervisningsmateriale/glcm.pdf (2008)
  2. 2.
    Benjamini, Y., Hochberg, Y.: Controlling the false discovery rate: A practical and powerful approach to multiple testing. J. R. Stat. Soc. Series B (Methodological) 57(1):289–300. http://www.jstor.org/stable/2346101 (1995)
  3. 3.
    Caspersen, C.J., Powell, K.E., Christenson, G.M.: Physical activity, exercise, and physical fitness: Definitions and distinctions for health-related research. Public Health Rep 100(2):126–131. http://www.ncbi.nlm.nih.gov/pmc/articles/PMC1424733/ (1985)
  4. 4.
    Chen, L., Hoey, J., Nugent, C., Cook, D., Yu, Z.: Sensor-based activity recognition. IEEE Trans. Syst. Man Cybern. Part C Appl. Rev. 42(6), 790–808 (2012). doi: 10.1109/TSMCC.2012.2198883 CrossRefGoogle Scholar
  5. 5.
    Dawadi, P.N., Cook, D.J., Schmitter-Edgecombe M.: Modeling patterns of activities using activity curves. Pervasive and Mobile Computing. doi:  10.1016/j.pmcj.2015.09.007. http://www.sciencedirect.com/science/article/pii/S157411921500173X (2015)
  6. 6.
    Dobkin, B.H.: Wearable motion sensors to continuously measure real-world physical activities. Curr Opin Neurol 26(6):602–608, doi:  10.1097/WCO.0000000000000026. http://www.ncbi.nlm.nih.gov/pmc/articles/PMC4035103/ (2013)
  7. 7.
    Feuz, K., Cook, D., Rosasco, C., Robertson, K., Schmitter-Edgecombe, M.: Automated Detection of Activity Transitions for Prompting. IEEE Transactions on Human-Machine Systems 45(5), 575–585 (2015). doi: 10.1109/THMS.2014.2362529 CrossRefGoogle Scholar
  8. 8.
    Grubbs, F.E.: Procedures for detecting outlying observations in samples. Technometrics 11(1):1, doi:  10.2307/1266761. http://www.jstor.org/stable/1266761?origin=crossref (1969)
  9. 9.
    Hido, S., Id, T., Kashima, H., Kubo, H., Matsuzawa, H.: Unsupervised change analysis using supervised learning. In: Washio, T., Suzuki, E., Ting, K.M., Inokuchi, A. (eds.) Advances in Knowledge Discovery and Data Mining, no. 5012 in Lecture Notes in Computer Science, Springer Berlin Heidelberg, pp. 148–159. http://link.springer.com/chapter/10.1007/978-3-540-68125-0_15, doi:  10.1007/978-3-540-68125-0_15 (2008)
  10. 10.
    Hodge, V.J., Austin, J.: A survey of outlier detection methodologies. Artif. Intell. Rev. 22(2):85–126, doi:  10.1007/s10462-004-4304-y. http://link.springer.com/article/10.1007/s10462-004-4304-y (2004)
  11. 11.
    Hu, M., Zhou, S., Wei, J., Deng, Y., Qu, W.: Change-point detection in multivariate time-series data by recurrence plot. WSEAS Transactions on Computers 13:592–599. http://www.wseas.org/multimedia/journals/computers/2014/a305705-716.pdf (2014)
  12. 12.
    Javed, F., Farrugia, S., Colefax, M., Schindhelm, K.: Early warning of acute decompensation in heart failure patients using a noncontact measure of stability index. IEEE Trans. Biomed. Eng. 63(2), 438–448 (2016). doi: 10.1109/TBME.2015.2463283 CrossRefGoogle Scholar
  13. 13.
    Lally, P., Jaarsveld, C. van, Potts, H., Wardle, J.: How are habits formed: Modelling habit formation in the real world. Eur. J. Soc. Psychol. 40(6):998–1009, doi:  10.1002/ejsp.674. http://dx.doi.org/10.1002/ejsp.674 (2010)
  14. 14.
    Liu, S., Yamada, M., Collier, N., Sugiyama, M.: Change-point detection in time-series data by relative density-ratio estimation. Neural Networks 43:72–83, doi:  10.1016/j.neunet.2013.01.012. http://www.sciencedirect.com/science/article/pii/S0893608013000270 (2013)
  15. 15.
    Maimon, O., Rokach, L.: Data mining and knowledge discovery handbook. Springer, New York. http://www.books24x7.com/marc.asp?bookid=16218 (2005)
  16. 16.
    Merilahti, J., Petkoski-Hult, T., Ermes, M., Gils, M.v., Lahti, H., Ylinen, A., Autio, L., Hyvrinen, E., Hyttinen, J.: Evaluation of new concept for balance and gait analysis: Patients with neurological disease, elderly people and young people. Gerontechnology 7(2):164. http://www.gerontechnology.info/index.php/journal/article/viewFile/gt.2008.07.02.101.00/832 (2008)
  17. 17.
    Merilahti, J., Viramo, P., Korhonen, I.: Wearable monitoring of physical functioning and disability changes, circadian rhythms and sleep patterns in nursing home residents. IEEE J. Biomed. Health Inform. PP(99):1–1, doi:  10.1109/JBHI.2015.2420680 (2015)
  18. 18.
    Ng, W., Dash, M.: A change detector for mining frequent patterns over evolving data streams. IEEE International Conference on Systems, Man and Cybernetics, 2008. SMC 2008, pp. 2407–2412, doi:  10.1109/ICSMC.2008.4811655 (2008)
  19. 19.
    Paavilainen, P., Korhonen, I., Ltjnen, J., Cluitmans, L., Jylh, M., Srel, A., Partinen, M.: Circadian activity rhythm in demented and non-demented nursing-home residents measured by telemetric actigraphy. J. Sleep Res. 14(1), 61–68 (2005). doi: 10.1111/j.1365-2869.2004.00433.x CrossRefGoogle Scholar
  20. 20.
    Prince, S.A., Adamo, K.B., Hamel, M.E., Hardt, J., Gorber, S.C., Tremblay, M.: A comparison of direct versus self-report measures for assessing physical activity in adults: a systematic review. Int. J. Behav. Nutr. Phys. Act. 5:56, doi:  10.1186/1479-5868-5-56. http://dx.doi.org/10.1186/1479-5868-5-56 (2008)
  21. 21.
    Refinetti, R., Lissen, G.C., Halberg, F.: Procedures for numerical analysis of circadian rhythms. Biol. Rhythm. Res. 38(4):275–325, doi:  10.1080/09291010600903692. http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3663600/ (2007)
  22. 22.
    Tan, T.H., Gochoo, M., Chen, K.H., Jean, F.R., Chen, Y.F., Shih, F.J., Ho, C.F.: Indoor activity monitoring system for elderly using RFID and Fitbit Flex wristband. 2014 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI), pp. 41–44, doi:  10.1109/BHI.2014.6864299 (2014)
  23. 23.
    Tran, D.H., Gaber, M.M., Sattler, K.U.: Change detection in streaming data in the era of big data: Models and issues. SIGKDD Explor Newsl 16(1):30–38, DOI  10.1145/2674026.2674031. http://doi.acm.org/10.1145/2674026.2674031 (2014)
  24. 24.
    Tucker, P., Gilliland, J.: The effect of season and weather on physical activity: A systematic review. Public Health 121(12):909–922, doi:  10.1016/j.puhe.2007.04.009. http://www.sciencedirect.com/science/article/pii/S0033350607001400 (2007)
  25. 25.
  26. 26.
    Wang, S., Skubic, M., Zhu, Y.: Activity density map visualization and dissimilarity comparison for eldercare monitoring. IEEE Trans. Inf. Technol. Biomed. 16(4), 607–614 (2012). doi: 10.1109/TITB.2012.2196439 CrossRefGoogle Scholar
  27. 27.
    Xu, Y., Zhang, Z., Yu, P., Long, B.: Pattern change discovery between high dimensional data sets. In: Proceedings of the 20th ACM International Conference on Information and Knowledge Management, ACM, New York, NY, USA, CIKM ’11, pp. 1097–1106, DOI  10.1145/2063576.2063735. http://doi.acm.org/10.1145/2063576.2063735 (2011)
  28. 28.
    Yamada, M., Kimura, A., Naya, F., Sawada, H.: Change-point detection with feature selection in high-dimensional time-series data. In: Proceedings of the Twenty-Third International Joint Conference on Artificial Intelligence, AAAI Press, Beijing, China, IJCAI ’13, pp. 1827–1833. http://dl.acm.org/citation.cfm?id=2540128.2540390 (2013)

Copyright information

© Springer International Publishing AG 2018

Authors and Affiliations

  • Gina Sprint
    • 1
    Email author
  • Diane J. Cook
    • 2
  • Maureen Schmitter-Edgecombe
    • 2
  1. 1.Gonzaga UniversitySpokaneUSA
  2. 2.Washington State UniversityPullmanUSA

Personalised recommendations