Evaluation of Three State-of-the-Art Classifiers for Recognition of Activities of Daily Living from Smart Home Ambient Data

Tobias Nef, Prabitha Urwyler, Marcel Büchler, Ioannis Tarnanas, Reto Stucki, Dario Cazzoli, René Müri, Urs Mosimann, Tobias Nef, Prabitha Urwyler, Marcel Büchler, Ioannis Tarnanas, Reto Stucki, Dario Cazzoli, René Müri, Urs Mosimann

Abstract

Smart homes for the aging population have recently started attracting the attention of the research community. The "health state" of smart homes is comprised of many different levels; starting with the physical health of citizens, it also includes longer-term health norms and outcomes, as well as the arena of positive behavior changes. One of the problems of interest is to monitor the activities of daily living (ADL) of the elderly, aiming at their protection and well-being. For this purpose, we installed passive infrared (PIR) sensors to detect motion in a specific area inside a smart apartment and used them to collect a set of ADL. In a novel approach, we describe a technology that allows the ground truth collected in one smart home to train activity recognition systems for other smart homes. We asked the users to label all instances of all ADL only once and subsequently applied data mining techniques to cluster in-home sensor firings. Each cluster would therefore represent the instances of the same activity. Once the clusters were associated to their corresponding activities, our system was able to recognize future activities. To improve the activity recognition accuracy, our system preprocessed raw sensor data by identifying overlapping activities. To evaluate the recognition performance from a 200-day dataset, we implemented three different active learning classification algorithms and compared their performance: naive Bayesian (NB), support vector machine (SVM) and random forest (RF). Based on our results, the RF classifier recognized activities with an average specificity of 96.53%, a sensitivity of 68.49%, a precision of 74.41% and an F-measure of 71.33%, outperforming both the NB and SVM classifiers. Further clustering markedly improved the results of the RF classifier. An activity recognition system based on PIR sensors in conjunction with a clustering classification approach was able to detect ADL from datasets collected from different homes. Thus, our PIR-based smart home technology could improve care and provide valuable information to better understand the functioning of our societies, as well as to inform both individual and collective action in a smart city scenario.

Keywords: activities of daily living; ambient assisted living; data classification; data mining; healthcare technology; smart cities; smart homes.

Figures

Figure 1
Figure 1
Starting with the (reformatted) raw data, a clustering further preprocessed the data before the actual classification was performed. Finally, the computed result was displayed.
Figure 2
Figure 2
Additionally to the activities of daily living (ADL) classifier, a parallel visitor classifier was used. The results of the two classifiers were then merged.
Figure 3
Figure 3
A token was calculated based on all passive infrared (PIR) values. Whenever the token changed (inactive states of all motion sensors were neglected), a change point was set. Periods between two change points were then compressed.
Figure 4
Figure 4
To provide the classifier with contextual information about overlapping time periods, additional feature columns were introduced.
Figure 5
Figure 5
Distribution of PIR recordings during 24 h of measurements for one volunteer. The x-axis shows the time of the day and the y-axis the normalized number of PIR recordings.

References

    1. Gustavsson A., Jonsson L., Rapp T., Reynish E., Ousset P.J., Andrieu S., Cantet C., Winblad B., Vellas B., Wimo A. Differences in resource use and costs of dementia care between European countries: Baseline data from the ICTUS study. J. Nutr. Health Aging. 2010;14:648–654. doi: 10.1007/s12603-010-0311-7.
    1. Giebel C.M., Sutcliffe C., Challis D. Activities of daily living and quality of life across different stages of dementia: A UK study. Aging Ment. Health. 2014;19:63–71. doi: 10.1080/13607863.2014.915920.
    1. Lawton M.P., Brody E.M. Assessment of older people: Self-maintaining and instrumental activities of daily living. Gerontologist. 1969;9:179–186. doi: 10.1093/geront/9.3_Part_1.179.
    1. Katz S., Ford A.B., Moskowitz R.W., Jackson B.A., Jaffe M.W. Studies of Illness in the Aged. The index of ADL: A standardized measure of biological and psychosocial function. J. Am. Med. Assoc. 1963;185:914–919. doi: 10.1001/jama.1963.03060120024016.
    1. Mioshi E., Kipps C.M., Dawson K., Mitchell J., Graham A., Hodges J.R. Activities of daily living in frontotemporal dementia and Alzheimer disease. Neurology. 2007;68:2077–2084. doi: 10.1212/01.wnl.0000264897.13722.53.
    1. Sikkes S.A., Visser P.J., Knol D.L., de Lange-de Klerk E.S., Tsolaki M., Frisoni G.B., Nobili F., Spiru L., Rigaud A.S., Frolich L. Do instrumental activities of daily living predict dementia at 1- and 2-year follow-up? Findings from the Development of Screening guidelines and diagnostic Criteria for Predementia Alzheimer’s disease study. J. Am. Geriatr. Soc. 2011;59:2273–2281. doi: 10.1111/j.1532-5415.2011.03732.x.
    1. Logsdon R.G., Gibbons L.E., McCurry S.M., Teri L. Quality of life in Alzheimer’s disease: Patient and caregiver reports. J. Ment. Health Aging. 1999;5:21–32.
    1. Takechi H., Kokuryu A., Kubota T., Yamada H. Relative Preservation of Advanced Activities in Daily Living among Patients with Mild-to-Moderate Dementia in the Community and Overview of Support Provided by Family Caregivers. Int. J. Alzheimer’s Dis. 2012;2012 doi: 10.1155/2012/418289.
    1. Fleury A., Vacher M., Noury N. SVM-based multimodal classification of activities of daily living in health smart homes. Inf. Technol. Biomed. 2010;14:274–283. doi: 10.1109/TITB.2009.2037317.
    1. Fleury N., Noury N., Vacher M. Introducing knowledge in the process of supervised classification of activities of Daily Living in Health Smart Homes; Proceedings of the e-Health Networking Applications and Services (Healthcom 2010); Lyon, France. 1–3 July 2010; pp. 322–329.
    1. Ordonez F.J., de Toledo P., Sanchis A. Activity recognition using hybrid generative/discriminative models on home environments using binary sensors. Sensors. 2013;13:5460–5477. doi: 10.3390/s130505460.
    1. Peetoom K.K., Lexis M.A., Joore M., Dirksen C.D., de Witte L.P. Literature review on monitoring technologies and their outcomes in independently living elderly people. Disabil. Rehabil. Assist. Technol. 2014;10:271–294. doi: 10.3109/17483107.2014.961179.
    1. Van Kasteren T.L.M., Englebienne G., Kröse B.J.A. An activity monitoring system for elderly care using generative and discriminative models. Pers. Ubiquit. Comput. 2010;14:489–498. doi: 10.1007/s00779-009-0277-9.
    1. Van Kasteren T.L.M., Englebienne G., Kröse B.J.A. Activity recognition using semi-Markov models on real world smart home datasets. J. Ambient Intell. Smart Environ. 2010;2:311–325.
    1. Hodges N.L., Kirsch M., Newman W., Pollack M.E. Automatic assessment of cognitive impairment through electronic observation of object usage; Proceedings of the 8th International Conference, Pervasive 2010; Helsinki, Finland. 17–20 May 2010; pp. 192–209.
    1. Wu P., Peng J., Zhu J., Zhang Y. Senscare: Semi-automatic activity summarization system for elderly care; Proceedings of the Third International Conference, MobiCASE 2011; Los Angeles, CA, USA. 24–27 October 2011; pp. 1–19.
    1. Zhang Y., McClean B., Scotney P., Chaurasia I., Nugent C. Using duration to learn activities of daily living in a smart home environment; Proceedings of the 2010 4th International Conference on Pervasive Computing Technologies for Healthcare (PervasiveHealth); Munich, Germany. 22–25 March 2010; pp. 1–8.
    1. Van Kasteren T.L.M., Englebienne G., Kröse B.J.A. Transferring Knowledge of Activity Recognition across Sensor Networks. In: Floréen P., Krüger A., Spasojevic M., editors. Pervasive 2010, LNCS 6030. Springer-Verlag; Berlin/Heidelberg, Germany: 2010. pp. 283–300.
    1. Zhang H., Wang B., Black N. Human activity detection in smart home environment with self-adaptive neural networks; Proceedings of the International Conference on Networking, Sensing and Control; Hainan, China. 6–8 April 2008; pp. 1505–1510.
    1. Jalal A., Kamal S. Real-time life logging via a depth silhouette-based human activity recognition system for smart home services; Proceedings of the 11th IEEE International Conference on Advanced Video and Signal-Based Surveillance; Seoul, Korea. 26–29 August 2014; pp. 74–80.
    1. Jalal A., Kamal S., Kim D. Depth map-based human activity tracking and recognition using body joints features and self-organized map; Proceedings of the IEEE International Conference on Computing, Communication and Networking Technologies; Hefei, China. 11–13 July 2014; pp. 1–6.
    1. Jalal A., Sharif N., Kim J.T., Kim T.S. Human activity recognition via recognized body parts of human depth silhouettes for residents monitoring services at smart homes. Indoor Built Environ. 2013;22:271–279. doi: 10.1177/1420326X12469714.
    1. Maki H., Ogawa S., Matsuoka Y., Yonezawa K., Caldwell W.M. A daily living activity remote monitoring system for solitary older people; Proceedings of the Annual International Conference of the Engineering in Medicine and Biology Society; Boston, MA, USA. 30 August–3 September 2011; pp. 5608–5611.
    1. Mosabbeb E.A., Raahemifar K., Fathy M. Multi-View Human activity recognition in distributed camera sensor networks. Sensors. 2013;13:8750–8770. doi: 10.3390/s130708750.
    1. Xu X., Tang J., Zhang X., Liu X., Zhang H., Qiu Y. Exploring techniques for vision based human activity recognition: Methods, system, and evaluation. Sensors. 2013;13:1635–1650. doi: 10.3390/s130201635.
    1. Medjahed H. A pervasive multi-sensor data fusion for smart home healthcare monitoring; Proceedings of the IEEE International Conference on Fuzzy Systems; Beijing, China. 6–11 July 2014; pp. 1466–1473.
    1. Stucki R.A., Mosimann U.P., Müri R., Nef T. Non-Intrusive Recognition of Activities of Daily Living in the Homes of Alzheimer Patients. In: Ecarnação P., Azevedo L., Gelderbom G.J., Newell A., Mathiassen N.-E., editors. Assistive Technology: From Research to Practice. IOS Press; Leiden, The Netherlands: 2013. pp. 71–76.
    1. Stucki R.A., Urwyler P., Rampa L., Muri R., Mosimann U.P., Nef T. A. web-based non-intrusive ambient system to measure and classify activities of daily living. J. Med. Internet Res. 2014;16 doi: 10.2196/jmir.3465.
    1. Witten I.H., Frank E., Hall M.A. Data Mining: Practical Machine Learning Tools and Techniques. 3rd ed. Morgan Kaufmann; Burlington, MA, USA: 2011.
    1. Bayes T., Price R. An Essay towards Solving a Problem in the Doctrine of Chances. By the Late Rev. Mr. Bayes, F.R.S. Communicated by Mr. Price, in a Letter to John Canton, A.M.F.R.S. Philos. Trans. 1763;53:370–418. doi: 10.1098/rstl.1763.0053.
    1. Cortes C., Vapnik V. Support-vector networks. Mach. Learn. 1995;20:273–297.
    1. Breiman L. Random forests. Mach. Learn. 2001;45:5–32. doi: 10.1023/A:1010933404324.
    1. Van Kasteren T.L.M., Englebienne G., Kröse B.J.A. Human Activity Recognition from Wireless Sensor Network Data: Benchmark and Software. In: Chen L., Nugent C.D., Biswas J., Hoey J., editors. Activity Recognition in Pervasive Intelligent Environments. Atlantis Press; Amsterdam, The Netherlands: 2011. pp. 165–186.
    1. Japkowicz N., Stephen S. The class imbalance problem: A systematic study. Intell. Data Anal. 2002;6:429–449.
    1. Van Kasteren T.L.M., Alemdar H., Ersoy C. Effective performance metrics for evaluating activity recognition methods; Proceedings of the ARCS 2011—24th International Conference on Architecture of Computing Systems; Comot, Italy. 24–25 February 2011; p. 10.
    1. Berthold M.R., Cebron N., Dill F., Gabriel T.R., Kötter T., Meinl T., Ohl P., Sieb C., Thiel K., Wiswedel B. Studies in Classification, Data Analysis, and Knowledge Organization (GfKL 2007) Springer-Verlag; Heidelberg-Berlin, Germany: 2007. KNIME: The Konstanz Information Miner.
    1. Hall M., Frank E., Holmes G., Pfahringer B., Reutemann P., Witten I.H. The WEKA Data Mining Software: An Update. SIGKDD Explor. 2009;11:10–18. doi: 10.1145/1656274.1656278.
    1. Maroco J., Silva D., Rodrigues A., Guerreiro M., Santana I., de Mendonça A. Data mining methods in the prediction of dementia: A real-data comparison of the accuracy, sensitivity and specificity of linear discriminant analysis, logistic regression, neural networks, support vector machines, classification trees and random forests. BMC Res. Notes. 2011;4 doi: 10.1186/1756-0500-4-299.
    1. Chen C., Liaw A., Breiman L. Using Random Forest to Learn Imbalanced Data. University of California; Berkeley, CA, USA: 2004.

Source: PubMed

Sponsorzy i współpracownicy

Warunki medyczne

Interwencje lekowe

3
Subskrybuj