Abstract
Analysis of human behaviour for deducing health and well-being information is one of the contemporary challenges given the ageing in place. To this end, existing and newly developed machine learning methods are needed to be evaluated using annotated real-world data sets. However, the metrics used in performance evaluation are directly taken from the machine learning domain, and they do not necessarily consider the specific needs of human behaviour analysis such as recognizing the duration, start time and frequency of the activities. Moreover, the commonly used metrics such as accuracy or F-measure can be misleading in the presence of skewed class distributions as in the case of human behaviour recognition. In this study, we evaluate the performance of two machine learning methods, hidden Markov model and time windowed neural network on five different real-world data sets through human behaviour understanding for health assessment perspective. According to the experimental results, standard metrics fail to reveal the actual performance of the two compared machine learning methods in terms of behaviour recognition. On the other hand, the proposed evaluation mechanism which considers three different activity categories leads to a more realistic evaluation of the overall performance.
Similar content being viewed by others
References
Alemdar H, Ersoy C (2010) Wireless sensor networks for healthcare: a survey. Comput Netw 54(15):2688–2710
Alemdar H, Ertan H, Incel OD, Ersoy C (2013) ARAS human activity datasets in multiple homes with multiple residents. In: 7th International Conference on pervasive computing technologies for healthcare. Venice, Italy
Alvarez G, Ayas N (2004) The impact of daily sleep duration on health: a review of the literature. Prog Cardiovasc Nurs 19(2):56
Bamis A, Lymberopoulos D, Teixeira T, Savvides A (2010) The behaviorscope framework for enabling ambient assisted living. Pers Ubiquitous Comput 14(6):473–487
Cook DJ (2012) Learning setting-generalized activity models for smart spaces. IEEE Intell Syst 27(1):32–38
Gaddam A, Mukhopadhyay S, Gupta G (2011) Elder care based on cognitive sensor network. IEEE Sensors J 11(3):574–581
Gallissot M, Caelen J, Bonnefond N, Meillon B, Pons S (2011) Using the multicom domus dataset. Research Report RR-LIG-020, LIG, Grenoble, France
Gangwisch JE, Heymsfield SB, Boden-Albala B, Buijs RM, Kreier F, Pickering TG, Rundle AG, Zammit GK, Malaspina D (2006) Short sleep duration as a risk factor for hypertension: analyses of the first National Health and Nutrition Examination Survey. Hypertension 47(5):833–839
Ghasemzadeh H, Jafari R (2011) Physical movement monitoring using body sensor networks: a phonological approach to construct spatial decision trees. IEEE Trans Ind Inf 7(1):66–77
Gordon D, Czerny J, Beigl M (2014) Activity recognition for creatures of habit. Pers Ubiquitous Comput 18(1):205–221
Helal S, Mann W, El-Zabadani H, King J, Kaddoura Y, Jansen E (2005) The gator tech smart house: a programmable pervasive space. Computer 38(3):50–60
Hong X, Nugent CD (2013) Segmenting sensor data for activity monitoring in smart environments. Person Ubiquitous Comput 17(3):545–559
Hu J, Brown MK, Turin W (1996) Hmm based on-line handwriting recognition. IEEE Trans Pattern Anal Mach Intell 18(10):1039–1045
Intille SS, Larson K, Beaudin JS, Nawyn J, Tapia EM, Kaushik P (2005) A living laboratory for the design and evaluation of ubiquitous computing technologies. In: Extended abstracts of the 2005 conference on human factors in computing systems, ACM Press, pp 1941–1944
van Kasteren T, Englebienne G, Kröse B (2011) Human activity recognition from wireless sensor network data: benchmark and software. In: Activity recognition in pervasive intelligent environments, Springer, pp 165–186
van Kasteren T, Noulas A, Englebienne G, Kröse B (2008) Accurate activity recognition in a home setting. Proceedings of the 10th international conference on Ubiquitous computing, UbiComp ’08, pp 1–9 ACM, New York, NY, USA
Kientz JA, Patel SN, Jones B, Price E, Mynatt ED, Abowd GD (2008) The Georgia tech aware home. In: HI ’08 extended abstracts on human factors in computing systems
Kuo CH, Chen CT, Chen TS, Kuo YC (2011) A wireless sensor network approach for rehabilitation data collections. In: Proceedings of 2011 IEEE international conference on systems, man, and cybernetics (SMC), pp 579–584
Lasserre J, Bishop CM (2007) Generative or discriminative? Getting the best of both worlds. Bayesian Stat 8:3–24
Rabiner LR (1989) A tutorial on Hidden Markov models and selected applications in speech recognition. Proc IEEE 77(2):257–286
Salah AA, Gevers T, Sebe N, Vinciarelli A (2010) Challenges of human behavior understanding. Proceedings of the first international conference on human behavior understanding, HBU’10, Springer-Verlag, Berlin, Heidelberg, pp 1–12
Suryadevara N, Mukhopadhyay S (2012) Wireless sensor network based home monitoring system for wellness determination of elderly. IEEE Sens J 12(6):1965–1972
Tapia EM, Intille SS, Larson K (2004) Activity recognition in the home using simple and ubiquitous sensors. In: Proceedings of international conference on pervasive computing, pp 158–175
Waibel A, Hanazawa T, Hinton G, Shikano K, Lang KJ (1989) Phoneme recognition using time-delay neural networks. IEEE Trans Acoust Speech Signal Process 37(3):328–339
Ward J, Lukowicz P, Gellersen H (2011) Performance metrics for activity recognition. ACM Trans Inf Syst Technol (TIST) 2(1)
Acknowledgments
This work is supported by the Boğaziçi University Research Fund under the Grant Number 8684.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Alemdar, H., Tunca, C. & Ersoy, C. Daily life behaviour monitoring for health assessment using machine learning: bridging the gap between domains. Pers Ubiquit Comput 19, 303–315 (2015). https://doi.org/10.1007/s00779-014-0823-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00779-014-0823-y