Human activity recognition has seen an enormous success in the last decade performing a dominant part in the field of ubiquitous computing. This rising demand can be attributed to several real life applications fundamentally dealing with human-centric applications like healthcare and eldercare systems. Many research experiments with data mining and machine learning procedures have been experiencing precisely to recognize human activities for healthcare systems. This work proposes a hybrid method to recognize the patient actions under care using a simple camera instead of multiple expensive sensors using machine learning with LBPTOP algorithm and body joint features with majority voting framework for real time monitoring applications with greater efficiency of recognition. This work uses different classifiers to achieve the experimental results approximately above 90% which clearly shows a remarkable recognition achievement compared to the other activity recognition techniques.

Machine Learning, Human activity, Body joint features, Real time, LBP-TOP, Classifiers

[1]. Katz S, Ford AB, Moskowitz RW, Jackson BA, Jaffe MW: Studies of illness in the aged. The index of ADL: A Standardized Measure of Biological and Psychological Function: JAMA 1963; 185:914–919.
[2]. Chan M, Esteve D, Escriba C, Campo E: A review of smart homes-Present state and future challenges: Comput Methods Programs Biomed 2008;91:51–81.
[3]. Tarricone R, Tsouros AD: The solid facts: home care in Europe: World Health Organization (WHO), Geneva, 2008.
[4]. Lai JHK, Yik FWH: Perceived importance of the quality of the indoor environment in commercial buildings: Indoor Built Environ 2007;16(4):311–321.
[5]. Aylward C, Harris RS, Harrison PTC: Analysis of topics and trends in indoor environment research in Europe: Studies in Indoor Monitoring: Indoor Built Environ 2005;14(3-4):197–200.
[6]. A. Yilmaz and M. Shah, “Actions sketch: a novel action representation,” in Proc. Comput. Vis. Pattern Recognit., 2005, vol. 1, pp. 984–989.
[7]. L. Gorelick, M. Blank, E. Shechtman, M. Irani, and R. Basri, “Actions as space-time shapes,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 29, no. 12, pp. 2247–2253, Dec. 2007.
[8]. D.-Y. Chen, H.-Y. M. Liao, and S.-W. Shih, “Humnn action recognition using 2-D spatio-temporal templates,” in Proc. Int. Conf. MultimediaExpo, 2007, pp. 667–670.
[9]. A. Bobick and J. Davis, “The recognition of human movement using temporal templates,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 23, no. 3, pp. 257–267, Mar. 2001.
[10]. M. Hu, “Visual pattern recognition by moment invariants,” IRE Trans. Inf. Theory, vol. 8, no. 2, pp. 179–187, Feb. 1962.
[11]. H. Meng, N. Pears, and C. Bailey, “A human action recognition system for embedded computer vision application,” in Proc. Comput. Vis. Pattern Recognit., 2007, pp. 1–8.
[12]. H. Fujiyoshi and A. Lipton, “Real-time human motion analysis by image skeletonization,” in Proc. 4th IEEE Workshop Appl. Comput. Vis., 1998, pp. 15–21.
[13]. M. Blank, L. Gorelick, E. Shechtman, M. Irani, and R. Basri, “Actions as space-time shapes,” in Proc. Int. Conf. Comput. Vis., 2005, pp. 1395–1402.
[14]. L.Wang and D. Suter, “Learning and matching of dynamic shape manifolds for human action recognition,” IEEE Trans. Image Process., vol. 16, no. 6, pp. 1646–1661, Jun. 2007.
[15]. Vapnik, V. Statistical learning theory (Adaptive and Learning Systems for Signal Processing, Communications and Control Series). John Wiley & Sons, New York (1998).
[16]. Larose, D. T. KNN. In: Discovering Knowledge in Data: An Introduction to Data Mining, 1st Ed., pp. 90-106. New Jersey; Wiley Interscience (2004).
[17]. Han, J., Kamber, M. Data Mining: Concepts and Techniques. Morgan Kaufmann (2006).
[18]. Larose, D. T. Decision Trees. In: Discovering Knowledge in Data: An Introduction to Data Mining, 1st Ed., pp. 108-126. New Jersey; Wiley Interscience (2004).
[19]. Lepetit V, Fua P (2006) Keypoint recognition using randomized trees. IEEE Trans Pattern Anal Mach Intell28:1465–1479
[20]. Baum E, Eagon J (1967) An inequality with applications to statistical estimation for probabilistic functions of Markov processes and to a model for ecology. Bull Am Math Soc 73:360–363
[21]. Lawrence R, Rabiner A (1989) Tutorial on hidden Markov models and selected applications in speech recognition. Proc IEEE 77(2):257–286
[22]. Nishimura Hand TsutsumiM (2001) Off-line hand-written character recognition using integrated1DHMMsbased on feature extraction filters. Sixth International Conference on Document Analysis and Recognition, p 417–421
[23]. Uddin, M.Z. (2017) Human activity recognition using segmented body part and body joint features with hidden Markov models. Multimed Tools Appl 76:13585–13614 DOI 10.1007/s11042-016-3742-2.