Abstract
Detection of falls is very important from a health and safety perspective. However, falls occur rarely and infrequently, which leads to either limited or no training data and thus can severely impair the performance of supervised activity recognition algorithms. In this paper, we address the problem of identification of falls in the absence of training data for falls, but with abundant training data for normal activities. We propose two ‘X-Factor’ Hidden Markov Model (XHMMs) approaches that are like normal HMMs, but have “inflated” output covariances (observation models), which can be estimated using cross-validation on the set of ‘outliers’ in the normal data that serve as proxies for the (unseen) fall data. This allows the XHMMs to be learned from only normal activity data. We tested the proposed XHMM approaches on two real activity recognition datasets that show high detection rates for falls in the absence of training data.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Bao, L., Intille, S.S.: Activity recognition from user-annotated acceleration data. In: Ferscha, A., Mattern, F. (eds.) PERVASIVE 2004. LNCS, vol. 3001, pp. 1–17. Springer, Heidelberg (2004)
Bourke, A.K., Lyons, G.M.: A threshold-based fall-detection algorithm using a bi-axial gyroscope sensor. Medical Engineering and Physics 30(1), 84 (2008)
CDC: Falls in nursing homes (2014), http://www.cdc.gov/HomeandRecreationalSafety/Falls/nursing.html (accessed on January 19, 2014)
Cheng, H., Haiyong, L., Zhao, F.: A fall detection algorithm based on pattern recognition and human posture analysis. In: IET International Conference on Communication Technology and Application. pp. 853–857 (2011)
Dai, J., Bai, X., Yang, Z., Shen, Z., Xuan, D.: Perfalld: A pervasive fall detection system using mobile phones. In: Pervasive Computing and Communications Workshops, pp. 292–297. IEEE (2010)
Ermes, M., Parkka, J., Cluitmans, L.: Advancing from offline to online activity recognition with wearable sensors. In: 2008 30th Annual International Conference EMBS. pp. 4451–4454 (2008)
He, Z., Jin, L.: Activity recognition from acceleration data based on discrete consine transform and svm. In: SMC, pp. 5041–5044. IEEE (2009)
Honda, D., Sakata, N., Nishida, S.: Activity recognition for risk management with installed sensor in smart and cell phone. In: HCI (3), pp. 230–239 (2011)
Igual, R., Medrano, C., Plaza, I.: Challenges, issues and trends in fall detection systems. BioMedical Engineering OnLine 12(1), 1–24 (2013)
Khan, S.S., Karg, M.E., Hoey, J., Kulic, D.: Towards the detection of unusual temporal events during activities using hmms. In: SAGAWARE - Proceedings of the 2012 ACM Conference on Ubiquitous Computing, UbiComp 2012, pp. 1075–1084. ACM (2012)
Kubat, M., Matwin, S.: Addressing the curse of imbalanced training sets: one-sided selection. In: ICML, vol. 97, pp. 179–186 (1997)
Lühr, S., Venkatesh, S., West, G.A.W., Bui, H.H.: Explicit state duration HMM for abnormality detection in sequences of human activity. In: Zhang, C., Guesgen, H.W., Yeap, W.-K. (eds.) PRICAI 2004. LNCS (LNAI), vol. 3157, pp. 983–984. Springer, Heidelberg (2004)
Luo, X., Liu, T., Liu, J., Guo, X., Wang, G.: Design and implementation of a distributed fall detection system based on wireless sensor networks. EURASIP Journal on Wireless Communications and Networking 2012, 1–13 (2012)
MobileHelp: Fall button (2014), http://www.mobilehelpnow.com/products.php (accessed on September 12, 2014)
Nadales, M.J.V.: Recognition of Human Motion Related Activities from Sensors. Master’s thesis, University of Malaga and German Aerospace Cener (2010)
Philips: Lifeline (2014), http://www.lifelinesys.com/content/lifeline-products/auto-alert (accessed on September 12, 2014)
Quinn, J.A., Williams, C.K., McIntosh, N.: Factorial switching linear dynamical systems applied to physiological condition monitoring. IEEE Transactions on PAMI 31(9), 1537–1551 (2009)
Rabiner, L.: A tutorial on hidden markov models and selected applications in speech recognition. Proceedings of the IEEE 77(2), 257–286 (1989)
Shi, G., Zou, Y., Jin, Y., Cui, X., Li, W.J.: Towards hmm based human motion recognition using mems inertial sensors. In: ROBIO, pp. 1762–1766. IEEE (2008)
Thome, N., Miguet, S.: A hhmm-based approach for robust fall detection. In: ICARCV, pp. 1–8. IEEE (2006)
Tokumitsu, M., Murakami, M., Ishida, Y.: An adaptive sensor network for home intrusion detection by human activity profiling. Artificial Life and Robotics 16(1), 36–39 (2011)
Tong, L., Song, Q., Ge, Y., Liu, M.: Hmm-based human fall detection and prediction method using tri-axial accelerometer. IEEE Sensors Journal 13(5), 1849–1856 (2013)
Vavoulas, G., Pediaditis, M., Spanakis, E., Tsiknakis, M.: The mobifall dataset: An initial evaluation of fall detection algorithms using smartphones. In: 2013 IEEE 13th International Conference on Bioinformatics and Bioengineering (BIBE), pp. 1–4 (November 2013)
Yu, M., Naqvi, S., Rhuma, A., Chambers, J.: Fall detection in a smart room by using a fuzzy one class support vector machine and imperfect training data. In: ICASSP, pp. 1833–1836 (2011)
Zhang, T., Wang, J., Xu, L., Liu, P.: Fall detection by wearable sensor and one-class svm algorithm. In: Intelligent Computing in Signal Processing and Pattern Recognition, vol. 345, pp. 858–863. Springer, Heidelberg (2006)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Khan, S.S., Karg, M.E., Kulić, D., Hoey, J. (2014). X-Factor HMMs for Detecting Falls in the Absence of Fall-Specific Training Data. In: Pecchia, L., Chen, L.L., Nugent, C., Bravo, J. (eds) Ambient Assisted Living and Daily Activities. IWAAL 2014. Lecture Notes in Computer Science, vol 8868. Springer, Cham. https://doi.org/10.1007/978-3-319-13105-4_1
Download citation
DOI: https://doi.org/10.1007/978-3-319-13105-4_1
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-13104-7
Online ISBN: 978-3-319-13105-4
eBook Packages: Computer ScienceComputer Science (R0)