Multimedia Tools and Applications

, Volume 74, Issue 20, pp 8861–8878 | Cite as

Direct optimization of inference model for human activity and posture class recognition

  • Mi-Hwa Song
  • Young-Ho LeeEmail author


The demand for ambulatory monitoring is rising due to the widespread adoption of home-based healthcare models for the increasing elderly population. Since monitoring patients makes it possible to provide remote medical services based on real-world contexts, context-aware technology is regarded as a crucial element in core module development for ubiquitous healthcare solutions. This paper describes the design and implementation of a class label tagging system for human activity recognition based on sensor data from a single tri-axial accelerometer attached to the waist of a human subject. Our human activity and posture classifier (APC) was designed to model more effectively an event that takes place over a period of time. Consequently, the APC problem becomes the process of tagging class labels onto sequential data from a single tri-axial accelerometer. This sequential tagging naturally led to our hypothesis that a linear combination of the classification model and the prior, approximated by observing a state transition event of human activity and posture (AP), may decrease the error rate of the system. Therefore, this paper aims at testing the aforementioned experimental hypothesis while explicating our method of direct optimization, also known as direct loss minimization. Our experimental hypothesis is based on the view that the task of labeling a series of class tags on a data object of the AP event should be supported by a statistical model capable of robustly capturing the probabilistic context influencing the generation of a set of features at a given discrete time. A radial basis function network algorithm was used for parameter estimation of a class likelihood inference model augmented by training a state transition model to capture the sequential nature of a posture or activity generation event. The linear combination requires our design step to have a further optimization, in addition to learning the parameters of each inference model, of the model parameters that represent the relative contribution to the decision process. Previous studies have elaborated on an effective approach to direct optimization of model parameters when an appropriate evaluation metric exists for a given problem domain. In our case, f-measure was used as an objective function of the direct optimization. We used local beam search to optimize directly the weight vector for the likelihood and the prior. Our method is tested on the set of nine-dimensional feature vectors contained in 69,376 lines of sequential AP data. The experiment shows that embedding prior probability into the recognition process decreases the error rate in a set of categories. Several experiments proved the efficiency of our proposed method and the usefulness of the system.


Tri-axial accelerometer State transition model Activity recognition Radial basis function networks Direct loss minimization 



This work was supported by the Gachon University Research Fund of 2013 (GCU-2013-R116)


  1. 1.
    Alpaydin E (2004) Introduction to machine learning: MIT pressGoogle Scholar
  2. 2.
    Bao L, Intille S (2004) Activity recognition from user-annotated acceleration data, Pervasive Computing, 2004, pp. 1–17Google Scholar
  3. 3.
    Cer D, Jurafsky D, Manning CD (2008) Regularization and search for minimum error rate training, in Proceedings of the Third Workshop on Statistical Machine Translation, 2008, pp. 26–34Google Scholar
  4. 4.
    DeVaul RW, Dunn S (2001) Real-time motion classification for wearable computing applications, project paper, . mit. edu/wearables/mithril/realtime. pdf, 2001
  5. 5.
    Duong TV, Bui HH, Phung DQ, Venkatesh S (2005) Activity recognition and abnormality detection with the switching hidden semi-markov model, in Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on, 2005, pp. 838–845Google Scholar
  6. 6.
    Ermes M, Parkka J, Mantyjarvi J, Korhonen I (2008) Detection of daily activities and sports with wearable sensors in controlled and uncontrolled conditions. Inf Technol Biomed IEEE Trans 12:20–26CrossRefGoogle Scholar
  7. 7.
    Galley M, Quirk C (2011) Optimal search for minimum error rate training, in Proceedings of the Conference on Empirical Methods in Natural Language Processing pp. 38–49Google Scholar
  8. 8.
    Győrbíró N, Fábián Á, Hományi G (2009) An activity recognition system for mobile phones. Mob Netw Appl 14:82–91CrossRefGoogle Scholar
  9. 9.
    He Z, Jin L (2009) Activity recognition from acceleration data based on discrete consine transform and SVM, in Systems, Man and Cybernetics, 2009. SMC 2009. IEEE International Conference on, 2009, pp. 5041–5044Google Scholar
  10. 10.
    Helaoui R, Niepert M, Stuckenschmidt H (2011) Recognizing interleaved and concurrent activities: A statistical-relational approach, in Pervasive Computing and Communications (PerCom), 2011 I.E. International Conference on, pp. 1–9Google Scholar
  11. 11.
    Jelinek F (1998) Statistical methods for speech recognition: MIT pressGoogle Scholar
  12. 12.
    Karaman S, Benois-Pineau J, Dovgalecs V, Mégret R, Pinquier J, André-Obrecht R, Gaëstel Y, Dartigues, J-F (2011) Hierarchical hidden Markov model in detecting activities of daily living in wearable videos for studies of dementia, Multimedia tools and applications, pp. 1–29Google Scholar
  13. 13.
    Karantonis DM, Narayanan MR, Mathie M, Lovell NH, Celler BG (2006) Implementation of a real-time human movement classifier using a triaxial accelerometer for ambulatory monitoring. Inf Technol Biomed IEEE Trans 10:156–167CrossRefGoogle Scholar
  14. 14.
    Khan AM, Lee Y-K, Lee SY, Kim T-S (2010) A triaxial accelerometer-based physical-activity recognition via augmented-signal features and a hierarchical recognizer. Inf Technol Biomed IEEE Trans 14:1166–1172CrossRefGoogle Scholar
  15. 15.
    Kirtley C, Smith R (2001) Application of multimedia to the study of human movement. Multimed Tools Appl 14:259–268zbMATHCrossRefGoogle Scholar
  16. 16.
    Kneser R, Ney H (1995) Improved backing-off for m-gram language modeling, in Acoustics, Speech, and Signal Processing, 1995. ICASSP-95., 1995 International Conference on, 1995, pp. 181–184Google Scholar
  17. 17.
    Lukowicz, P, Ward J, Junker H, Stäger M, Tröster G, Atrash A, Starner, T (2004) Recognizing workshop activity using body worn microphones and accelerometers, Pervasive Computing,pp. 18–32Google Scholar
  18. 18.
    Mathie M, Celler B, Lovell N, Coster AC (2004) Classification of basic daily movements using a triaxial accelerometer. Med Biol Eng Comput 42:679–687CrossRefGoogle Scholar
  19. 19.
    Mathie MJ, Coster AC, Lovell NH, Celler BG, Lord SR, Tiedemann A (2004) A pilot study of long-term monitoring of human movements in the home using accelerometry. J Telemedicine Telecare 10:144–151CrossRefGoogle Scholar
  20. 20.
    Maurer U, Rowe A, Smailagic A, Siewiorek D (2006) Location and activity recognition using eWatch: A wearable sensor platform, Ambient Intelligence in Everyday Life, pp. 86–102Google Scholar
  21. 21.
    Maurer U, Smailagic A Siewiorek, DP, Deisher M (2006) Activity recognition and monitoring using multiple sensors on different body positions, in Wearable and Implantable Body Sensor Networks, 2006. BSN 2006. International Workshop on, 2006, pp. 4 pp.-116Google Scholar
  22. 22.
    Modayil J, Bai T, Kautz H (2008) Improving the recognition of interleaved activities, in Proceedings of the 10th international conference on Ubiquitous computing, pp. 40–43Google Scholar
  23. 23.
    Moody J, Darken CJ (1989) Fast learning in networks of locally-tuned processing units. Neural Comput 1:281–294CrossRefGoogle Scholar
  24. 24.
    Och FJ (2003) Minimum error rate training in statistical machine translation, in Proceedings of the 41st Annual Meeting on Association for Computational Linguistics-Volume 1, 2003, pp. 160–167Google Scholar
  25. 25.
    Olguın DO, Pentland AS (2006) Human activity recognition: Accuracy across common locations for wearable sensorsGoogle Scholar
  26. 26.
    Patterson DJ, Fox D, Kautz H, Philipose, M (2005) Fine-grained activity recognition by aggregating abstract object usage, in Wearable Computers, 2005. Proceedings. Ninth IEEE International Symposium on, pp. 44–51Google Scholar
  27. 27.
    Pober DM, Staudenmayer J, Raphael C, Freedson PS (2006) Development of novel techniques to classify physical activity mode using accelerometers. Med Sci Sports Exerc 38:1626CrossRefGoogle Scholar
  28. 28.
    Pogorelc B, Bosnić Z, Gams M (2012) Automatic recognition of gait-related health problems in the elderly using machine learning. Multimed Tools Appl 58:333–354CrossRefGoogle Scholar
  29. 29.
    Ravi N, Dandekar N, Mysore P, Littman ML (2005) Activity recognition from accelerometer data, in Proceedings of the national conference on artificial intelligence p. 1541Google Scholar
  30. 30.
    Rousseeuw PJ (1987) Silhouettes: a graphical aid to the interpretation and validation of cluster analysis. J Comput Appl Math 20:53–65zbMATHCrossRefGoogle Scholar
  31. 31.
    Simon C, Meessen J, De Vleeschouwer C (2010) Visual event recognition using decision trees. Multimed Tools Appl 50:95–121CrossRefGoogle Scholar
  32. 32.
    Song S-k, Jang J, Park S (2008) A phone for human activity recognition using triaxial acceleration sensor, in Consumer Electronics, 2008. ICCE 2008. Digest of Technical Papers. International Conference on, 2008, pp. 1–2Google Scholar
  33. 33.
    Van Kasteren T, Noulas A, Englebienne G, Kröse B (2008) Accurate activity recognition in a home setting, in Proceedings of the 10th international conference on Ubiquitous computing, 2008, pp. 1–9Google Scholar
  34. 34.
    Veltink PH, Bussmann H, de Vries W, Martens W, Van Lummel RC (1996) Detection of static and dynamic activities using uniaxial accelerometers. Rehabil Eng IEEE Trans 4:375–385CrossRefGoogle Scholar
  35. 35.
    Yang J-Y, Chen Y-P, Lee G-Y, Liou S-N, Wang J-S (2007)Activity recognition using one triaxial accelerometer: A neuro-fuzzy classifier with feature reduction, Entertainment Computing–ICEC 2007, pp. 395–400Google Scholar
  36. 36.
    Yang J-Y, Wang J-S, Chen Y-P (2008) Using acceleration measurements for activity recognition: an effective learning algorithm for constructing neural classifiers. Pattern Recognition Lett 29:2213–2220CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2013

Authors and Affiliations

  1. 1.Department of Information & Communication SystemSemyung UniversityJecheonKorea
  2. 2.Department of Computer Information TechnologyGachon UniversityYeonsu-GuKorea

Personalised recommendations