Human Activity Recognition on Smartphones Using a Multiclass Hardware-Friendly Support Vector Machine

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7657)


Activity-Based Computing [1] aims to capture the state of the user and its environment by exploiting heterogeneous sensors in order to provide adaptation to exogenous computing resources. When these sensors are attached to the subject’s body, they permit continuous monitoring of numerous physiological signals. This has appealing use in healthcare applications, e.g. the exploitation of Ambient Intelligence (AmI) in daily activity monitoring for elderly people. In this paper, we present a system for human physical Activity Recognition (AR) using smartphone inertial sensors. As these mobile phones are limited in terms of energy and computing power, we propose a novel hardware-friendly approach for multiclass classification. This method adapts the standard Support Vector Machine (SVM) and exploits fixed-point arithmetic for computational cost reduction. A comparison with the traditional SVM shows a significant improvement in terms of computational costs while maintaining similar accuracy, which can contribute to develop more sustainable systems for AmI.


Activity Recognition SVM Smartphones Hardware-Friendly 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Davies, N., Siewiorek, D.P., Sukthankar, R.: Activity-based computing. IEEE Pervasive Computing 7(2), 20–21 (2008)CrossRefGoogle Scholar
  2. 2.
    Ekholm, J., Fabre, S.: Forecast: Mobile data traffic and revenue, worldwide. In: Gartner Mobile Communications Worldwide, pp. 2010–2015 (July 2011)Google Scholar
  3. 3.
    Cook, D.J., Das, S.K.: Pervasive computing at scale: Transforming the state of the art. Pervasive and Mobile Computing 8(1), 22–35 (2012)CrossRefGoogle Scholar
  4. 4.
    Allen, F.R., Ambikairajah, E., Lovell, N.H., Celler, B.G.: Classification of a known sequence of motions and postures from accelerometry data using adapted gaussian mixture models. Physiological Measurement 27(10), 935 (2006)CrossRefGoogle Scholar
  5. 5.
    Rodríguez-Molinero, A., Pérez-Martínez, D., Samá, A., Sanz, P., Calopa, M., Gálvez, C., Pérez-López, C., Romagosa, J., Catalá, A.: Detection of gait parameters, bradykinesia and falls in patients with parkinson’s disease by using a unique triaxial accelerometer. World Parkinson Congress, Glasgow (2007)Google Scholar
  6. 6.
    Mannini, A., Sabatini, A.M.: Machine learning methods for classifying human physical activity from on-body accelerometers. Sensors 10(2), 1154–1175 (2010)CrossRefGoogle Scholar
  7. 7.
    Ravi, N., Dandekar, N., Mysore, P., Littman, M.L.: Activity recognition from accelerometer data. In: Proceedings of the Seventeenth Conference on Innovative Applications of Artificial Intelligence, IAAI, pp. 1541–1546. AAAI Press (2005)Google Scholar
  8. 8.
    Kwapisz, J.R., Weiss, G.M., Moore, S.A.: Activity recognition using cell phone accelerometers. SIGKDD Explor. Newsl. 12(2), 74–82 (2011)CrossRefGoogle Scholar
  9. 9.
    LeCun, Y., Jackel, L., Bottou, L., Brunot, A., Cortes, C., Denker, J., Drucker, H., Guyon, I., Mller, U., Sckinger, E., Simard, P., Vapnik, V.: Comparison of learning algorithms for handwritten digit recognition. In: International Conference on Artificial Neural Networks, pp. 53–60 (1995)Google Scholar
  10. 10.
    Ganapathiraju, A., Hamaker, J., Picone, J.: Applications of support vector machines to speech recognition. IEEE Transactions on Signal Processing 52(8), 2348–2355 (2004)CrossRefGoogle Scholar
  11. 11.
    Wawrzynek, J., Asanovic, K., Morgan, N.: The design of a neuro-microprocessor. VLSI for Neural Networks and Artificial Intelligence 4, 103–107 (1993)Google Scholar
  12. 12.
    Anguita, D., Gomes, B.A.: Mixing floating- and fixed-point formats for neural network learning on neuroprocessors. Microprocess. Microprogram. 41(10), 757–769 (1996)CrossRefGoogle Scholar
  13. 13.
    Anguita, D., Ghio, A., Pischiutta, S., Ridella, S.: A hardware-friendly support vector machine for embedded automotive applications. In: International Joint Conference on Neural Networks, IJCNN 2007, pp. 1360–1364 (August 2007)Google Scholar
  14. 14.
    Rifkin, R., Klautau, A.: In defense of one-vs-all classification. Journal of Machine Learning Research 5, 101–141 (2004)MathSciNetzbMATHGoogle Scholar
  15. 15.
    Keerthi, S.S., Shevade, S.K., Bhattacharyya, C., Murthy, K.R.K.: Improvements to platt’s smo algorithm for svm classifier design. Neural Comput. 13(3), 637–649 (2001)zbMATHCrossRefGoogle Scholar
  16. 16.
    Vapnik, V.N.: The nature of statistical learning theory. Springer-Verlag New York, Inc., New York (1995)zbMATHGoogle Scholar
  17. 17.
    Platt, J.C.: Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods. In: Advances in Large Margin Classifiers, pp. 61–74. MIT Press (1999)Google Scholar
  18. 18.
    Anguita, D., Sterpi, D.: Nature Inspiration for Support Vector Machines. In: Gabrys, B., Howlett, R.J., Jain, L.C. (eds.) KES 2006. LNCS (LNAI), vol. 4252, pp. 442–449. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  19. 19.
    Neven, H., Denchev, V.S., Rose, G., Macready, W.G.: Training a binary classifier with the quantum adiabatic algorithm. Arxiv preprint arXiv08110416 (x)  11 (2008)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  1. 1.DITEN - Università degli Studi di GenovaGenoaItaly
  2. 2.CETpD - Universitat Politècnica de CatalunyaSpain

Personalised recommendations