Advertisement

Hardware-Friendly Activity Recognition with Fixed-Point Arithmetic

  • Jorge Luis Reyes OrtizEmail author
Chapter
  • 1.1k Downloads
Part of the Springer Theses book series (Springer Theses)

Abstract

Exploiting SVM models for HAR on smartphones requires a multitude of operations to be carried out per second: despite not being an issue from a theoretical point of view, this could lead to battery discharge after few hours of continuous operation, making this approach unfeasible to allow people’s mobility.

Keywords

Generalization Ability Hypothesis Space Structural Risk Minimization Battery Consumption Recognition Speed 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

References

  1. D. Anguita, A. Ghio, L. Oneto, S. Ridella, in A learning machine with a bit-based hypothesis space, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, 2013Google Scholar
  2. D. Anguita, A. Ghio, L. Oneto, S. Ridella, in Selecting the hypothesis space for improving the generalization ability of support vector machines, International Joint Conference on Neural Networks, 2011Google Scholar
  3. D. Anguita, A. Ghio, L. Oneto, S. Ridella, In-sample and out-of-sample model selection and error estimation for support vector machines. IEEE Trans. Neural Networks. Learn. Syst. 23, 1390–1406 (2012)Google Scholar
  4. D. Anguita, A. Ghio, S. Pischiutta, S. Ridella, in A hardware-friendly support vector machine for embedded automotive applications, International Joint Conference on Neural Networks, 2007Google Scholar
  5. D. Anguita, A. Ghio, S. Ridella, D. Sterpi, in K-fold cross validation for error rate estimate in support vector machines, International Conference on Data Mining, 2009Google Scholar
  6. D. Anguita, D. Sterpi, in Nature inspiration for support vector machines, International conference on Knowledge-Based Intelligent Information and Engineering Systems, 2006Google Scholar
  7. L. Bao, S.S. Intille, in Activity recognition from user-annotated acceleration data, Pervasive Computing, 2004Google Scholar
  8. P.L. Bartlett, S. Mendelson, Rademacher and gaussian complexities: risk bounds and structural results. J. Mach. Learn. Res. 3, 463–482 (2003)zbMATHMathSciNetGoogle Scholar
  9. P.L. Bartlett, O. Bousquet, S. Mendelson, Local rademacher complexities. Ann. Stat. 33, 1497–1537 (2005)CrossRefzbMATHMathSciNetGoogle Scholar
  10. M.G. Epitropakis, V.P. Plagianakos, M.N. Vrahatis, Hardware-friendly higher-order neural network training using distributed evolutionary algorithms. Appl. Soft Comput. 10, 398–408 (2010)CrossRefGoogle Scholar
  11. R. Genov, G. Cauwenberghs, Kerneltron: support vector machine in silicon. IEEE Trans. Neural Networks 14, 1426–1434 (2003)CrossRefGoogle Scholar
  12. R. Herbrich, R.C. Williamson, Algorithmic luckiness. J.Mach. Learn. Res. 3, 175–212 (2003)zbMATHMathSciNetGoogle Scholar
  13. K. Irick, M. DeBole, V. Narayanan, A. Gayasen, in A hardware efficient support vector machine architecture for FPGA, International Symposium on Field-Programmable Custom Computing Machines, 2008Google Scholar
  14. V. Koltchinskii, Local rademacher complexities and oracle inequalities in risk minimization. Ann. Stat. 34, 2593–2656 (2006)CrossRefzbMATHMathSciNetGoogle Scholar
  15. N. Lane, M. Mohammod, M. Lin, X. Yang, H. Lu, S. Ali, A. Doryab, E. Berke, T. Choudhury, A.C Bewell, in A smartphone application to monitor, model and promote wellbeing, IEEE International ICST Conference on Pervasive Computing Technologies for Healthcare, 2012Google Scholar
  16. S.W. Lee, S.W. Lee, H.C. Jung, in Real-time implementation of face recognition algorithms on dsp chip, Audio-and Video-Based Biometric Person Authentication, 2003Google Scholar
  17. B. Lesser, M. Mücke, W.N. Gansterer, Effects of reduced precision on floating-point SVM classification accuracy. Procedia Comput. Sci. 4, 508–517 (2011)CrossRefGoogle Scholar
  18. N.H. Lovell, N. Wang, E. Ambikairajah, B.G. Celler, in Accelerometry based classification of walking patterns using time-frequency analysis, IEEE Annual International Conference of the Engineering in Medicine and Biology Society, 2007Google Scholar
  19. H. Neven, V.S. Denchev, G. Rose, W.G. Macready. Training a binary classifier with the quantum adiabatic algorithm (2008) In arXiv preprint http://arxiv.org/abs/0811.0416arXiv:0811.0416
  20. H. Neven, V.S. Denchev, G. Rose, W.G. Macready. Training a large scale classifier with the quantum adiabatic algorithm (2009), In arXiv preprint http://arxiv.org/abs/0912.0779arXiv:0912.0779
  21. J.C. Platt, in Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods, Advances in Large Margin Classifiers, 1999Google Scholar
  22. T. Poggio, S. Mukherjee, A. Raklin, A. Verri. R. Rifkin. Uncertainty in Geometric Computations (Kluwer Academic Publishers, Boston, 2002)Google Scholar
  23. A. Sama, D.E. Pardo-Ayala, J. Cabestany, A Rodríguez-Molinero, Time series analysis of inertial-body signals for the extraction of dynamic properties from human gait, IEEE International Joint Conference on Neural Networks, 2010Google Scholar
  24. J. Shawe-Taylor, P.L. Bartlett, R.C. Williamson, M. Anthony, Structural risk minimization over data-dependent hierarchies. IEEE Trans. Inf. Theor. 44, 1926–1940 (1998)CrossRefzbMATHMathSciNetGoogle Scholar
  25. V.N. Vapnik, The nature of statistical learning theory (Springer-Verlag, New York, 1995)CrossRefzbMATHGoogle Scholar
  26. John Wawrzynek, Krste Asanovic, Nelson Morgan, Senior Member, The design of a neuro-microprocessor. VLSI Neural Networks. Artif. Intell. 4, 103–127 (1993)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  1. 1.CETpDUniversitat Politècnica de CatalunyaBarcelonaSpain

Personalised recommendations