Advertisement

Spectral Machine Learning for Predicting Power Wheelchair Exercise Compliance

  • Robert Fisher
  • Reid Simmons
  • Cheng-Shiu Chung
  • Rory Cooper
  • Garrett Grindle
  • Annmarie Kelleher
  • Hsinyi Liu
  • Yu Kuang Wu
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8502)

Abstract

Pressure ulcers are a common and devastating condition faced by users of power wheelchairs. However, proper use of power wheelchair tilt and recline functions can alleviate pressure and reduce the risk of ulcer occurrence. In this work, we show that when using data from a sensor instrumented power wheelchair, we are able to predict with an average accuracy of 92% whether a subject will successfully complete a repositioning exercise when prompted. We present two models of compliance prediction. The first, a spectral Hidden Markov Model, uses fast, optimal optimization techniques to train a sequential classifier. The second, a decision tree using information gain, is computationally efficient and produces an output that is easy for clinicians and wheelchair users to understand. These prediction algorithms will be a key component in an intelligent reminding system that will prompt users to complete a repositioning exercise only in contexts in which the user is most likely to comply.

Keywords

Machine learning spectral learning HMMs healthcare applications 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Bailly, R.: Quadratic weighted automata: Spectral algorithm and likelihood maximization. Journal of Machine Learning Research 20, 147–162 (2011)Google Scholar
  2. 2.
    Beach, S.R., Schulz, R., Matthews, J.T., Courtney, K., Dabbs, A.D.: Preferences for technology versus human assistance and control over technology in the performance of kitchen and personal care tasks in baby boomers and older adults. Disability and Rehabilitation: Assistive Technology, 1–13 (2013)Google Scholar
  3. 3.
    B. Boots, G.J. Gordon.: An online spectral learning algorithm for partially observable nonlinear dynamical systems. In: AAAI (2011)Google Scholar
  4. 4.
    Boots, B., Siddiqi, S.M., Gordon, G.J.: Closing the learning-planning loop with predictive state representations. The International Journal of Robotics Research 30(7), 954–966 (2011)CrossRefGoogle Scholar
  5. 5.
    Cohen, S.B., Stratos, K., Collins, M., Foster, D.P., Ungar, L.: Spectral learning of latent-variable pcfgs. In: Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Long Papers. Association for Computational Linguistics, vol. 1, pp. 223–231 (2012)Google Scholar
  6. 6.
    Cruz, J.A., Wishart, D.S.: Applications of machine learning in cancer prediction and prognosis. Cancer Informatics 2, 59 (2006)Google Scholar
  7. 7.
    Dhillon, P.S., Rodu, J., Collins, M., Foster, D.P., Ungar, L.H.: Spectral dependency parsing with latent variables. In: Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning. Association for Computational Linguistics, pp. 205–213 (2012)Google Scholar
  8. 8.
    Dubey, A.K.: Using rough sets, neural networks, and logistic regression to predict compliance with cholesterol guidelines goals in patients with coronary artery disease. In: AMIA Annual Symposium Proceedings. American Medical Informatics Association, vol. 2003, p. 834 (2003)Google Scholar
  9. 9.
    Falakmasir, M.H., Pardos, Z.A., Gordon, G.J., Brusilovsky, P.: A spectral learning approach to knowledge tracing (2010)Google Scholar
  10. 10.
    Fisher, R., Simmons, R.: Smartphone interruptibility using density-weighted uncertainty sampling with reinforcement learning. In: 2011 10th International Conference on Machine Learning and Applications and Workshops (ICMLA), vol. 1, pp. 436–441. IEEE (2011)Google Scholar
  11. 11.
    Hsu, D., Kakade, S.M., Zhang, T.: A spectral algorithm for learning hidden markov models. Journal of Computer and System Sciences 78(5), 1460–1480 (2012)CrossRefzbMATHMathSciNetGoogle Scholar
  12. 12.
    Lacoste, M., Weiss-Lambrou, R., Allard, M., Dansereau, J.: Powered tilt/recline systems: why and how are they used? Assistive Technology 15(1), 58–68 (2003)CrossRefGoogle Scholar
  13. 13.
    Minh, H.Q., Cristani, M., Perina, A., Murino, V.: A regularized spectral algorithm for hidden markov models with applications in computer vision. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2384–2391. IEEE (2012)Google Scholar
  14. 14.
    Reddy, M., Gill, S.S., Rochon, P.A.: Preventing pressure ulcers: A systematic review. JAMA 296(8), 974–984 (2006)CrossRefGoogle Scholar
  15. 15.
    Rosenthal, S., Dey, A.K., Veloso, M.: Using decision-theoretic experience sampling to build personalized mobile phone interruption models. In: Lyons, K., Hightower, J., Huang, E.M. (eds.) Pervasive 2011. LNCS, vol. 6696, pp. 170–187. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  16. 16.
    Song, X., Mitnitski, A., Cox, J., Rockwood, K.: Comparison of machine learning techniques with classical statistical models in predicting health outcomes. Med. Info. 11(pt 1), 736–740 (2004)Google Scholar
  17. 17.
    Terwijn, S.A.: On the learnability of hidden markov models. In: Adriaans, P.W., Fernau, H., van Zaanen, M. (eds.) ICGI 2002. LNCS (LNAI), vol. 2484, pp. 261–268. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  18. 18.
    Allan, P.: White and Wei Zhong Liu. Technical note: Bias in information-based measures in decision tree induction. Machine Learning 15(3), 321–329 (1994)zbMATHGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Robert Fisher
    • 1
  • Reid Simmons
    • 1
  • Cheng-Shiu Chung
    • 2
  • Rory Cooper
    • 2
  • Garrett Grindle
    • 2
  • Annmarie Kelleher
    • 2
  • Hsinyi Liu
    • 2
  • Yu Kuang Wu
    • 2
  1. 1.Carnegie Mellon UniversityPittsburghUSA
  2. 2.Human Engineering Research LaboratoriesUniversity of PittsburghPittsburghUSA

Personalised recommendations