Spectral Machine Learning for Predicting Power Wheelchair Exercise Compliance
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.
KeywordsMachine learning spectral learning HMMs healthcare applications
Unable to display preview. Download preview PDF.
- 1.Bailly, R.: Quadratic weighted automata: Spectral algorithm and likelihood maximization. Journal of Machine Learning Research 20, 147–162 (2011)Google Scholar
- 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.B. Boots, G.J. Gordon.: An online spectral learning algorithm for partially observable nonlinear dynamical systems. In: AAAI (2011)Google Scholar
- 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.Cruz, J.A., Wishart, D.S.: Applications of machine learning in cancer prediction and prognosis. Cancer Informatics 2, 59 (2006)Google Scholar
- 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.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.Falakmasir, M.H., Pardos, Z.A., Gordon, G.J., Brusilovsky, P.: A spectral learning approach to knowledge tracing (2010)Google Scholar
- 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
- 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
- 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