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.

[1]  Kenneth Rockwood,et al.  Comparison of Machine Learning Techniques with Classical Statistical Models in Predicting Health Outcomes , 2004, MedInfo.

[2]  Allan P. White,et al.  Technical Note: Bias in Information-Based Measures in Decision Tree Induction , 1994, Machine Learning.

[3]  Byron Boots,et al.  Closing the learning-planning loop with predictive state representations , 2011, Int. J. Robotics Res..

[4]  Sebastiaan A. Terwijn,et al.  On the Learnability of Hidden Markov Models , 2002, ICGI.

[5]  Uwe Hansmann,et al.  Pervasive Computing , 2003 .

[6]  B. Thiers.  Preventing Pressure Ulcers: A Systematic Review , 2007 .

[7]  Richard Schulz,et al.  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 , 2014, Disability and rehabilitation. Assistive technology.

[8]  Dean Alderucci.  A SPECTRAL ALGORITHM FOR LEARNING HIDDEN MARKOV MODELS THAT HAVE SILENT STATES , 2015 .

[9]  Byron Boots,et al.  An Online Spectral Learning Algorithm for Partially Observable Nonlinear Dynamical Systems , 2011, AAAI.

[10]  Philipp Koehn,et al.  Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL) , 2007 .

[11]  David S. Wishart,et al.  Applications of Machine Learning in Cancer Prediction and Prognosis , 2006, Cancer informatics.

[12]  Stephanie Rosenthal,et al.  Using Decision-Theoretic Experience Sampling to Build Personalized Mobile Phone Interruption Models , 2011, Pervasive.

[13]  Jean Dansereau,et al.  Powered Tilt/Recline Systems: Why and How Are They Used? , 2003, Assistive technology : the official journal of RESNA.

[14]  Anil K. Dubey.  Using Rough Sets, Neural Networks, and Logistic Regression to Predict Compliance with Cholesterol Guidelines Goals in Patients with Coronary Artery Disease , 2003, AMIA.

[15]  Byron Boots,et al.  Closing the learning-planning loop with predictive state representations , 2009, Int. J. Robotics Res..

[16]  Karl Stratos,et al.  Spectral Learning of Latent-Variable PCFGs , 2012, ACL.

[17]  Raphaël Bailly.  Quadratic Weighted Automata: Spectral Algorithm and Likelihood Maximization , 2011, ACML 2011.

[18]  Reid G. Simmons,et al.  Smartphone Interruptibility Using Density-Weighted Uncertainty Sampling with Reinforcement Learning , 2011, 2011 10th International Conference on Machine Learning and Applications and Workshops.

[19]  Michael Collins,et al.  Spectral Dependency Parsing with Latent Variables , 2012, EMNLP-CoNLL.

[20]  Amaury Habrard,et al.  A Polynomial Algorithm for the Inference of Context Free Languages , 2008, ICGI.

[21]  Zachary A. Pardos,et al.  A Spectral Learning Approach to Knowledge Tracing , 2013, EDM.

[22]  Alessandro Perina,et al.  A regularized spectral algorithm for Hidden Markov Models with applications in computer vision , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.