Health Problems Discovery from Motion-Capture Data of Elderly
Rapid aging of the population of the developed countries could exceed the society’s capacity for taking care for them. In order to help solving this problem, we propose a system for automatic discovery of health problems from motion-capture data of gait of elderly. The gait of the user is captured with the motion capture system, which consists of tags attached to the body and sensors situated in the apartment. Position of the tags is acquired by the sensors and the resulting time series of position coordinates are analyzed with machine learning algorithms in order to identify the specific health problem. We propose novel features for training a machine learning classifier that classifies the user’s gait into: i) normal, ii) with hemiplegia, iii) with Parkinson’s disease, iv) with pain in the back and v) with pain in the leg. Results show that naive Bayes needs more tags and less noise to reach classification accuracy of 98 % than support vector machines for 99 %.
KeywordsSupport Vector Machine Classification Accuracy Activity Recognition Support Vector Machine Classifier Motion Capture System
Unable to display preview. Download preview PDF.
This work is partially financed by the European Union, the European Social Fund. The authors thank Martin Tomšič, Bojan Nemec and Leon Žlajpah for their help with data acquisition, Anton Gradišek for his medical expertise and Zoran Bosnić and Mitja Luštrek for helpful discussions.
- 1.D. Strle, V. Kempe, “MEMS-based inertial systems”, Informacije MIDEM 37(2007)4, pp. 199-209.Google Scholar
- 2.D. Jurman, M. Jankovec, R. Kamnik, M. Topič, “Inertial and magnetic sensors: The calibration aspect”, Informacije MIDEM 37(2007)2, pp. 67-72.Google Scholar
- 3.F. Dimic, B. Mušič, R. Osredkar, “An example of an integrated GPS and DR positioning system designed for archeological prospecting”, Informacije MIDEM 38(2008)2, pp. 144-148.Google Scholar
- 4.S. Ribarič, J. Rozman, “Sensors for measurement of tremor type joint movements”, Informacije MIDEM 37(2007)2, pp. 98-104.Google Scholar
- 5.J. Trontelj, J. Trontelj and L. Trontelj, “Safety Margin at mammalian neuromuscular junction – an example of the significance of fine time measurements in neurobiology”, Informacije MIDEM 38(2008)3, pp. 155-160.Google Scholar
- 7.Bourke, A.K., Scanaill, C.N., Culhane, K.M., O'Brien, J.V., and Lyons, G.M. An optimum accelerometer configuration and simple algorithm for accurately detecting falls. In Proc. BioMed 2006 (2006), 156–160.Google Scholar
- 8.Confidence: Ubiquitous Care System to Support Independent Living. http://www.confidenceeu.org.
- 9.Craik R., and Oatis C. Gait Analysis: Theory and Application. Mosby-Year Book (1995).Google Scholar
- 10.Perry J. Gait Analysis: Normal and Pathological Function. McGraw-Hill, Inc., 1992.Google Scholar
- 11.eMotion. Smart motion capture system. http://www.emotion3d.com/smart/smart.html.
- 14.Luštrek M., Kaluža B., Fall Detection and Activity Recognition with Machine Learning. Informatica (Slovenia) 33(2): 197-204 (2009).Google Scholar
- 15.Maybeck, P.S. Stochastic models, estimation, and control. Mathematics in Science and Engineering 141 (1979).Google Scholar
- 16.Qian, G., Guo, F., Ingalls, T., Olson, L., James, J., and Rikakis, T. A gesture-driven multimodal interactive dance system. In Proc. ICME ’04 (2004), 1579–1582.Google Scholar
- 18.Tapia, E.M., Intille, S.S., Haskell, W., Larson, K., Wright, J., King, A., and Friedman, R. Real-time recognition of physical activities and their intensities using wireless accelerometers and a heart rate monitor. In Proc. ISWC 2007 (2007), 37–40.Google Scholar
- 20.Witten, I.H., and Frank, E. Data Mining: Practical Machine Learning Tools and Techniques (2nd edition). Morgan Kaufmann (2005).Google Scholar
- 22.Zouba, N., Boulay, B., Bremond, F., and Thonnat, M. Monitoring activities of daily living (ADLs) of elderly based on 3D key human postures. In Proc. ICVW 2008 (2008), 37–50.Google Scholar
- 23.Moore ST, et al., Long-term monitoring of gait in Parkinson’s disease, Gait Posture (2006), doi:10.1016/j.gaitpost.2006.09.011Google Scholar