Characterizing Dynamic Walking Patterns and Detecting Falls with Wearable Sensors Using Gaussian Process Methods
Abstract
:1. Introduction
2. Methods
2.1. Preliminaries
2.2. GP-Based Solutions for Characterizing Dynamic Walking Patterns
3. Experimental Results
4. Discussion
- In [18], the GPDM model was applied to the problem of 3D people tracking based on human motion capture data, whereas in this paper, we used an extended version of the GPDM for the purpose of characterizing dynamic walking patterns with wearable sensor data.
- In the original GPDM method, the low-dimensional latent trajectories were obtained through optimization, which minimizes an objective function related with the negative log posterior. The proposed auto-encoded GPDM is equipped with the GP encoder, which is capable of yielding latent representations for given observations. This capability played important roles in our finding latent trajectories for test data (e.g., solid lines in Figure 6).
5. Conclusions
Acknowledgments
Author Contributions
Conflicts of Interest
References
- Lan, M.; Samy, L.; Alshurafa, N.; Suh, M.K.; Ghasemzadeh, H.; Macabasco-O’Connell, A.; Sarrafzadeh, M. Wanda: An end-to-end remote health monitoring and analytics system for heart failure patients. In Proceedings of the Conference on Wireless Health, San Diego, CA, USA, 23–25 October 2012; pp. 1–8. [Google Scholar]
- Ghasemzadeh, H.; Ostadabbas, S.; Guenterberg, E.; Pantelopoulos, A. Wireless medical-embedded systems: A review of signal-processing techniques for classification. IEEE Sens. J. 2013, 13, 423–437. [Google Scholar] [CrossRef]
- Özdemir, A.T.; Barshan, B. Detecting falls with wearable sensors using machine learning techniques. Sensors 2014, 14, 10691–10708. [Google Scholar] [PubMed]
- Luštrek, M.; Kaluža, B. Fall detection and activity recognition with machine learning. Informatica 2009, 33, 197–204. [Google Scholar]
- Liu, S.H.; Cheng, W.C. Fall detection with the support vector machine during scripted and continuous unscripted activities. Sensors 2012, 12, 12301–12316. [Google Scholar] [PubMed]
- Dubey, R.; Ni, B.; Moulin, P. A depth camera based fall recognition system for the elderly. In Proceedings of the International Conference Image Analysis and Recognition, Aveiro, Portugal, 25–27 June 2012; pp. 106–113. [Google Scholar]
- Jeon, A.; Park, G.; Ro, J.H.; Geon, G.R. Development of the algorithm for detecting falls during daily activity using 2 tri-axial accelerometers. World Acad. Sci. Eng. Technol. Issue 2012, 61, 19–23. [Google Scholar]
- Ellis, D.; Sommerlade, E.; Reid, I. Modelling pedestrian trajectory patterns with gaussian processes. In Proceedings of the 2009 IEEE 12th International Conference on Computer Vision Workshops, Kyoto, Japan, 27 September–4 October 2009; pp. 1229–1234. [Google Scholar]
- Ojetola, O.; Gaura, E.I.; Brusey, J. Fall detection with wearable sensors–safe (Smart Fall Detection). In Proceedings of the 2011 7th International Conference on Intelligent Environments, Nottingham, UK, 25–28 July 2011; Volume 5, pp. 318–321. [Google Scholar]
- Choi, Y.; Ralhan, A.S.; Ko, S. A study on machine learning algorithms for fall detection and movement classification. In Proceedings of the 2011 International Conference on Information Science and Applications, Jeju Island, Jeju Province, Korea, 26–29 April 2011; Volume 5, pp. 1–8. [Google Scholar]
- Abbate, S.; Avvenuti, M.; Bonatesta, F.; Cola, G.; Corsini, P.; Vecchio, A. A smartphone-based fall detection system. Pervasive Mob. Comput. 2012, 8, 883–899. [Google Scholar] [CrossRef]
- Wang, N.; Ambikairajah, E.; Lovell, N.H.; Celler, B.G. Accelerometry based classification of walking patterns using time-frequency analysis. In Proceedings of the 2007 29th Annual International Conference of the Engineering in Medicine and Biology Society (EMBS 2007), Lyon, France, 23–26 August 2007; Volume 5, pp. 4899–4902. [Google Scholar]
- Sekine, M.; Tamura, T.; Fujimoto, T.; Fukui, Y. Classification of walking pattern using acceleration waveform in elderly people. In Proceedings of the 2000 22nd Annual International Conference of the Engineering in Medicine and Biology Society, Navy Pier Convention Center, Chicago, IL, USA, 23–28 July 2000; Volume 2, pp. 1356–1359. [Google Scholar]
- Schölkopf, B.; Smola, A.J. Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond; MIT Press: Cambridge, MA, USA, 2002. [Google Scholar]
- Rasmussen, C.E.; Williams, K.I. Gaussian Processes for Machine Learning; MIT Press: Cambridge, MA, USA, 2006. [Google Scholar]
- Krauth, K.; Bonilla, E.V.; Cutajar, K.; Filippone, M. AutoGP: Exploring the Capabilities and Limitations of Gaussian Process Models. Available online: https://arxiv.org/pdf/1610.05392.pdf (accessed on 6 March 2017).
- Lawrence, N.D. Gaussian process latent variable models for visualization of high dimensional data. Adv. Neural Inf. Process. Syst. (Nips) 2003, 2, 329–336. [Google Scholar]
- Wang, J.; Fleet, D.J.; Hertzmann, A. Gaussian process dynamical models for human motion. IEEE Trans. Pattern Anal. Mach. Intell. 2008, 30, 283–298. [Google Scholar] [PubMed]
- Urtasun, R.; Fleet, D.J.; Hertzmann, A.; Fua, P. Priors for people tracking from small training sets. In Proceedings of the IEEE International Conference on Computer Vision, Beijing hotel, Beijing, China, 15–21 October 2005; Volume 1, pp. 403–410. [Google Scholar]
- Urtasun, R.; Fleet, D.J.; Fua, P. 3D people tracking with Gaussian process dynamical models. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, New York, NY, USA, 17–22 June 2006; Volume 1, pp. 238–245. [Google Scholar]
- Vincent, P.; Larochelle, H.; Lajoie, I.; Bengio, Y.; Manzagol, P.A. Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion. J. Mach. Learn. Res. 2010, 11, 3371–3408. [Google Scholar]
- Kingma, D.P.; Welling, M. Auto-Encoding Variational Bayes. The International Conference on Learning Representations (ICLR). 2014. Available online: https://arxiv.org/pdf/1312.6114v10.pdf (accessed on 1 May 2014).
- Bishop, C.M. Pattern Recognition and Machine Learning; Springer-Verlag: New York, NY, USA, 2006. [Google Scholar]
- Roweis, S.T.; Saul, L.K. Nonlinear dimensionality reduction by locally linear embedding. Science 2000, 290, 2323–2326. [Google Scholar] [CrossRef] [PubMed]
- Tenenbaum, J.B.; De Silva, V.; Langford, J.C. A global geometric framework for nonlinear dimensionality reduction. Science 2000, 290, 2319–2323. [Google Scholar] [CrossRef] [PubMed]
- Schölkopf, B.; Smola, A.; Müller, K.R. Nonlinear component analysis as a kernel eigenvalue problem. Neural Comput. 1998, 10, 1299–1319. [Google Scholar] [CrossRef]
- Kemmler, M.; Rodner, E.; Wacker, E.S.; Kwok, J.T.; Denzler, J. One-class classification with Gaussian processes. Pattern Recognit. 2013, 46, 3507–3518. [Google Scholar] [CrossRef]
- Rodner, E.; Wacker, E.S.; Kemmler, M.; Denzler, J. One-class classification for anomaly detection in wire ropes with Gaussian processes in a few lines of code. Training 2011, 1, 1–5. [Google Scholar]
- Bodesheim, P.; Freytag, A.; Rodner, E.; Kemmler, M.; Denzler, J. Kernel null space methods for novelty detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Oregon, Portland, 25–27 June 2013; pp. 3374–3381. [Google Scholar]
- McGeer, T. Powered flight, child’s play, silly wheels and walking machines. In Proceedings of the 1989 IEEE International Conference on Robotics and Automation, Scottsdale, AZ, USA, 14–19 May 1989; pp. 1592–1597. [Google Scholar]
- Collins, S.H. Dynamic Walking Principles Applied to Human Gait. Ph.D. Thesis, University of Michigan, Ann Arbor, MI, USA, 2008. [Google Scholar]
- Karantonis, D.M.; Narayanan, M.R.; Mathie, M.; Lovell, N.H.; Celler, B.G. Implementation of a real-time human movement classifier using a triaxial accelerometer for ambulatory monitoring. IEEE Trans. Inf. Technol. Biomed. 2006, 10, 156–167. [Google Scholar] [CrossRef] [PubMed]
- Bersch, S.D.; Azzi, D.; Khusainov, R.; Achumba, I.E.; Ries, J. Sensor data acquisition and processing parameters for human activity classification. Sensors 2014, 14, 4239–4270. [Google Scholar] [CrossRef] [PubMed]
- Kocijan, J.; Girard, A.; Banko, B.; Murray-Smith, R. Dynamic systems identification with Gaussian processes. Math. Comput. Model. Dyn. Syst. 2005, 11, 411–424. [Google Scholar] [CrossRef]
- Van Vaerenbergh, S.; Via, J.; Santamaria, I. Nonlinear system identification using a new sliding-window kernel RLS algorithm. JCM 2007, 2, 1–8. [Google Scholar] [CrossRef]
- Van Vaerenbergh, S.; Via, J.; Santamaría, I. A sliding-window kernel RLS algorithm and its application to nonlinear channel identification. In Proceedings of the 2006 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2006), Toulouse Pierre Baudis Congress Center, Toulouse, France, 14–19 May 2006; Volume 5, pp. 789–792. [Google Scholar]
- Titsias, M.K. Variational learning of inducing variables in sparse Gaussian processes. AISTATS 2009, 5, 567–574. [Google Scholar]
- Watter, M.; Springenberg, J.; Boedecker, J.; Riedmiller, M. Embed to control: A locally linear latent dynamics model for control from raw images. Advances in Neural Information Processing Systems, Palais des Congres de Montreal, Montreal, CANADA, 7–12 December 2015; pp. 2746–2754. [Google Scholar]
- Rudin, W. Real and Complex Analysis; Tata McGraw-Hill Education: 2 Pennsylvania Plaza: New York, NY, USA, 1987. [Google Scholar]
- Park, J.; Kang, D.; Kim, J.; Kwok, J.T.; Tsang, I.W. SVDD-based pattern denoising. Neural Comput. 2007, 19, 1919–1938. [Google Scholar] [CrossRef] [PubMed]
- Rätsch, G.; Mika, S.; Schölkopf, B.; Müller, K.R. Constructing boosting algorithms from SVMs: An application to one-class classification. IEEE Trans. Pattern Anal. Mach. Intell. 2002, 24, 1184–1199. [Google Scholar] [CrossRef]
- Hunter, J.D. Matplotlib: A 2D graphics environment. Comput. Sci. Eng. 2007, 9, 90–95. [Google Scholar] [CrossRef]
- Auto-encoded GPDM. Available online: https://www.youtube.com/watch?v=ZQSdYvSHcU8 (accessed on 16 February 2017).
Notation | Meaning |
---|---|
Acceleration along the x-direction | |
Acceleration along the y-direction | |
Acceleration along the z-direction | |
Total magnitude of acceleration, i.e., | |
Angular velocity around the x-direction | |
Angular velocity around the y-direction | |
Angular velocity around the z-direction | |
Total magnitude of angular velocity, i.e., |
1: Obtain five sets of training data for each class of walking, standing, and lying. |
2: Obtain five sets of test data for each class of walking, standing, and lying. |
3: Train the auto-encoded Gaussian process dynamical model with the training data for walking, and fix the model. |
4: Based on the fixed model, compute latent trajectory samples with the training data for each class of walking, standing, and lying. |
5: Plot contours of the predictive mean score (see e.g., [27]) based on the latent trajectory samples for each class of walking, standing, and lying. |
6: (optional) Perform classification for the test data. |
© 2017 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
Share and Cite
Kim, T.; Park, J.; Heo, S.; Sung, K.; Park, J. Characterizing Dynamic Walking Patterns and Detecting Falls with Wearable Sensors Using Gaussian Process Methods. Sensors 2017, 17, 1172. https://doi.org/10.3390/s17051172
Kim T, Park J, Heo S, Sung K, Park J. Characterizing Dynamic Walking Patterns and Detecting Falls with Wearable Sensors Using Gaussian Process Methods. Sensors. 2017; 17(5):1172. https://doi.org/10.3390/s17051172
Chicago/Turabian StyleKim, Taehwan, Jeongho Park, Seongman Heo, Keehoon Sung, and Jooyoung Park. 2017. "Characterizing Dynamic Walking Patterns and Detecting Falls with Wearable Sensors Using Gaussian Process Methods" Sensors 17, no. 5: 1172. https://doi.org/10.3390/s17051172
APA StyleKim, T., Park, J., Heo, S., Sung, K., & Park, J. (2017). Characterizing Dynamic Walking Patterns and Detecting Falls with Wearable Sensors Using Gaussian Process Methods. Sensors, 17(5), 1172. https://doi.org/10.3390/s17051172