Self-Adaptive Multi-Sensor Activity Recognition Systems Based on Gaussian Mixture Models
Abstract
:1. Introduction
1.1. Related Work
1.2. Research Gap
2. Methods
2.1. Classifier based on Mixture Model
2.2. Data-Based Adaptation
2.3. Model-Based Adaptation
3. Results
- mean
- variance
3.1. Benchmark
3.2. Baseline
3.3. Extension
3.4. Comparison
3.5. Evaluation Results
4. Discussion
Outlook
Author Contributions
Funding
Acknowledgments
Conflicts of Interest
References
- Lukowicz, P.; Kirstein, T.; Tröster, G. Wearable systems for health care applications. Methods Inf. Med. 2004, 43, 232–238. [Google Scholar] [PubMed]
- Abowd, G.; Dey, A.; Brown, P.; Davies, N.; Smith, M.; Steggles, P. Towards a better understanding of context and context-awareness. In Proceedings of International Symposium on Handheld and Ubiquitous Computing; Springer: Berlin/Heidelberg, Germany, 1999; pp. 304–307. [Google Scholar]
- Clarkson, B.; Mase, K.; Pentland, A. Recognizing user context via wearable sensors. In Proceedings of the Fourth International Symposium on Wearable Computers, Digest of Papers, Atlanta, GA, USA, 16–17 October 2000; pp. 69–75. [Google Scholar]
- Gellersen, H.; Schmidt, A.; Beigl, M. Multi-sensor context-awareness in mobile devices and smart artifacts. Mob. Netw. Appl. 2002, 7, 341–351. [Google Scholar] [CrossRef]
- Abowd, G.D. Beyond Weiser: From Ubiquitous to Collective Computing. Computer 2016, 49, 17–23. [Google Scholar] [CrossRef]
- Tomforde, S.; Hähner, J.; von Mammen, S.; Gruhl, C.; Sick, B.; Geihs, K. “Know Thyself”-Computational Self-Reflection in Intelligent Technical Systems. In Proceedings of the 2014 IEEE Eighth International Conference on Self-Adaptive and Self-Organizing Systems Workshops, London, UK, 8–12 September 2014; pp. 150–159. [Google Scholar]
- Roggen, D.; Forster, K.; Calatroni, A.; Holleczek, T.; Fang, Y.; Troster, G.; Ferscha, A.; Holzmann, C.; Riener, A.; Lukowicz, P.; et al. OPPORTUNITY: Towards opportunistic activity and context recognition systems. In Proceedings of the 2009 IEEE International Symposium on a World of Wireless, Mobile and Multimedia Networks & Workshops, Kos, Greece, 15–19 June 2009; pp. 1–6. [Google Scholar]
- Pan, S.J.; Yang, Q. A Survey on Transfer Learning. IEEE Trans. Knowl. Data Eng. 2010, 22, 1345–1359. [Google Scholar] [CrossRef] [Green Version]
- Daumé, H, III. Frustratingly Easy Domain Adaptation. arxiv, 2009; arXiv:0907.1815. [Google Scholar]
- Jiang, J. A Literature Survey on Domain Adaptation of Statistical Classifiers. 2008. Available online: http://sifaka.cs.uiuc.edu/jiang4/domainadaptation/survey (accessed on 16 September 2018).
- Duan, L.; Xu, D.; Tsang, I. Learning with Augmented Features for Heterogeneous Domain Adaptation. arXiv, 2012; arXiv:1206.4660v1. [Google Scholar]
- Chen, L.; Hoey, J.; Nugent, C.D.; Cook, D.J.; Yu, Z. Sensor-Based Activity Recognition. IEEE Trans. Syst. Man Cybern. Part C 2012, 42, 790–808. [Google Scholar] [CrossRef]
- Lara, O.D.; Labrador, M.A. A survey on human activity recognition using wearable sensors. Commun. Surv. Tutor. 2013, 15, 1192–1209. [Google Scholar] [CrossRef]
- Bulling, A.; Blanke, U.; Schiele, B. A Tutorial on Human Activity Recognition Using Body-worn Inertial Sensors. ACM Comput. Surv. 2014, 46, 33:1–33:33. [Google Scholar] [CrossRef]
- Shoaib, M.; Bosch, S.; Incel, O.D.; Scholten, H.; Havinga, P.J. Complex Human Activity Recognition Using Smartphone and Wrist-Worn Motion Sensors. Sensors 2016, 16, 426. [Google Scholar] [CrossRef] [PubMed]
- Lane, N.D.; Eisenman, S.B.; Musolesi, M.; Miluzzo, E.; Campbell, A.T. Urban Sensing Systems: Opportunistic or Participatory? In Proceedings of the 9th Workshop on Mobile Computing Systems and Applications, Napa Valley, CA, USA, 25–26 February 2008; pp. 11–16. [Google Scholar]
- Campbell, A.T.; Eisenman, S.B.; Lane, N.D.; Miluzzo, E.; Peterson, R.A. People-centric Urban Sensing. In Proceedings of the 2nd Annual International Workshop on Wireless Internet, Boston, MA, USA, 2–5 August 2006. [Google Scholar]
- Bannach, D.; Sick, B.; Lukowicz, P. Automatic adaptation of mobile activity recognition systems to new sensors. In Proceedings of the 2011 Workshop Mobile Sensing: Challenges, Opportunities, and Future Directions, Beijing, China, 17–21 September 2011. [Google Scholar]
- Bannach, D. Tools and Methods to Support Opportunistic Human Activity Recognition. Ph.D. Thesis, University of Kaiserslautern, Kaiserslautern, Germany, 2015. [Google Scholar]
- Lau, S.; König, I.; David, K.; Parandian, B.; Carius-Düssel, C.; Schultz, M. Supporting patient monitoring using activity recognition with a smartphone. In Proceedings of the 2010 7th International Symposium on Wireless Communication Systems, York, UK, 19–22 September 2010; pp. 810–814. [Google Scholar]
- Turaga, P.; Chellappa, R.; Subrahmanian, V.S.; Udrea, O. Machine Recognition of Human Activities: A Survey. IEEE Trans. Circuits Syst. Video Technol. 2008, 18, 1473–1488. [Google Scholar] [CrossRef] [Green Version]
- Gan, M.T.; Hanmandlu, M.; Tan, A.H. From a Gaussian mixture model to additive fuzzy systems. IEEE Trans. Fuzzy Syst. 2005, 13, 303–316. [Google Scholar] [Green Version]
- Jordan, A. On discriminative vs. generative classifiers: A comparison of logistic regression and naive bayes. Adv. Neural Inf. Process. Syst. 2002, 14, 841. [Google Scholar]
- Raina, R.; Shen, Y.; Mccallum, A.; Ng, A.Y. Classification with hybrid generative/discriminative models. In Advances in Neural Information Processing Systems; MIT Press Ltd.: Cambridge, MA, USA, 2003. [Google Scholar]
- Huỳnh, T.; Schiele, B. Towards Less Supervision in Activity Recognition from Wearable Sensors. In Proceedings of the 2006 10th IEEE International Symposium on Wearable Computers, Montreux, Switzerland, 11–14 October 2006; pp. 3–10. [Google Scholar]
- Kasteren, T.L.M.; Englebienne, G.; Kröse, B.J.A. An activity monitoring system for elderly care using generative and discriminative models. Pers. Ubiquitous Comput. 2010, 14, 489–498. [Google Scholar] [CrossRef] [Green Version]
- Khan, M.A.A.H.; Roy, N.; Hossain, H.M.S. COAR: Collaborative and Opportunistic Human Activity Recognition. In Proceedings of the 2017 13th International Conference on Distributed Computing in Sensor Systems (DCOSS), Ottawa, ON, Canada, 5–7 June 2017; pp. 142–146. [Google Scholar]
- Berger, A.L.; Pietra, V.J.D.; Pietra, S.A.D. A maximum entropy approach to natural language processing. Comput. Linguist. 1996, 22, 39–71. [Google Scholar]
- Villalonga, C.; Pomares, H.; Rojas, I.; Banos, O. Minertial measurement units-Wear: Ontology-based sensor selection for real-world wearable activity recognition. Neurocomputing 2017, 250, 76–100. [Google Scholar] [CrossRef]
- Rokni, S.A.; Ghasemzadeh, H. Autonomous Training of Activity Recognition Algorithms in Mobile Sensors: A Transfer Learning Approach in Context-Invariant Views. IEEE Trans. Mob. Comput. 2018, 17, 1764–1777. [Google Scholar] [CrossRef]
- Munkres, J. Algorithms for the assignment and transportation problems. J. Soc. Ind. Appl. Math. 1957, 5, 32–38. [Google Scholar] [CrossRef]
- Wang, Z.; Wu, D.; Gravina, R.; Fortino, G.; Jiang, Y.; Tang, K. Kernel fusion based extreme learning machine for cross-location activity recognition. Inf. Fusion 2017, 37, 1–9. [Google Scholar] [CrossRef]
- Münzner, S.; Schmidt, P.; Reiss, A.; Hanselmann, M.; Stiefelhagen, R.; Dürichen, R. CNN-based Sensor Fusion Techniques for Multimodal Human Activity Recognition. In Proceedings of the 2017 ACM International Symposium on Wearable Computers, Maui, HI, USA, 11–15 September 2017; pp. 158–165. [Google Scholar]
- Morales, F.J.O.; Roggen, D. Deep convolutional feature transfer across mobile activity recognition domains, sensor modalities and locations. In Proceedings of the 2016 ACM International Symposium on Wearable Computers, Heidelberg, Germany, 12–16 September 2016; pp. 92–99. [Google Scholar]
- Rey, V.F.; Lukowicz, P. Label Propagation: An Unsupervised Similarity Based Method for Integrating New Sensors in Activity Recognition Systems. Proc. ACM Interact. Mob. Wearable Ubiquitous Technol. 2017, 1, 94:1–94:24. [Google Scholar] [CrossRef]
- Jänicke, M.; Sick, B.; Lukowicz, P.; Bannach, D. Self-Adapting Multi-sensor Systems: A Concept for Self-Improvement and Self-Healing Techniques. In Proceedings of the 2014 IEEE Eighth International Conference on the Self-Adaptive and Self-Organizing Systems Workshops (SASOW), London, UK, 8–12 September 2014; pp. 128–136. [Google Scholar]
- Jänicke, M. Self-adapting Multi-Sensor System Using Classifiers Based on Gaussian Mixture Models. In Organic Computing: Doctoral Dissertation Colloquium 2015; Kassel University Press GmbH: Kassel, Germany, 2015; Volume 7, p. 109. [Google Scholar]
- Jänicke, M.; Tomforde, S.; Sick, B. Towards Self-Improving Activity Recognition Systems Based on Probabilistic, Generative Models. In Proceedings of the 2016 IEEE International Conference on Autonomic Computing (ICAC), Würzburg, Germany, 17–22 July 2016; pp. 285–291. [Google Scholar]
- Bishop, C.M. Pattern Recognition and Machine Learning; Springer: New York, NY, USA, 2006. [Google Scholar]
- Reitmaier, T.; Calma, A.; Sick, B. Transductive active learning—A new semi-supervised learning approach based on iteratively refined generative models to capture structure in data. Inf. Sci. 2015, 293, 275–298. [Google Scholar] [CrossRef]
- Duda, R.O.; Hart, P.E.; Stork, D.G. Pattern Classification; John Wiley & Sons: Chichester, NY, USA, 2001. [Google Scholar]
- Fisch, D.; Sick, B. Training of Radial Basis Function Classifiers With Resilient Propagation and Variational Bayesian Inference. In Proceedings of the 2009 International Joint Conference on Neural Networks, Atlanta, GA, USA, 14–19 June 2009; pp. 838–847. [Google Scholar]
- Reiss, A.; Stricker, D. Introducing a New Benchmarked Dataset for Activity Monitoring. In Proceedings of the 2012 16th International Symposium on Wearable Computers, Newcastle, UK, 18–22 June 2012; pp. 108–109. [Google Scholar]
- Reiss, A.; Stricker, D. Creating and benchmarking a new dataset for physical activity monitoring. In Proceedings of the 5th International Conference on Pervasive Technologies Related to Assistive Environments, Heraklion, Crete, Greece, 6–8 June 2012; p. 40. [Google Scholar]
- Lau, S.; David, K. Movement recognition using the accelerometer in smartphones. In Proceedings of the Future Network and Mobile Summit, Florence, Italy, 16–18 June 2010; pp. 1–9. [Google Scholar]
- Sokolova, M.; Japkowicz, N.; Szpakowicz, S. Beyond accuracy, F-score and ROC: A family of discriminant measures for performance evaluation. In Proceedings of Australasian Joint Conference on Artificial Intelligence; Springer: Berlin/Heidelberg, Germany, 2006; pp. 1015–1021. [Google Scholar]
- Reitmaier, T.; Sick, B. The Responsibility Weighted Mahalanobis Kernel for Semi-supervised Training of Support Vector Machines for Classification. Inf. Sci. 2015, 323, 179–198. [Google Scholar] [CrossRef]
# Sensors | Method | |||
---|---|---|---|---|
Baseline | Adapt-from-Class | Adapt-from-Train | Comparison | |
1 | 0.349 ± 0.095 | 0.358 ± 0.078 | 0.302 ± 0.068 | 0.440 ± 0.039 |
2 | 0.440 ± 0.039 | 0.444 ± 0.035 | 0.370 ± 0.032 | 0.468 ± 0.027 |
3 | 0.468 ± 0.028 | 0.471 ± 0.026 | 0.396 ± 0.021 | 0.480 ± 0.017 |
4 | 0.480 ± 0.020 | – | – | 0.480 ± 0.020 |
# Sensors | Method | |||
---|---|---|---|---|
Baseline | Adapt-from-Class | Adapt-from-Train | Comparison | |
1 | 0.423 ± 0.095 | 0.491 ± 0.080 | 0.311 ± 0.096 | 0.537 ± 0.034 |
2 | 0.537 ± 0.035 | 0.569 ± 0.031 | 0.413 ± 0.041 | 0.573 ± 0.023 |
3 | 0.573 ± 0.024 | 0.590 ± 0.023 | 0.458 ± 0.023 | 0.591 ± 0.012 |
4 | 0.591 ± 0.014 | – | – | 0.591 ± 0.014 |
© 2018 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
Jänicke, M.; Sick, B.; Tomforde, S. Self-Adaptive Multi-Sensor Activity Recognition Systems Based on Gaussian Mixture Models. Informatics 2018, 5, 38. https://doi.org/10.3390/informatics5030038
Jänicke M, Sick B, Tomforde S. Self-Adaptive Multi-Sensor Activity Recognition Systems Based on Gaussian Mixture Models. Informatics. 2018; 5(3):38. https://doi.org/10.3390/informatics5030038
Chicago/Turabian StyleJänicke, Martin, Bernhard Sick, and Sven Tomforde. 2018. "Self-Adaptive Multi-Sensor Activity Recognition Systems Based on Gaussian Mixture Models" Informatics 5, no. 3: 38. https://doi.org/10.3390/informatics5030038
APA StyleJänicke, M., Sick, B., & Tomforde, S. (2018). Self-Adaptive Multi-Sensor Activity Recognition Systems Based on Gaussian Mixture Models. Informatics, 5(3), 38. https://doi.org/10.3390/informatics5030038