ABSTRACT
Personalization of activity recognition has become a topic of interest recently. This paper presents a novel concept, using a set of classifiers as general model, and retraining only the weight of the classifiers with new labeled data from a previously unknown subject. Experiments with different methods based on this concept show that it is a valid approach for personalization. An important benefit of the proposed concept is its low computational cost compared to other approaches, making it also feasible for mobile applications. Moreover, more advanced classifiers (e.g. boosted decision trees) can be combined with the new concept, to achieve good performance even on complex classification tasks. Finally, a new algorithm is introduced based on the proposed concept, which outperforms existing methods, thus further increasing the performance of personalized applications.
- Berchtold, M., Budde, M., Gordon, D., Schmidtke, H., and Beigl, M. ActiServ: Activity Recognition Service for Mobile Phones. In Proc. ISWC (2010).Google ScholarCross Ref
- Blum, A. On-Line Algorithms in Machine Learning. In Proc. Workshop on On-Line Algorithms, Dagstuhl (1996), 306--325. Google ScholarDigital Library
- Cvetkovic, B., and Kaluza, B. Semi-supervised Learning for Adaptation of Human Activity Recognition Classifier to the User. In Proc. IJCAI (2011).Google Scholar
- Ermes, M., P\"arkk\"a, J., and Cluitmans, L. Advancing from offline to online activity recognition with wearable sensors. In Proc. 30th Annual International IEEE EMBS Conference (2008), 4451--4454.Google ScholarCross Ref
- Kuncheva, L. I. Combining Pattern Classifiers: Methods and Algorithms. Wiley-Interscience, 2004. Google ScholarDigital Library
- Maekawa, T., and Watanabe, S. Unsupervised Activity Recognition with User's Physical Characteristics Data. In Proc. ISWC (2011). Google ScholarDigital Library
- P\"arkk\"a, J., Cluitmans, L., and Ermes, M. Personalization algorithm for real-time activity recognition using PDA, wireless motion bands, and binary decision tree. IEEE Trans. Inf. Technol. Biomed. 14, 5 (2010). Google ScholarDigital Library
- Reiss, A., and Stricker, D. Introducing a Modular Activity Monitoring System. In Proc. 33rd Annual International IEEE EMBS Conference (2011), 5621--5624.Google ScholarCross Ref
- Reiss, A., and Stricker, D. Creating and Benchmarking a New Dataset for Physical Activity Monitoring. In Proc. 5th Workshop on Affect and Behaviour Related Assistance (ABRA) (2012). Google ScholarDigital Library
- Reiss, A., and Stricker, D. Introducing a New Benchmarked Dataset for Activity Monitoring. In Proc. ISWC (2012). Google ScholarDigital Library
- Reiss, A. Personalized Mobile Physical Activity Recognition. Supporting Webpage (2013-05--28). www.sites.google.com/site/iswc2013personalized/.Google Scholar
- Roggen, D., Magnenat, S., Waibel, M., and Tröster, G. Wearable Computing: Designing and Sharing Activity Recognition Systems Across Platforms. IEEE Robotics & Automation Magazine 18, 2 (2011), 83--95.Google Scholar
- Stefano, C. D., Cioppa, A. D., and Marcelli, A. An Adaptive Weighted Majority Vote Rule for Combining Multiple Classifiers. In Proc. ICPR (2002), 192--195.Google ScholarCross Ref
- 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). Google ScholarDigital Library
- Weiss, G. M., and Lockhart, J. W. The Impact of Personalization on Smartphone-Based Activity Recognition. In Proc. AAAI Workshop on Activity Context Representation (2012).Google Scholar
- Zhao, Z., Chen, Y., Liu, J., Shen, Z., and Liu, M. Cross-People Mobile-Phone based Activity Recognition. In Proc. IJCAI (2011). Google ScholarDigital Library
Index Terms
- Personalized mobile physical activity recognition
Recommendations
Effects of Personalized and Aggregate Top-N Recommendation Lists on User Preference Ratings
Prior research has shown a robust effect of personalized product recommendations on user preference judgments for items. Specifically, the display of system-predicted preference ratings as item recommendations has been shown in multiple studies to bias ...
A novel confidence-based multiclass boosting algorithm for mobile physical activity monitoring
This paper addresses one of the main challenges in physical activity monitoring, as indicated by recent benchmark results: The difficulty of the complex classification problems exceeds the potential of existing classifiers. Therefore, this paper ...
Confidence-based multiclass AdaBoost for physical activity monitoring
ISWC '13: Proceedings of the 2013 International Symposium on Wearable ComputersPhysical activity monitoring has recently become an important topic in wearable computing, motivated by e.g. healthcare applications. However, new benchmark results show that the difficulty of the complex classification problems exceeds the potential of ...
Comments