Julien Rebetez
ABSTRACT
Activity recognition has recently gained a lot of interest and there already exist several methods to detect human activites based on wearable sensors. Most of the existing methods rely on a database of labelled activities that is used to train an offline activity recognition system. This paper presents an approach to build an online activity recognition system that do not require any a priori labelled data. The system incrementally learns activities by actively querying the user for labels. To choose when the user should be queried, we compare a method based on random sampling and another that uses a Growing Neural Gas (GNG). The use of GNG helps reducing the number of user queries by 20% to 30%.
- Beyer, O., and Cimiano, P. Online labelling strategies for growing neural gas. In Proceedings of the 12th international conference on Intelligent data engineering and automated learning, Springer-Verlag (2011), 76--83. Google Scholar
Digital Library
- Fritzke, B. A growing neural gas network learns topologies. In Advances in Neural Information Processing Systems 7, MIT Press (1995), 625--632.Google Scholar
- Hamker, F. H. Life-long learning cell structures - continuously learning without catastrophic interference. Neural Networks 14, 4 (2001), 551--573. Google ScholarDigital Library
- Hasenjager, K., Ritter, H., and Obermayer, K. Active learning in self-organizing maps. Kohonen maps (1999), 57--70.Google Scholar
- Kapoor, A., and Horvitz, E. Experience sampling for building predictive user models: a comparative study. In Proceedings of the twenty-sixth annual SIGCHI conference on Human factors in computing systems, ACM (2008), 657--666. Google ScholarDigital Library
- Lara O. D. et al. Centinela: A human activity recognition system based on acceleration and vital sign data. Pervasive and Mobile Computing 8, 5 (2012), 717--729. Google ScholarDigital Library
- Longstaff, B., Reddy, S., and Estrin, D. Improving activity classification for health applications on mobile devices using active and semi-supervised learning. In Pervasive Computing Technologies for Healthcare, IEEE (2010), 1--7.Google Scholar
- Mayrhofer, R., and Radi, H. Extending the growing neural gas classifier for context recognition. In Computer Aided Systems Theory--EUROCAST 2007. Springer, 2007, 920--927. Google ScholarDigital Library
- Sagha, H. et al. Benchmarking classification techniques using the Opportunity human activity dataset. In IEEE International Conference on Systems, Man, and Cybernetics (2011).Google ScholarCross Ref
- Stikic, M., Van Laerhoven, K., and Schiele, B. Exploring semi-supervised and active learning for activity recognition. In Wearable Computers, 2008. ISWC 2008. 12th IEEE International Symposium on, IEEE (2008), 81--88. Google ScholarDigital Library
Index Terms
- Reducing user intervention in incremental activityrecognition for assistive technologies
Recommendations
An intervention mechanism for assistive living in smart homes
In order to support ageing in place for elderly people, technologies and services for home environments need to be developed. An intervention mechanism is proposed in this paper in a smart home environment to provide reminders to assist elderly ...
An incremental online semi-supervised active learning algorithm based on self-organizing incremental neural network
Special Issue on ICONIP2009An incremental online semi-supervised active learning algorithm, which is based on a self-organizing incremental neural network (SOINN), is proposed. This paper describes improvement of the two-layer SOINN to a single-layer SOINN to represent the ...
SuperAD: supervised activity discovery
UbiComp/ISWC'15 Adjunct: Adjunct Proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2015 ACM International Symposium on Wearable ComputersActivity recognition (AR) has become an essential component of many applications present in our everyday lives such as life-logging, fitness tracking, health and wellbeing monitoring. To build an AR system, one needs to first identify a set of ...
Comments