An Ontology for Dynamic Sensor Selection in Wearable Activity Recognition
A strong effort has been made during the last years in the autonomous and automatic recognition of human activities by using wearable sensor systems. However, the vast majority of proposed solutions are designed for ideal scenarios, where the sensors are pre-defined, well-known and steady. Such systems are of little application in real-world settings, in which the sensors are subject to changes that may lead to a partial or total malfunctioning of the recognition system. This work presents an innovative use of ontologies in activity recognition to support the intelligent and dynamic selection of the best replacement for a given shifted or anomalous wearable sensor. Concretely, an upper ontology describing wearable sensors and their main properties, such as measured magnitude, location and internal characteristics is presented. Moreover, a domain ontology particularly defined to neatly and unequivocally represent the exact placement of the sensor on the human body is presented. These ontological models are particularly aimed at making possible the use of standard wearable activity recognition in data-driven approaches.
KeywordsOntologies Activity Recognition Wearable sensors Sensor selection Sensor placement Human anatomy
Unable to display preview. Download preview PDF.
- 1.Foundational Model of Anatomy ontology (FMA), http://sig.biostr.washington.edu/projects/fm/AboutFM.html
- 2.Linked data, http://linkeddata.org/
- 3.Uber anatomy ontology (Uberon), http://uberon.github.io/
- 5.BakhshandehAbkenar, A., Loke, S.W.: Myactivity: Cloud-hosted continuous activity recognition using ontology-based stream reasoning. In: 2014 2nd IEEE International Conference on Mobile Cloud Computing, Services, and Engineering, pp. 117–126 (2014)Google Scholar
- 6.Banos, O., Damas, M., Guillen, A., Herrera, L.-J., Pomares, H., Rojas, I., Villalonga, C.: Multi-sensor fusion based on asymmetric decision weighting for robust activity recognition. Neural Processing Letters, 1–22 (2014)Google Scholar
- 12.Mungall, C., Torniai, C., Gkoutos, G., Lewis, S., Haendel, M.: Uberon, an integrative multi-species anatomy ontology. Genome Biology 13(1), R5 (2012)Google Scholar
- 15.Patel, S., Mancinelli, C., Healey, J., Moy, M., Bonato, P.: Using wearable sensors to monitor physical activities of patients with copd: A comparison of classifier performance. In: Proceedings of 6th International Workshop on Wearable and Implantable Body Sensor Networks, Washington, DC, USA, pp. 234–239 (2009)Google Scholar