Ontological Sensor Selection for Wearable Activity Recognition

Wearable activity recognition has attracted very much attention in the recent years. Although many contributions have been provided so far, most solutions are developed to operate on predefined settings and fixed sensor setups. Real-world activity recognition applications and users demand more flexible sensor configurations, which may deal with potential adverse situations such as defective or missing sensors. A novel method to intelligently select the best replacement for an anomalous or nonrecoverable sensor is presented in this work. The proposed method builds on an ontology defined to neatly describe wearable sensors and their main properties, such as measured magnitude, location and internal characteristics. SPARQL queries are used to retrieve the ontological sensor descriptions for the selection of the best sensor replacement. The on-body location proximity of the sensors is considered during the sensor search process to determine the most adequate alternative.

[1]  Héctor Pomares,et al.  Daily living activity recognition based on statistical feature quality group selection , 2012, Expert Syst. Appl..

[2]  Marco Aiello,et al.  Ontology-based office activity recognition with applications for energy savings , 2014, J. Ambient Intell. Humaniz. Comput..

[3]  Héctor Pomares,et al.  Dealing with the Effects of Sensor Displacement in Wearable Activity Recognition , 2014, Sensors.

[4]  Ihn-Han Bae,et al.  An ontology-based approach to ADL recognition in smart homes , 2014, Future Gener. Comput. Syst..

[5]  Héctor Pomares,et al.  An Ontology for Dynamic Sensor Selection in Wearable Activity Recognition , 2015, IWBBIO.

[6]  Andrea Mannini,et al.  Activity recognition using a single accelerometer placed at the wrist or ankle. , 2013, Medicine and science in sports and exercise.

[7]  Miguel Damas,et al.  Multi-sensor Fusion Based on Asymmetric Decision Weighting for Robust Activity Recognition , 2014, Neural Processing Letters.

[8]  Ling Bao,et al.  Activity Recognition from User-Annotated Acceleration Data , 2004, Pervasive.

[9]  Claudio Bettini,et al.  OWL 2 modeling and reasoning with complex human activities , 2011, Pervasive Mob. Comput..

[10]  Amin Bakhshandehabkenar,et al.  MyActivity: Cloud-Hosted Continuous Activity Recognition Using Ontology-Based Stream Reasoning , 2014, 2014 2nd IEEE International Conference on Mobile Cloud Computing, Services, and Engineering.

[11]  Ilkka Korhonen,et al.  Detection of Daily Activities and Sports With Wearable Sensors in Controlled and Uncontrolled Conditions , 2008, IEEE Transactions on Information Technology in Biomedicine.

[12]  Héctor Pomares,et al.  On the Use of Sensor Fusion to Reduce the Impact of Rotational and Additive Noise in Human Activity Recognition , 2012, Sensors.

[13]  Chris D. Nugent,et al.  An Ontology-Based Hybrid Approach to Activity Modeling for Smart Homes , 2014, IEEE Transactions on Human-Machine Systems.