Child-activity recognition from multi-sensor data

Authors:
Sabri Boughorbel;Jeroen Breebaart;Fons Bruekers;Ingrid Flinsenberg;Warner ten Kate
Affiliations:
Philips Research Laboratories Eindhoven, Eindhoven, The Netherlands;Philips Research Laboratories Eindhoven, Eindhoven, The Netherlands;Philips Research Laboratories Eindhoven, Eindhoven, The Netherlands;Philips Research Laboratories Eindhoven, Eindhoven, The Netherlands;Philips Research Laboratories Eindhoven, Eindhoven, The Netherlands
Venue:
Proceedings of the 7th International Conference on Methods and Techniques in Behavioral Research
Year:
2010

Citing 5
Cited 1

Pattern Classification (2nd Edition)

Pattern Classification (2nd Edition)
Capturing human motion using body-fixed sensors: outdoor measurement and clinical applications: Research Articles

Computer Animation and Virtual Worlds
Activity Recognition and Monitoring Using Multiple Sensors on Different Body Positions

BSN '06 Proceedings of the International Workshop on Wearable and Implantable Body Sensor Networks
Activity Recognition of Assembly Tasks Using Body-Worn Microphones and Accelerometers

IEEE Transactions on Pattern Analysis and Machine Intelligence
Activity recognition from accelerometer data

IAAI'05 Proceedings of the 17th conference on Innovative applications of artificial intelligence - Volume 3

Improving the classification accuracy of streaming data using SAX similarity features

Pattern Recognition Letters

Quantified Score

Hi-index	0.01

Visualization

Abstract

The automatic recognition of child activity using multi-sensor data enables various applications such as child-development monitoring, energy-expenditure estimation, child-obesity prevention, child safety in and around the home, etc. We formulate the activity recognition task as a classification problem based on multiple sensors embedded in a wearable device. The approach we propose in this paper isto apply spectral analysis techniques of multiple sensor data for activity recognition. Quadratic Discriminant Analysis (QDA) classifieris then trained using manually annotated data and applied for activity recognition. The obtained experimental results for the recognition of 7 activities based on a limited data set are promising and show the potential of the proposed method.