A Hybrid Approach for Recognizing ADLs and Care Activities Using Inertial Sensors and RFID

Authors:
Albert Hein;Thomas Kirste
Affiliations:
Institute of Computer Science, University of Rostock, Rostock, Germany;Institute of Computer Science, University of Rostock, Rostock, Germany
Venue:
UAHCI '09 Proceedings of the 5th International on ConferenceUniversal Access in Human-Computer Interaction. Part II: Intelligent and Ubiquitous Interaction Environments
Year:
2009

Citing 10
Cited 0

RFID-based techniques for human-activity detection

Communications of the ACM - Special issue: RFID
Fine-Grained Activity Recognition by Aggregating Abstract Object Usage

ISWC '05 Proceedings of the Ninth IEEE International Symposium on Wearable Computers
Practical Lessons from Place Lab

IEEE Pervasive Computing
Data Mining: Practical Machine Learning Tools and Techniques, Second Edition (Morgan Kaufmann Series in Data Management Systems)

Data Mining: Practical Machine Learning Tools and Techniques, Second Edition (Morgan Kaufmann Series in Data Management Systems)
Common sense based joint training of human activity recognizers

IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence
A hybrid discriminative/generative approach for modeling human activities

IJCAI'05 Proceedings of the 19th international joint conference on Artificial intelligence
Detection Of Normal and Novel Behaviours In Ubiquitous Domestic Environments

The Computer Journal
Towards an integrated approach for task modeling and human behavior recognition

HCI'07 Proceedings of the 12th international conference on Human-computer interaction: interaction design and usability
Scalable recognition of daily activities with wearable sensors

LoCA'07 Proceedings of the 3rd international conference on Location-and context-awareness
Activity classification using realistic data from wearable sensors

IEEE Transactions on Information Technology in Biomedicine

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper we present a feasibility study regarding the recognition of high level daily living and care activities. We examine a hybrid discriminative and model based generative approach based on RFID and inertial sensor data. We show that the presented sensor configuration is able to deliver sensor readings and object sightings at a sufficient rate without forcing user compliance. We further evaluated the advantage of a model based approach over a static classifier, compared the individual contribution of each sensor type and could reach accuracy rates of 97% and 85%.