ActiviTune: a multi-stage system for activity recognition of passive entities from ambient FM-Radio signals

Authors:
Shuyu Shi;Stephan Sigg;Yusheng Ji
Affiliations:
National Institute of Informatics, Tokyo, Japan;National Institute of Informatics, Tokyo, Japan;National Institute of Informatics, Tokyo, Japan
Venue:
WASA'13 Proceedings of the 8th international conference on Wireless Algorithms, Systems, and Applications
Year:
2013

Citing 8
Cited 0

Spine versus Porcupine: A Study in Distributed Wearable Activity Recognition

ISWC '04 Proceedings of the Eighth International Symposium on Wearable Computers
Challenges: device-free passive localization for wireless environments

Proceedings of the 13th annual ACM international conference on Mobile computing and networking
Dynamic clustering for tracking multiple transceiver-free objects

PERCOM '09 Proceedings of the 2009 IEEE International Conference on Pervasive Computing and Communications
Radio Tomographic Imaging with Wireless Networks

IEEE Transactions on Mobile Computing
At the flick of a switch: detecting and classifying unique electrical events on the residential power line

UbiComp '07 Proceedings of the 9th international conference on Ubiquitous computing
Continuous activity recognition in a maintenance scenario: combining motion sensors and ultrasonic hands tracking

Pattern Analysis & Applications
Mobility detection using everyday GSM traces

UbiComp'06 Proceedings of the 8th international conference on Ubiquitous Computing
FM-based indoor localization

Proceedings of the 10th international conference on Mobile systems, applications, and services

Quantified Score

Hi-index	0.00

Visualization

Abstract

The amplitude of a received RF-signal is affected by physical phenomena, such as reflection, refraction or scattering due to objects and individuals in the signal propagation path. Activities in the proximity of a receiver can thus induce a characteristic pattern on amplitude-based features. We investigate the use of the radio frequency channel to detect activities. ActiviTune, our passive device-free recognition system, implements a multi-stage classifier to recognise activities and situations in an indoor environment leveraging amplitude-based features of RF signals from an ambient FM radio source. Comparing with other RF-based approaches, ActiviTune has the advantage of neither installing a transmitter generating the signal nor equipping the monitored entities with any active component of the system. We experimentally demonstrate the distinction of two dynamic activities, 'walking', 'crawling', and three static activities, 'empty room', 'standing', 'lying' with an average true positive rate of over 80%.