Paper Info
Title
VibroSense: Recognizing home activities by deep learning subtle vibrations on an interior surface of a house from a single point usingLaser Doppler Vibrometry
Abstract
Smart homes of the future are envisioned to have the ability to recognize many types of home activities such as running a washing machine, flushing the toilet, and using a microwave. In this paper, we present a new sensing technology, VibroSense, which is able to recognize 18 different types of activities throughout a house by observing structural vibration patterns on a wall or ceiling using a laser Doppler vibrometer. The received vibration data is processed and sent to a deep neural network which is trained to distinguish between 18 activities. We conducted a system evaluation, where we collected data of 18 home activities in 5 different houses for 2 days in each house. The results demonstrated that our system can recognize 18 home activities with an average accuracy of up to 96.6%. After re-setup of the device on the second day, the average recognition accuracy decreased to 89.4%. We also conducted follow-up experiments, where we evaluated VibroSense under various scenarios to simulate real-world conditions. These included simulating online recognition, differentiating between specific stages of a device's activity, and testing the effects of shifting the laser's position during re-setup. Based on these results, we discuss the opportunities and challenges of applying VibroSense in real-world applications.
Year
DOI
Venue
2020
10.1145/3411828
Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
Keywords
DocType
Volume
Deep learning,Home activity recognition,Laser Doppler Vibrometry,Structural vibration
Journal
4
Issue
ISSN
Citations 
3
2474-9567
0
PageRank 
References 
Authors
0.34
44
10
Name
Order
Citations
PageRank
Wei Sun101.35
Tuochao Chen200.34
Jiayi Zheng300.68
Zhenyu Lei400.34
Lucy Wang500.34
Benjamin Steeper601.69
Peng He700.68
Matthew Dressa800.34
Feng Tian922844.58
Cheng Zhang1018216.88