Designing Multi-Task Convolutional Variational Autoencoder for Radio Tomographic Imaging

Radio tomographic imaging (RTI) emerges to model the environment and detect the passive targets by a wireless network. In this work, the received signal strength (RSS) measurements are collected from an uncalibrated network, and a multi-task convolutional variational autoencoder model is proposed to...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on circuits and systems. II, Express briefs Vol. 69; no. 1; pp. 219 - 223
Main Authors: Wu, Hongzhuang, Ma, Xiaoli, Liu, Songyong
Format: Journal Article
Language:English
Published: New York IEEE 01.01.2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Attenuation
Calibration
Convolution
convolutional neural network
Image classification
Image reconstruction
multi-task learning
Noise level
Noise levels
Noise measurement
Radio tomographic imaging
Signal strength
Target detection
Tomography
variational autoencoder
Wireless networks
ISSN:1549-7747, 1558-3791
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Radio tomographic imaging (RTI) emerges to model the environment and detect the passive targets by a wireless network. In this work, the received signal strength (RSS) measurements are collected from an uncalibrated network, and a multi-task convolutional variational autoencoder model is proposed to realize RTI. The presented model is trained end-to-end to denoise the RSS measurements, reconstruct the static tomographic images, estimate the parameters of the wireless network, and classify the measurement noise level, simultaneously. The multi-task variational learning strategy is able to improve the generalization of the model. Numerical experiments demonstrate the efficacy of our RTI method.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1549-7747
1558-3791
DOI:10.1109/TCSII.2021.3081997