Radio Tomographic Imaging Localization Based on Transformer Model
- Resource Type
- Conference
- Authors
- Lu, Zhichao; Liu, Heng; Zhang, Xueming
- Source
- 2023 IEEE 6th Information Technology,Networking,Electronic and Automation Control Conference (ITNEC) Information Technology,Networking,Electronic and Automation Control Conference (ITNEC), 2023 IEEE 6th. 6:1134-1138 Feb, 2023
- Subject
- Communication, Networking and Broadcast Technologies
Computing and Processing
Engineering Profession
Power, Energy and Industry Applications
Robotics and Control Systems
Signal Processing and Analysis
Location awareness
Deep learning
Radio frequency
Wireless sensor networks
Automation
Inverse problems
Computational modeling
Radio tomographic imaging
wireless sensor network
Transformer
deep learning
- Language
- ISSN
- 2693-3128
Device-free localization (DFL) is an indispensable part of disaster relief and anti-terrorism operations. Radio tomographic imaging (RTI) emerges for locating targets in the area by using received signal strength (RSS) measurements from a wireless sensor network. In this paper, we briefly analyze the forward model of RTI and proposes a deep learning based RTI method to achieve multi-target location with high precision. Compared with the traditional RTI algorithm, this method has advantages in distinguishing multiple targets and computing efficiency. Simulation and experimental results verify the effectiveness of the proposed method.