Passive Radio Localization System Using Channel Impulse Response and Deep Learning
- Resource Type
- Conference
- Authors
- Batres, Amilcar Ernesto; Ouarab, Tamazight; Talbi, Larbi
- Source
- 2023 International Electrical Engineering Congress (iEECON) Electrical Engineering Congress (iEECON), 2023 International. :429-433 Mar, 2023
- Subject
- Aerospace
Bioengineering
Communication, Networking and Broadcast Technologies
Components, Circuits, Devices and Systems
Computing and Processing
Engineered Materials, Dielectrics and Plasmas
Engineering Profession
Fields, Waves and Electromagnetics
General Topics for Engineers
Geoscience
Nuclear Engineering
Photonics and Electrooptics
Power, Energy and Industry Applications
Robotics and Control Systems
Signal Processing and Analysis
Transportation
Radio frequency
Location awareness
Performance evaluation
Electrical engineering
Receiving antennas
Intrusion detection
Smart homes
device-free indoor localization
fingerprinting
channel impulse response
machine learning
SVM
Naive Bayes
deep learning
- Language
Device-free passive indoor localization is playing a crucial role in some applications like smart homes and intrusion detection. While most systems are designed to locate humans, this research demonstrates that it is possible to use a device-free passive technique to locate a small object in a Non Line Of Sight (NLOS) indoor environment using only one antenna acting as an emitter and another as a receiver. i.e., a single radio frequency (RF) link. The fingerprinting technique is used. The channel impulse response (CIR) is used as a signature, it is obtained by the IFFT of the channel frequency response. Signatures are matched to positions using machine learning (ML) techniques. The results show that it is possible to accurately locate an object of a few centimetres with good accuracy.