Abstract
Using a hybrid method of mm-wave frequency scanning and pattern-recognition techniques, a highly accurate chipless Radio Frequency Identification (RFID) system in 60 GHz free spectrum has been developed. It contains high encoding capacity chipless tag based on alphabetic characters printed onto a low-cost substrate. The individual tag is scanned with a pair of orthogonally polarized horn antennas in a few view angles within the 57-64 GHz band. The resulted cross-polar backscattered signal is processed to enable feature learning and classifications using different networks, such as Support Vector Machines (SVMs), K-Nearest neighbors (KNNs) and Ensembles. This method yields > 95% reading accuracy which demonstrates great improvement in many low-cost chipless tag applications.
Original language | English |
---|---|
Title of host publication | Proceedings of the 48th European Microwave Conference |
Editors | Ferran Martin, Francisco Mesa |
Place of Publication | Piscataway NJ USA |
Publisher | IEEE, Institute of Electrical and Electronics Engineers |
Pages | 973-976 |
Number of pages | 4 |
ISBN (Electronic) | 9782874870514, 9782874870507 |
ISBN (Print) | 9781538652855 |
DOIs | |
Publication status | Published - 2018 |
Event | European Microwave Conference 2018 - Madrid, Spain Duration: 23 Sep 2018 → 27 Sep 2018 Conference number: 48th https://ieeexplore.ieee.org/xpl/conhome/8528202/proceeding (Proceedings) |
Conference
Conference | European Microwave Conference 2018 |
---|---|
Abbreviated title | EuMC 2018 |
Country | Spain |
City | Madrid |
Period | 23/09/18 → 27/09/18 |
Internet address |
Keywords
- classification algorithms
- Hybrid chipless RFID
- Internet of Things
- nearest neighbor searches
- pattern analysis
- RFID tags
- support vector machines