| Autor: |
Jian Zhang, Di Wu, Tao Hu, Shu Wang, Shiju Wang, Tingli Li |
| Rok vydání: |
2022 |
| Zdroj: |
Proceeding of 2021 International Conference on Wireless Communications, Networking and Applications ISBN: 9789811924552 |
| DOI: |
10.1007/978-981-19-2456-9_88 |
| Popis: |
Open-set recognition in blind shortwave signal processing is an important issue in modern communication signal processing. This paper presents a novel method for this problem. By preprocessing, the signal data matrix and vector diagram are obtained as network input. Then, the network is trained and tested with the known signal, and the upper and lower quintile algorithm is used to obtain the interval threshold for judging the known signal and the distance threshold for intercepting the length range of the unknown signal. Finally, the network is used for numerical regression in open-set range, the threshold combined with kernel density clustering algorithm is used to identify different signals. Simulation results show that the proposed method overcomes the defects of traditional algorithm, which cannot distinguish different types of unknown signals and only applicable for few signal types. |
| Databáze: |
OpenAIRE |
| Externí odkaz: |
|
