Radar Signal Sorting Based on Adaptive SOFM and Coyote optimization

In modern electronic warfare, the radar signal sorting method plays an important role in the electronic support measurement system. However, most of the traditional methods based on unsupervised clustering require prior information, such as the initial category centers and numbers, which has limitat...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2022 7th International Conference on Signal and Image Processing (ICSIP) s. 157 - 161
Hlavní autoři: Cui, Zongding, Fu, Xiongjun, Lang, Ping, Dong, Jian, Wu, Fei, Gao, Haodong
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 20.07.2022
Témata:
Clustering algorithms
coyote optimization algorithm clustering
Image processing
Neurons
Radar
Radar imaging
Radar measurements
self-organizing feature map
Self-organizing feature maps
signal sorting
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:In modern electronic warfare, the radar signal sorting method plays an important role in the electronic support measurement system. However, most of the traditional methods based on unsupervised clustering require prior information, such as the initial category centers and numbers, which has limitations in practical applications. To solve the problems mentioned above, a two-stage radar signal sorting method is proposed, which combines an improved self-organizing feature map (SOFM) network and coyote optimization algorithm, (i.e., SOCOA). In the first stage, the improved SOFM network is used to roughly sort the radar signals, and obtains the approximate number of categories and cluster center position of the input data. In the second stage, the coyote optimization algorithm is used to finely optimize the sorting process to obtain optimal results with the prior knowledge of the first stage. Experimental results show that our proposed method can improve the sorting performance without any prior information.
DOI:10.1109/ICSIP55141.2022.9886467