Radar Signal Sorting Based on Adaptive SOFM and Coyote optimization

Cui, Zongding; Fu, Xiongjun; Lang, Ping; Dong, Jian; Wu, Fei; Gao, Hongbo

doi:10.1109/icsip55141.2022.9886467

Cited by 1 publication

(1 citation statement)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In 2022, Zhu [10] proposed a presorting method based on a Mean‐Shift algorithm, improving the sorting accuracy and performance. Also in 2019, Su [11] combined the density dynamic clustering and Self‐Organising Features Maps (SOFM) natural network with the K ‐Means algorithm, and in 2022, Cui [12] proposed the SOCOA algorithm, combining an improved SOFM network and a Coyote Optimisation Algorithm. These neural network‐based innovations have provided many alternative methods for presorting; however, there is a notable absence of methods for main sorting.…”

Section: Introductionmentioning

confidence: 99%

A novel deinterleaving method for radar pulse trains using pulse descriptor word dot matrix images and cascade‐recurrent loop network

Chen,

Liu,

Guo

et al. 2023

IET Radar Sonar & Navi

View full text Add to dashboard Cite

Traditional signal deinterleaving methods depend on preset parameters, use complicated steps and have limitations in handling complex electromagnetic environments where signals overlap in the space, time and frequency domains. This paper presents a novel approach using a deep segmentation network for radar signal deinterleaving. The pulse descriptor word data is transformed into a dot matrix image, which is then processed by a Cascade‐Recurrent Loop Network (CRLN) for segmentation. The CRLN consists of a Type Segmentation Network, an Amount Decision Network and a Recurrent Individual Segmentation Network. By recursively segmenting each target and determining the number of sources, the CRLN overcomes the challenges posed by the discontinuity and high overlap of individuals in the dot matrix image. Experimental results demonstrate the effectiveness of the proposed method, surpassing traditional deinterleaving methods, achieving high accuracy, low omission rate and effectively mitigates the increasing batch problem in complex scenarios. The experiments conducted on a randomly generated dataset yielded impressive results: over 90% accuracy when dealing with pulses from 15 radars of different types, over 96% accuracy when deinterleaving pulses from 4 radar individuals of a same type and over 90% accuracy when handling 5 radars of different types with 10% pulse loss.

show abstract

Section: Introductionmentioning

confidence: 99%