Class incremental radar radiation source individual intelligent identification method based on K center feature distribution reconstruction

Through the method based on K-center feature distribution reconstruction, the catastrophic forgetting problem in individual recognition of radar radiation sources under incremental conditions is solved, which improves the recognition accuracy under small sample conditions and ensures data privacy.

CN119669824AActive Publication Date: 2025-03-21XIDIAN UNIV
3 Cites 0 Cited by

Patent Information

Application Number
CN202411726953.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-11-28
Publication Date
2025-03-21
Estimated Expiration
2044-11-28

AI Technical Summary

Technical Problem

The prior art radar radiation source individual identification method in incremental situations has catastrophic forgetting, and it is difficult to improve the recognition accuracy under small sample conditions. At the same time, it is necessary to ensure the privacy of individual data sets of radar radiation source individuals.

Method used

An intelligent identification method of individuals of a kind-incremental radar radiation source based on K-center feature distribution reconstruction is adopted to generate a noise-free radar radiation source data set through simulation, a pre-trained feature extractor is constructed, and a modified supervised comparison loss function is used for training. The training set features of each class are extracted based on K-means, and pseudo-features are generated to reconstruct the distribution of old class features, and merge new class features for training of network classifiers.

Benefits of technology

It significantly improves the accuracy of individual recognition of radar radiation sources under small sample conditions, reduces the catastrophic forgetting caused by class increments, and ensures the privacy of data without the need to save the original data.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention relates to a class incremental radar radiation source individual intelligent identification method based on K center feature distribution reconstruction, and belongs to the technical field of radar data processing. Comprising the steps that an initial category data set is generated through simulation, the initial category data set serves as input of a feature extractor, the feature extractor is trained based on an improved supervised contrast loss function, and the feature extractor is adopted for feature extraction to obtain training set features; performing K-means-based multi-center extraction on the training set features of each class to obtain each cluster center of each class as a K center set of the class of features and points contained in a cluster where the K center is located, and generating points of noise around the K center as pseudo features; and combining the pseudo features and the new features, and training a network classifier. According to the method, the task of radar radiation source individual incremental recognition under the small sample condition can be processed, and the generalization of the model is remarkably improved.
Need to check novelty before this filing date? Find Prior Art