| 摘要: |
| 天波雷达的干扰检测问题可转化为距离-多普勒(Range-Doppler,RD)图像分类。在RD图分类器设计中，使用K近邻(K-Nearest Neighbor,KNN)算法时，玨值的选取直接影响到干扰检测准确率。根据过往经验预设玨值时，无法确定所设玨值下的干扰检测准确率。为此，将互近邻条件引申为玨值自动赋值方法，以局部均值为距离计算依据，设计动态自适应近邻(Dynamic Adaptive Nearest Neighbor,DANN)新算法。分别在多个UCI(University of California Irvine)数据集与现有RD图库上测试，与6个常数玨值下K近邻算法进行对比分析。多个UCI数据集实验表明，DANN的平均准确率比不同玨值下KNN的均值高6.21%，且比最优玨值高3.7%；实测RD图库实验表明，DANN的平均准确率比不同玨值下KNN的均值高2.9%，且比最优玨值高0.56%。因此，该算法可以在干扰检测中减少人工参与，且能够获得较高的检测准确率。 |
| 关键词: 天波雷达 干扰检测 RD图像分类 自适应近邻 |
| DOI：10.20079/j.issn.1001-893x.230504005 |
|
| 基金项目:国家自然科学基金资助项目（61701067，61702065） |
|
| RD Image Classifier Design Based on Dynamic Adaptive Nearest Neighbor Algorithm for Sky Wave Radar |
| LUO Zhongtao,TANG Hongtao,GAO Tianao,CAO Jian |
| (1.School of Communication and Information Engineering,Chongqing University of Posts and Telecommunications,Chongqing 400065,China;2.Nanjing Research Institute of Electronics Technology,Nanjing 210013,China) |
| Abstract: |
| The interference detection problem of sky wave radar can be converted into range-Doppler (RD) image classification.When K-nearest neighbor (KNN) algorithm is used in the design of RD image classifier,the selection of 玨 value directly affects the accuracy of interference detection.The 玨 values is required to be preset according to past experience,but the accuracy of interference detection cannot be anticipated under the set 玨 values.Therefore,the authors extend the mutual nearest neighbor condition to the 玨 value automatic assignment method,and by using the local mean as the distance calculation basis,designs a new dynamic adaptive nearest neighbor (DANN) algorithm.The proposed algorithm is testel on multiple University of Calitornia Irvine(UCI) datasets and existing RD image dataset,and compared with the KNN algorithm with 6 constant 玨 values.Multiple UCI dataset experiments show that the average accuracy of DANN is 6.21% higher than the mean of KNN under different 玨 values,and 3.7% higher than the optimal 玨 value.The real RD image dataset experiment shows that the average accuracy of DANN is 2.9% higher than the mean of KNN under different 玨 values,and 0.56% higher than the optimal 玨 value.The proposed algorithm can reduce manual involvement in interference detection and obtain a better detection accuracy. |
| Key words: sky wave radar interference detection range-Doppler image classification adaptive nearest neighbor |
