基于双层随机森林的空袭目标识别

Air strike target recognition based on a double-layer random forest

空袭目标识别是防空作战指挥决策的关键环节,针对空袭目标特征繁杂容易造成模型拟合和识别精度不高这一问题,为提高空袭目标的识别能力,提出了一种基于双层随机森林的空袭目标识别算法。该算法在第一层随机森林通过计算基尼指数变化量对特征进行重要性评估和优选,然后在第二层随机森林进行数据降维和目标识别,相较传统随机森林能够提高目标识别的准确率和稳定性。将该算法与传统随机森林、支持向量机和PNN神经网络进行对比分析,仿真结果表明该算法能够在保证识别准确率的基础上同时具有较高的识别速度和识别稳定性。

Air strike target recognition is a key link in air defense combat command decision-making.Aiming at the problem that the complex features of air strike targets can easily cause model over-fitting and a low recognition accuracy,in order to improve the recognition ability of air strike targets,this paper proposes an air strike target recognition algorithm based on a double-layer random forest.The algorithm evaluates and optimizes the importance of features in the first layer of the random forest by calculating the Gini index change,and then performs data dimensionality reduction and target recognition in the second layer.Compared with traditional random forests,it can improve the accuracy and stability of target recognition.The algorithm is compared and analyzed with the traditional random forest,support vector machine and PNN neural network.The simulation results show that the algorithm ensures the recognition accuracy and has a high recognition speed and recognition stability at the same time.