基于多属性决策的模糊特征目标识别

Fuzzy Feature Target Recognition Based on Multi-attribute Decision-making

针对指挥与控制系统在目标识别过程中的模糊特征信息导致目标识别准确率低的问题,提出基于多属性决策的模糊特征目标识别方法。首先,引入三角模糊数,将观测值转化为模糊数;然后,使用加权欧式距离计算目标相似度,并使用基于指标相关性的权重确定(criteria importance through intercriteria correlation,CRITIC)方法得到目标特征属性权重,基于目标相似度和特征属性权重构建加权相似度矩阵;最后,使用相对熵排序法计算出目标贴近度排序,识别出目标。基于多个指标的仿真结果表明,所提方法提高了目标识别准确率和系统的目标识别能力。

For the problem of low target recognition accuracy caused by fuzzy feature information in the process of target recognition in command and control system,a fuzzy feature target recognition method based on multiattribute decision-making is proposed.Firstly,triangular fuzzy numbers are introduced to convert the observed values into fuzzy numbers.Then,the weighted Euclidean distance is used to calculate target similarity.At the same time,the method of criteria importance through intercriteria correlation(CRITIC)is used to obtain the weight of the target feature attributes.The weighted similarity matrix is constructed based on the two indexes of target similarity and feature attribute weight.Finally,the relative entropy sorting method is used to calculate the target closeness degree to sort and identify the target.The simulation results based on multiple indexes show that the proposed method has high target recognition accuracy and improves the target recognition ability of the system.