摘要
水下目标识别在鱼雷水下武器反对抗中占有重要的地位,模糊聚类与神经网络相结合,广泛应用在模式识别的各个领域;在FCM算法中,考虑到样本矢量中各维特征对目标分类的不同影响,提出一种基于特征加权的改进FCM算法,使数据更有效的分类;将改进的FCM算法与改进RBF神经网络结合起来建模,充分利用二者的优点,运用到水下目标识别的分类中,得到满意的结果,提高了鱼雷跟踪定位目标的可靠性。
Underwater targets identified in anti-submarine torpedoes, occupy an important position. Fuzzy Clustering and neural network integration, has been widely used in various fields of pattern recognition. In FCM algorithm, taking into account samples of the different effects of vector-dimensional characteristics to the target classification, introduce a algorithm based on weight to improve FCM, making the data classification more effective. Making the improved FCM algorithm and the improved RBF neural network combined with modeling, taking full use of the advantages of the two, bringing to the classification of underwater target identification, get a satisfied results.
出处
《计算机测量与控制》
CSCD
北大核心
2009年第5期954-956,共3页
Computer Measurement &Control
基金
国家水下信息处理与控制重点实验室基金项目(9140C2304100807)
