摘要
针对当前目标识别系统中常用的信息融合方法识别率较低、运行速度慢、抗噪性差等问题,提出一种基于神经网络组和DS证据理论的信息融合方法。该方法兼顾神经网络和DS推理二者的优势,有效地解决了目前信息融合方法对大噪声不确定性传感器测量信息的误识别问题。仿真实验表明,该方法是可行的,能有效地提高系统识别率及鲁棒性。
An information fusion method based on GNN （Group of Neural Network） and DS evidence they is presented to solve those problems of the low recognition rate, the slow running speed and the noise immunity of the object identification system at present. This method has the advantage of both neural and DS evidential theory and solves the problem. The simulation shows that the method is practicable and it can effectively enhance the efficiency and robustness of the target identification.
出处
《微计算机信息》
2009年第22期193-194,172,共3页
Control & Automation
关键词
信息融合
神经网络组
证据理论
目标识别
information fusion
group of neural network
evidence theory
target identification
