摘要
捕获是卫星导航接收机中信号处理的第一步,对接收机的各项指标如灵敏度、动态性能等有重要影响。捕获算法中最重要的环节之一是判断是否已捕获到信号,在并行捕获算法中是通过对并行相关结果进行峰值检测实现的。结合机器学习技术,将峰值检测看作是对相关结果的二分类问题。首先,在MATLAB中重复运行并行捕获算法得到包含足够数量的相关结果组成样例集;然后,使用二分类学习算法对率回归从样例集中学得一个二分类学习器,并对分类器的性能进行分析,分析结果表明了方法的可行性和正确性;最后,指出了该方法需继续研究完善的地方,为后续工程实现该方法奠定了基础。
Acquisition is the first step of signal processing in satellite navigation receiver,and it has a great influence on receiver’s various indexes such as sensitivity,dynamic performance etc. One of most important steps in acquisition is to decide whether the signal has been acquired or not,and it is achieved by peak detection with parallel correlation result. In combination of machine learning techniques,peak detection can be regarded as a binary classification problem with correlation result. Firstly,adequate correlation results are obtained by running acquisition algorithm repeatedly in MATLAB,these results compose example set;Then,a binary classifier is learned from example set with binary learning algorithm such as logistic regression,and an analysis is made for the classifier,the analysis result indicates feasibility and correctness of the method;Finally,some drawbacks of the method needed to be studied and improved in follow-up work is stated briefly to establish the foundation for the following implementation in engineering.
作者
贾彬彬
刘俊莹
JIA Bin-bin;LIU Jun-ying(College of Electrical and Information Engineering,Lanzhou University of Technology,Lanzhou,Gansu 730050,China;KeyLaboratory of Gansu Advanced Control for Industrial Processes (Lanzhou University of Technology),Lanzhou,Gansu 730050,China;National Demonstration Center for Experimental Electrical and Control Engineering Education,Lanzhou University of Technology,Lanzhou,Gansu 730050,China)
出处
《计算技术与自动化》
2019年第1期43-48,共6页
Computing Technology and Automation
基金
甘肃省自然科学基金资助项目(1610RJYA007,1610RJYA026)
甘肃省工业过程先进控制重点实验室开放课题资助项目(XJK201517)
关键词
机器学习
卫星导航
捕获
峰值检测
对率回归
machine learning
satellite navigation
acquisition
peak detection
logistic regression