摘要
基于复杂非线性系统的相空间重构理论,提出了一种基于遗传算法的支持向量机预测方法.利用改进的自相关法和饱和关联维数法确定混沌信号的时间延迟和嵌入维,从而实现相空间重构.通过遗传算法优化支持向量机中的惩罚系数和核函数参数,并结合支持向量机建立混沌序列的单步预测模型,从预测误差中检测出淹没在混沌背景中的微弱信号(包括瞬态信号和周期信号).以Lorenz系统和加拿大McMaster大学利用IPIX雷达实测得到的海杂波数据作为混沌背景噪声进行仿真实验,结果表明该方法能够有效地从混沌背景噪声中检测出微弱目标信号,所得的均方根误差为0.00049521(信噪比为-89.7704 dB),这比传统支持向量机方法的均方根误差(0.049,信噪比为-54.60 dB)降低了两个数量级.
According to the phase space reconstruction theory of nonlinear system, we propose a prediction method of support vector machine based on genetic algorithm. Using the improved autocorrelation method and Grassberger-Procaccia algorithm to determine the time delay and embedding dimension of chaotic signal, the phase space reconstruction is implemented. The penalty coefficient and the kernel function parameter of support vector machine are optimized by genetic algorithm. Combined with support vector machine, single-step prediction model of the chaotic sequence is set up, so we can detect the weak signal in chaos from the prediction error （including the transient signal and periodic signal）. Lorenz attractor and the data from the McMaster IPIX radar sea clutter database are used in the simulation. The proposed method can effectively detect the weak target from chaotic signal. When the signal-to-noise ratio is -89.7704 dB in the chaotic noise background, by using the new method the root mean square error can be reduced by two orders of magnitude, reaching 0.00049521, while the conventional support vector machine can reach only 0.049 under the condition of -54.60 dB.
出处
《物理学报》
SCIE
EI
CAS
CSCD
北大核心
2014年第10期41-47,共7页
Acta Physica Sinica
基金
国家自然科学基金(批准号:61072133)
江苏省产学研联合创新计划(批准号:BY2013007-02
BY2011112)
江苏省高等学校科研成果产业化推进计划(批准号:JHB2011-15)
江苏省"六大人才高峰"计划资助的课题~~
关键词
支持向量机
遗传算法
海杂波
相空间重构
support vector machine
genetic algorithm
sea clutter
phase space reconstruction
作者简介
E-mail：xinghy@nuist．edu．cn
