基于最小二乘SVM的混沌跳频通信码预测方法

Chaotic-FH Code Prediction Method Based on LS-SVM

作为一种用于解决诸如非线性分类,函数估计,密度估计一类问题有力的解决方法,支持向量机近来在其他许多基于核函数学习领域得到发展。基于混沌跳频码的动力系统特性,本文构建了一种支持向量机的预测模型,并采用最小二乘法对模型进行训练,最后通过L-K映射生成的跳频码序列对模型进行了验证,仿真结果表明这种高精度的支持向量机用于针对基于混沌映射的跳频码的预测,具有很低的均方误差和高相关系数良好性能。

Support vector machine （SVM） is a powerful method for solving problems such as nonlinear classification, function estimation and density estimation. It has also achieved great developments in many other kernelbased learning fields recently. Based on the chaotic-FH code characteristics in chaotic dynamic system, a prediction model of support vector machine in combination with Takens＇ delay coordinate phase reconstruction of chaotic time is established; and least square model for large-scale problems is used to train this model. Finally an FH-code series generated by Logistic-Kent mapping is applied to test the model. Simulation results show that this high-accuracy and fault-tolerant SVM model has an excellent performance with very low mean square error and high correlation coefficient in chaotic-FH code prediction.