摘要
针对神经网络分类器容易陷入局部最小值和不适用于小样本的缺点,提出一种应用零中心瞬时特征提取法提取分类特征,采用支持向量机分类器进行数字调制信号识别的方法。与传统的神经网络方法相比,该方法具有更好的泛化推广能力。实验仿真结果表明,该调制识别方法在小样本下具有较高的识别率。
Aiming at the two shortcomings of easy to fall into local minimum and inappropriate for small sample of neural network classifier,a new method of modulation recognition for digital signals is proposed using zero-center instantaneous features extraction to extract characteristics and based on support vector machine(SVM).Compared with traditional algorithms based on neural networks,this algorithm has better generalization ability.Computer simulation results indicate that the method has the high recognition rate with less samples.
出处
《计算机与现代化》
2011年第3期1-4,共4页
Computer and Modernization
基金
国家自然科学基金资助项目(60772138)
国家863计划项目(2007AA01Z288)
高等学校学科创新引智计划项目(B08038)
关键词
调制识别
支持向量机
特征提取
modulation recognition
support vector machine
feature extraction