摘要
为了解决软件无线电系统中多种调制方式之间切换的问题,提出了一种基于支持向量机的多类数字调制方式识别算法.该算法通过提取有效的特征向量以区分不同的调制方式,并基于支持向量机和判决树分类思想,将特征向量映射到高维空间中加以分类,解决了样本在低维空间中的非线性不可分问题,避免了判决门限的确定,与传统的神经网络方法相比,具有更好的泛化推广能力.仿真结果表明,在具有加性带限高斯噪声的环境下,信噪比大于等于10dB时,识别正确率大于90%.
In order to solve the problem of conversion of multi-class modulation types which exists in software radio system, an algorithm based on support vector machine (SVM) for recognition of digital modulation signals was presented. By analyzing the modulation signals, a set of key features for identifying different types of digital modulation were extracted, and were mapped into the high dimension space. The classification was carried out in the high dimension space based on SVM and decision tree, so the problem of nonlinear non-separable classification in low dimension was resolved and the decision threshold became unnecessary. Better generalization ability was also acquired comparing with traditional neural networks. Experiment on six digital modulation signals corrupted by band-limited Gaussian noise was conducted. The results show that all types of digital modulation are classified with success rate that is more than 90% when SNR is not less than 10 dB.
出处
《西安交通大学学报》
EI
CAS
CSCD
北大核心
2004年第6期619-622,共4页
Journal of Xi'an Jiaotong University
基金
国家自然科学基金资助项目(90207012)
关键词
支持向量机
调制方式识别
软件无线电
特征提取
Algorithms
Digital signal processing
Feature extraction
Gaussian noise (electronic)
Modulation
Neural networks
Radio systems
Signal to noise ratio
