联合时域和时频域特征的数字调制信号自动分类
发布时间：2018-09-10 15:51
【摘要】：针对ASK、PSK、QAM、FSK、MSK、LFM、OFDM信号的调制分类问题,在无任何先验知识的条件下,本文提出了一种基于模糊函数域、Choi-William分布时频域和时域特征的自动分类算法。该算法首先提取信号在不同域上的特征,然后通过主成份分析法降维去除特征之间的冗余信息,再利用支持向量机分类器实现信号分类。为评估算法性能及优点,本文在不同信噪比和调制信号参数条件下,做了一系列仿真实验,并将本文算法与其他分类识别算法进行了对比。最后结果验证了本文算法的可行性和有效性,以及在低信噪比条件下较好的鲁棒性。
[Abstract]:For the modulation classification of ASK,PSK,QAM,FSK,MSK,LFM,OFDM signals, an automatic classification algorithm based on the time-frequency and time-domain features of Choi-William distribution in fuzzy function domain is proposed without any prior knowledge. The algorithm firstly extracts the features of the signals in different domains, then reduces the dimension of the features by using the principal component analysis method to remove the redundant information between the features, and then realizes the signal classification by using the support vector machine classifier. In order to evaluate the performance and advantages of the algorithm, a series of simulation experiments are done under different SNR and modulation signal parameters, and the algorithm is compared with other classification and recognition algorithms. Finally, the feasibility and effectiveness of the proposed algorithm and its robustness under low signal-to-noise ratio (SNR) are verified.
【作者单位】： 武汉大学电子信息学院;
【基金】：湖北省自然科学基金青年基金项目(2015CFB202)资助课题
【分类号】：TN911.3
本文编号：2234903
[Abstract]:For the modulation classification of ASK,PSK,QAM,FSK,MSK,LFM,OFDM signals, an automatic classification algorithm based on the time-frequency and time-domain features of Choi-William distribution in fuzzy function domain is proposed without any prior knowledge. The algorithm firstly extracts the features of the signals in different domains, then reduces the dimension of the features by using the principal component analysis method to remove the redundant information between the features, and then realizes the signal classification by using the support vector machine classifier. In order to evaluate the performance and advantages of the algorithm, a series of simulation experiments are done under different SNR and modulation signal parameters, and the algorithm is compared with other classification and recognition algorithms. Finally, the feasibility and effectiveness of the proposed algorithm and its robustness under low signal-to-noise ratio (SNR) are verified.
【作者单位】： 武汉大学电子信息学院;
【基金】：湖北省自然科学基金青年基金项目(2015CFB202)资助课题
【分类号】：TN911.3
【相似文献】
相关期刊论文 前1条
1 罗扬;;基于内容的音乐自动分类模式识别系统设计[J];福建电脑;2012年11期
相关硕士学位论文 前1条
1 赵传敏;基于多特征选择的心电信号自动分类算法研究[D];苏州大学;2012年
，本文编号：2234903
本文链接：https://www.wllwen.com/kejilunwen/xinxigongchenglunwen/2234903.html
