A Method for Wireless Communication High-precision Signal Identification and Baud Rate Parameter Estimation

Faquan Yang, Zan Li, Haiyan Wang, Xinmei Yu

Abstract


High computation complexity happens when the existing support vector machine (SVM) identifies multi-class problems, and the modulation identification rate is not ideal when the receiving signal noise ratio (SNR) is low. For these two problems, high-order cumulants used in this article can have good anti-noise performance. To begin with, high-order cumulants can be extracted as the characteristic value of signal. Then, SVM is conducted training. Finally, the identification algorithm routine of conventional SVM is promoted. After this process presented in this article, the simulation result showed that the corresponding average modulation identification rate can increase by more than 25% than the situation when individually using conventional SVM. Especially, when SNR is 5dB, the identification rate can reach 90% and the system prone to be achieved, which shows that high-order cumulants has wide application prospect in the signal identification and parameter estimation.


Full Text:

PDF

Refbacks

  • There are currently no refbacks.