A Method of High-Precision Signal Recognition Based on Higher-Order Cumulants and SVM

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

[1]  Engin Avci,et al.  An expert Discrete Wavelet Adaptive Network Based Fuzzy Inference System for digital modulation recognition , 2007, Expert Syst. Appl..

[2]  Said Safi,et al.  Identification of quadratic systems using higher order cumulants and neural networks: Application to model the delay of video-packets transmission , 2011, Appl. Soft Comput..

[3]  Guo Hui.  Digital modulation recognition algorithm based on support vector machine , 2011 .

[4]  M. H. Valipour,et al.  Automatic digital modulation recognition in presence of noise using SVM and PSO , 2012, 6th International Symposium on Telecommunications (IST).

[5]  Nan Xu,et al.  Modulation recognition of communication signals based on high order cumulants and support vector machine , 2012 .

[6]  Ataollah Ebrahimzade Sherme.  A novel method for automatic modulation recognition , 2012, Appl. Soft Comput..

[7]  Shrideep Pallickara,et al.  On the performance of high dimensional data clustering and classification algorithms , 2013, Future Gener. Comput. Syst..

[8]  Ai Lingme.  Tire tread pattern recognition based on composite feature extraction and hierarchical support vector machine , 2013 .

[9]  Yang Faquan,et al.  Method of Modulation Recognition of Mixed Modulation Signal , 2014 .

[10]  Kevin Noronha,et al.  Biomedical Signal Processing and Control Automated Classification of Glaucoma Stages Using Higher Order Cumulant Features , 2022 .

[11]  Feng-Li Lian,et al.  Confirming robustness of fuzzy support vector machine via ξ-α bound , 2015, Neurocomputing.

[12]  Dong Xu,et al.  L1-norm loss based twin support vector machine for data recognition , 2016, Inf. Sci..