Automatic Modulation Classification of Overlapped Sources Using Multiple Cumulants

Huang, Sai; Yao, Yuanyuan; Wei, Zhiqing; Feng, Zhiyong; Zhang, Ping

doi:10.1109/tvt.2016.2636324

Cited by 128 publications

(51 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Harr is a traditional machine learning method for visual object classification [22], but the impact of uneven illumination in industrial manufacturing cannot be well balanced [2]. Navneet Dalal et al proposed HOG descriptors, which can significantly outperform existing feature sets for human classification [4].…”

Section: Traditional Machine Learning Methodsmentioning

confidence: 99%

Transfer Learning Based Screen Defect Classification

Li¹,

Li²,

Zhang³

et al. 2020

Proceedings of the 13th EAI International Conference on Mobile Multimedia Communications, Mobimedia 2020, 27-28 August 2020, Cy

View full text Add to dashboard Cite

Section: Traditional Machine Learning Methodsmentioning

confidence: 99%

Transfer Learning Based Screen Defect Classification

Li¹,

Li²,

Zhang³

et al. 2020

Proceedings of the 13th EAI International Conference on Mobile Multimedia Communications, Mobimedia 2020, 27-28 August 2020, Cy

View full text Add to dashboard Cite

“…The state of art existing work can also be found in ref. [10][11][12][13][14][15][16][17][18][19][20][21]. Table 1.…”

Section: Introductionmentioning

confidence: 99%

Genetic Algorithm Assisted Support Vector Machine for M-QAM Classification

Ghauri¹,

Sarfraz²,

Muhammad³

et al. 2020

MMEP

View full text Add to dashboard Cite

Automatic modulation classification (AMC) has wide spread applications in today's communication system. AMC has vast applications both in military as well as civilian. In intelligent communication systems such as software defined radios networks and cognitive radio networks, AMC is the most important issue, when there is no prior information about the signal. In this research article, pattern recognition approach has been utilized for classification of M-ARY quadrature amplitude modulated (M-QAM) signals. Higher order cumulants are selected as feature set and Genetic Algorithm assisted Support Vector Machine (SVM) classifier is used for classification of M-QAM signals. The performance of classifier is evaluated on fading channels in the presence of additive white Guassain noise. The classification accuracy is also compared with and without optimized classifier.

show abstract

“…With the deepening of the research on Convolutional Neural Network (CNN), the method based on CNN has achieved superior results on various computer vision tasks [3][4][5], [8]. And methods based on CNN for mobile phone screen defect detection have become a good solution [2], [6], [7].…”

Section: Introductionmentioning

confidence: 99%