Loading...

Digital Modulation Recognition of Communication Signals

Hassanpour Zahraei, Salman | 2012

799 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 44105 (05)
  4. University: Sharif University of Technology
  5. Department: Electrical Engineering
  6. Advisor(s): Pezeshk, Amir Mansour; Behnia, Fereidoon
  7. Abstract:
  8. Modulation Recognition of communication signals has been an important theme in the field of wireless communication. Modulation Recognition has various applications for both military and civil purposes. Recently there has been considerable attention to Digital Modulation Recognition, due to the vast application of this kind of Modulation Recognition tasks. In this thesis, we proposed a Digital Modulation Recognition Algorithm, which is able to identify various types of digital modulations in low SNRs. These include BASK, BFSK, BPSK, 4-ASK, 4-FSK, 4-PSK, 8-FSK, 8-PSK, MQAM (M=16, 32, 64). The proposed method uses a general pattern recognition scheme, consisting of a feature extraction phase and a classification phase. The focus of previous work was mostly on the classification phase. In this thesis, we proposed a new set of features based on Wavelet Transform in addition to the features from previous work. We also investigated and analyzed each individual feature, before using in the classification phase. In order to use SVM for this multi-class problem, we used the conventional One-against-One method and a proposed Tree method. The tree method needs much fewer SVM blocks to work. Experimental results show that the tree method has better recognition accuracy in comparison with the one-against-one method. They also show that the recognition of proposed algorithm is better than that of the previous work. Recognition accuracy of the tree method in 5dB, 0dB, -5dB and -10dB SNRs is %99.8, %98, %92.5 and %75.5, respectively
  9. Keywords:
  10. Signal to Noise Ratio ; Feature Extraction ; Classification ; Support Vector Machine (SVM) ; Modulation Recognition ; Digital Modulation ; Wavelet Transform ; Cross Correlation

 Digital Object List

 Bookmark

No TOC