Loading...

Ahangarzadeh, Amir | 2019

506 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 52721 (05)
  4. University: Sharif University of Technology
  5. Department: Electrical Engineering
  6. Advisor(s): Shabani, Mahdi; Hashemi, Matin
  7. Abstract:
  8. The application of deep learning algorithms in the processing of telecommunication signals is increasing. One of the issues in this area is the automatic recognition of radio signal modulation. Recognizing the type of signal modulation as the first stage of baseband signal processing on the receiver side is a key issue in military and civilian applications. The problem with classical algorithms for solving this problem is their strong dependence on channel characteristics and factors resulting from the transmitter and receiver being non-ideal. However, modern algorithms based on deep neural networks have been able to make the model somewhat resistant to these factors. However, the detection of disturbed signals for both sets of algorithms is accompanied by a significant reduction in their accuracy. In this study, an algorithmic combination of classical methods based on signal features and modern methods based on deep learning is presented. The distinguishing characteristic of this algorithm is its high accuracy in detecting the modulation of disturbed signals as it has been able to improve the classification accuracy of the modulations by up to 20% over similar algorithms
  9. Keywords:
  10. Deep Learning ; Wireless Communication ; Automatic Modulation Recognition ; Feature-based Method ; Radio Signals ; Automatic Modulation Classification

 Digital Object List

 Bookmark

No TOC