A Study on Deep Neural Network-based Automatic Blind Modulation Classification for Communication Systems
- Title
- A Study on Deep Neural Network-based Automatic Blind Modulation Classification for Communication Systems
- Author
- Jung Hwan LEE
- Alternative Author(s)
- 이정환
- Advisor(s)
- Jun-Won CHOI
- Issue Date
- 2019-02
- Publisher
- 한양대학교
- Degree
- Master
- Abstract
- In this paper, a high - performance blind modulation classification (BMC) technology based on deep neural network (DNN) for fading channels is proposed. First, a large and diverse feature set is provided. Then, features are selected that have statistical relevance on the modulation class with at least redundancy on the other features. Next, the selected features are used to train the DNN and classify the modulation class. Due to the ability of DNN to learn complex structures in the high dimensional feature space, the proposed scheme achieves excellent classification accuracy using a number of features in a challenging fading events. Numerical evaluation shows that the proposed technique has better performance than the existing BMC methods.
- URI
- https://repository.hanyang.ac.kr/handle/20.500.11754/99646http://hanyang.dcollection.net/common/orgView/200000434365
- Appears in Collections:
- GRADUATE SCHOOL[S](대학원) > ELECTRICAL ENGINEERING(전기공학과) > Theses (Master)
- Files in This Item:
There are no files associated with this item.
- Export
- RIS (EndNote)
- XLS (Excel)
- XML