Automatic modulation classification in practical wireless channels
- Authors
- Kim, Sung-Jin; Yoon, Dong weon
- Issue Date
- Nov-2016
- Publisher
- Institute of Electrical and Electronics Engineers Inc.
- Keywords
- Automatic modulation classification; Machine learning; Support vector machine
- Citation
- 2016 International Conference on Information and Communication Technology Convergence, ICTC 2016, pp.915 - 917
- Indexed
- SCOPUS
- Journal Title
- 2016 International Conference on Information and Communication Technology Convergence, ICTC 2016
- Start Page
- 915
- End Page
- 917
- URI
- https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/21402
- DOI
- 10.1109/ICTC.2016.7763329
- ISSN
- 0000-0000
- Abstract
- Flexible spectrum utilization becomes one of the major agendas in the next generation wireless communications. A core technology to efficiently adjust spectrum is automatic modulation classification (AMC) which recently emerges in various future wireless research including military communications, cognitive radio and high-Throughput wireless. AMC is essential for capturing over-The-Air information, estimating a remained spectral resource and improving spectral efficiency in the corresponding wireless services. We consider support vector machine (SVM) for AMC in practical wireless channels, which includes typical impairments such as frequency offsets and multipath fading. On the top of concatenated sorted symbols (CSS), we propose to include a new process and a new training procedure so that the classification performance is significantly improved from the conventional CSS-SVM approach in practical wireless channels.
- Files in This Item
-
Go to Link
- Appears in
Collections - 서울 공과대학 > 서울 융합전자공학부 > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/21402)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.