본문 바로가기

Deep Learning-Based Modulation Recognition with Multi-Scale Temporal Feature Extraction

문서 유형
연구출판물 · 학술대회 발표논문
등재
Scopus
저널 순위
Scopus Q2
피인용
Scopus 1
FWCI (Scopus)
1.28
ISSN
1976-7684

저자

  1. 신다민제1저자교신저자Pusan National University, Dept. of Electrical and Electronics Engineering, Busan, Republic of Korea
  2. 박도현Pusan National University, School of Electrical and Electronics Engineering, Busan, Republic of Korea
  3. 김형남Pusan National University, School of Electrical and Electronics Engineering, Busan, Republic of Korea

초록

This paper studies a deep learning-driven method for identifying modulation types in communication signals without prior information. To effectively capture the relationship between points in the time-series data, we apply a multi-head self-attention mechanism. The results demonstrate superior modulation recognition accuracy compared to conventional AMR models. In particular, the classification accuracy between QAM16 and QAM64 was significantly improved, confirming that the performance of the model has been enhanced compared to previous models.

키워드

automatic modulation recognitionmulti-head self-attention

식별자

Scopus EID
2-s2.0-105005717682