AI 中文总结
本文综述基于AI的通信与雷达调制识别技术，涵盖模型机器学习和深度学习方法。先研究调制类型、总结特征优缺点，再介绍AI模型并分层研究相关方法，最后突出开放问题并给出未来研究方向。
AI 中文摘要
自动调制识别（AMR）对于确保通信和雷达可靠性、高效频谱利用以及抗电子干扰至关重要。人工智能（AI）技术的发展正在重塑AMR的技术范式，推动其从依赖人工特征的传统模式向数据驱动的智能识别转变。这种变化不仅体现在识别准确率的显著提高上，还通过算法创新、架构优化和场景扩展为通信和雷达系统的智能演进注入强大动力。为了阐明AMR的当前发展状况和瓶颈，并找到突破方向，本文对近期基于AI的AMR技术进行了全面综述，包括基于模型的机器学习（ML）方法和数据驱动的深度学习（DL）方法。首先研究了当前通信和雷达系统中使用的调制类型，接着总结了AMR领域常用特征并讨论其优缺点，然后介绍了AMR的基本AI模型并对通信和雷达的AMR方法进行分层研究，最后基于现有研究突出了开放问题并提出了AMR的未来研究方向。
英文摘要
Automatic modulation recognition (AMR) is of vital importance for ensuring communication and radar reliability, efficient spectrum utilization and resistance to electronic interference. The development of artificial intelligence (AI) technology is reshaping the technological paradigm of AMR, promoting its transition from traditional modes relying on manual features to data-driven intelligent recognition. This change is not only reflected in the significant improvement of recognition accuracy, but also injects strong momentum into the intelligent evolution of both communication and radar systems through algorithm innovation, architecture optimization, and scenario expansion. In order to clarify the current development status and bottlenecks of AMR, and to find breakthrough directions, we make a comprehensive survey of recent AI-based technologies for AMR in this paper, including model-based machine learning (ML) methods and data-driven deep learning (DL) methods. We first investigate the modulation types used in current communication and radar systems. Next, we summarize the typically used features in the field of AMR, and discuss their inherent advantages and disadvantages. Then, we introduce the basic AI models for AMR and conduct a hierarchical investigation of AMR methods for communication and radar. Finally, based on existing research works, we highlight open issues and propose future research directions for AMR.
