Revolution of Wireless Signal Recognition for 6G: Recent Advances, Challenges and Future Directions

TL;DR

This paper surveys wireless signal recognition (WSR) for 6G, tracing the evolution from traditional likelihood- and feature-based methods to intelligent deep learning approaches across four core tasks: radio frequency fingerprint identification (RFFI), automatic modulation classification (AMC), wireless technology classification (WTC), and wireless interference identification (WII). It classifies methods into model-based (LB/FB/ML) and intelligent (DL/hybrid) families, and provides an integrated view of model architectures, data representations (image-based and sequence-based), learning strategies (contrastive, transfer, multi-task), and practical implementation considerations (lightweight models, compression, hardware). The survey also covers datasets, evaluation metrics, and standardization efforts, and discusses challenges posed by complex, dynamic, and open 6G environments, offering future directions such as data-model synergy, open-set and few-shot learning, adversarial robustness, and potential integration with large language models for adaptive spectrum management. Overall, it presents a comprehensive, state-of-the-art roadmap for WSR in 6G, highlighting the concrete techniques, datasets, and design choices that will shape robust, real-time recognition in future networks.

Abstract

Wireless signal recognition (WSR) is a crucial technique for intelligent communications and spectrum sharing in the next six-generation (6G) wireless communication networks. It can be utilized to enhance network performance and efficiency, improve quality of service (QoS), and improve network security and reliability. Additionally, WSR can be applied for military applications such as signal interception, signal race, and signal abduction. In the past decades, great efforts have been made for the research of WSR. Earlier works mainly focus on model-based methods, including likelihood-based (LB) and feature-based (FB) methods, which have taken the leading position for many years. With the emergence of artificial intelligence (AI), intelligent methods including machine learning-based (ML-based) and deep learning-based (DL-based) methods have been developed to extract the features of the received signals and perform the classification. In this work, we provide a comprehensive review of WSR from the view of applications, main tasks, recent advances, datasets and evaluation metrics, challenges, and future directions. Specifically, intelligent WSR methods are introduced from the perspective of model, data, learning and implementation. Moreover, we analyze the challenges for WSR from the view of complex, dynamic, and open 6G wireless environments and discuss the future directions for WSR. This survey is expected to provide a comprehensive overview of the state-of-the-art WSR techniques and inspire new research directions for WSR in 6G networks.

Figures (14)

• Figure 1: Historical development and evolution of WSR methods.
• Figure 2: Organization and contents of this survey and its sections.
• Figure 3: Applications of wireless signal recognition, including civilian applications (blue circles) and military applications (green circle).
• Figure 4: Illustration of the Likelihood-based methods for WSR, (a) MLC in AWGN channel, (b) ALRT, (c) GLRT, and (d) HLRT.
• Figure 5: Features for wireless signals, including spectral features, statistical features, transform features and others.