Transmitter Identification and Protocol Categorization in Shared Spectrum via Multi-Task RF Classification at the Network Edge

TL;DR

The paper addresses the challenge of identifying transmitters and categorizing transmission protocols in shared spectrum using a lightweight, multi-task CNN that operates at the network edge. By leveraging a multi-channel RF input, the model jointly classifies protocols, transmitters, and their combinations, achieving $^{}$approximately $0.90$ for protocol, $1.00$ for transmitter, and $0.92$ for joint tasks on POWDER data, formalized as $P_1$, $P_2$, and $P_3$ classifications. The approach demonstrates strong edge-deployment viability and contributes to spectrum monitoring, management, and security in modern wireless networks, with future work on scalability and adaptability in rapidly changing spectrum conditions. Overall, the work highlights the practicality of compact CNNs for real-time RF classification in shared-spectrum environments and informs policy-compliant spectrum use in 6G-era networks.

Abstract

As spectrum sharing becomes increasingly vital to meet rising wireless demands in the future, spectrum monitoring and transmitter identification are indispensable for enforcing spectrum usage policy, efficient spectrum utilization, and network security. This study proposed a robust framework for transmitter identification and protocol categorization via multi-task RF signal classification in shared spectrum environments, where the spectrum monitor will classify transmission protocols (e.g., 4G LTE, 5G-NR, IEEE 802.11a) operating within the same frequency bands, and identify different transmitting base stations, as well as their combinations. A Convolutional Neural Network (CNN) is designed to tackle critical challenges such as overlapping signal characteristics and environmental variability. The proposed method employs a multi-channel input strategy to extract meaningful signal features, achieving remarkable accuracy: 90% for protocol classification, 100% for transmitting base station classification, and 92% for joint classification tasks, utilizing RF data from the POWDER platform. These results highlight the significant potential of the proposed method to enhance spectrum monitoring, management, and security in modern wireless networks.

Figures (9)

• Figure 1: Proposed Framework for transmitter identification and protocol categorization via multi-task RF signal classification in shared spectrum.
• Figure 2: POWDER Cite Map. Adapted from POWDERPlatform.
• Figure 3: Confusion Matrix of Protocol Classification
• Figure 4: Protocol T-SNE Embeddings
• Figure 5: Confusion Matrix of Transmitter Classification