[论文解读] Real-World Considerations for Deep Learning in Wireless Signal Identification Based on Spectral Correlation Function.

Kürşat Tekbıyık, Özkan Akbunar+3 more|arXiv (Cornell University)|Mar 17, 2020

Wireless Signal Modulation Classification被引用 3

一句话总结

本文提出一种基于CNN的无线信号识别方法，利用谱相关函数（SCF）在不预先知晓带宽或中心频率的情况下对无线接入技术进行分类。该方法可实现联合或串行感知与分类，在低信噪比条件下优于经典循环平稳特征检测方法，通过消除阈值估计和人工特征提取，显著提升性能。

ABSTRACT

This paper proposes a convolutional neural network (CNN) model which utilizes the spectral correlation function (SCF) for wireless radio access technology identification without any prior information about bandwidth and/or the center frequency. The sensing and classification methods are applied to the baseband equivalent signals. Two different approaches are elaborated. The proposed method is implemented in two different settings; in the first setting, signals are jointly sensed and classified. Sensing and classification are conducted in a sequential manner in the second setting. The performance of both approaches is discussed in detail. The proposed method eliminates the threshold estimation processes of classical estimators. It also eliminates the need to know the distinct features of signals beforehand. Over-the-air real-world measurements are used to show the robustness and the validity of the proposed method and various wireless signals are successfully distinguished from each other without any a priori knowledge. The over-the-air real-world measurements are also shared in the format of SCF. The performance of SCF-based identification is compared with the cases when fast Fourier transform and amplitude-phase representation are used as the training inputs for CNN. The comparative performance of the proposed method is quantified by precision, recall, and F1-score metrics. Moreover, a setup to compare the performance of the proposed approach with classical cyclostationary features detection (CFD) is prepared. Measurement results indicate the superiority of the proposed method against CFD, especially at the low signal-to-noise ratio regime.

研究动机与目标

• 开发一种无需预先知晓信号参数（如带宽或中心频率）的深度学习无线信号识别方法。
• 消除传统循环平稳特征检测（CFD）方法中对人工特征工程和阈值估计的需求。
• 评估基于SCF的分类在实际空中信号测量下的鲁棒性与性能表现。
• 将基于SCF的输入与FFT和幅度-相位等替代表示形式在CNN训练中进行对比。
• 在低信噪比（SNR）条件下，证明所提方法相比经典CFD方法具有更优的分类性能。

提出的方法

• 使用谱相关函数（SCF）作为输入，训练卷积神经网络（CNN）以实现无线信号分类。
• 实现两种工作模式：联合感知与分类，以及先感知后分类的串行模式。
• 直接从基带等效信号计算SCF，以提取循环平稳特征，且无需预先知晓信号参数。
• 通过端到端学习原始SCF表示中的特征，避免了阈值估计。
• 使用真实空中信号测量数据，通过精确率、召回率和F1分数等指标评估性能。
• 建立对比实验设置，将基于SCF的CNN与经典CFD方法及替代输入表示形式（FFT、幅度-相位）进行基准对比。

实验结果

研究问题

• RQ1 仅使用谱相关函数作为输入，CNN模型是否能在不预先知晓带宽或中心频率的情况下实现准确的无线信号分类？
• RQ2 在低信噪比环境下，基于SCF的深度学习方法与经典循环平稳特征检测（CFD）方法相比性能如何？
• RQ3 在CNN框架中，基于SCF的输入与FFT及幅度-相位表示形式相比，其相对分类准确率如何？
• RQ4 所提方法是否消除了在谱特征提取中对人工阈值估计的需求？
• RQ5 在真实空中信号条件下，基于SCF的分类方法在实际传播环境下的鲁棒性如何？

主要发现

• 基于SCF的CNN在低信噪比（SNR）区域显著优于经典循环平稳特征检测（CFD）方法。
• 该方法在无需预先知晓带宽或中心频率的情况下，成功对多种无线信号进行分类。
• 所提方法消除了经典CFD方法中常见的阈值估计需求，显著降低人工干预。
• 与FFT和幅度-相位表示形式相比，使用SCF作为输入可使CNN获得更高的精确率、召回率和F1分数。
• 真实空中信号测量结果证实了基于SCF的分类方法在实际传播条件下的鲁棒性与有效性。
• 联合感知与分类模式实现了具有竞争力的性能，而串行方法则支持模块化信号处理。