Shared spectrum usage is inevitable due to the ongoing increase in wireless services and bandwidth requirements. Spectrum monitoring is a key enabler for efficient spectrum sharing by multiple radio access technologies (RATs). In this paper, we present signal classification using deep neural networks to identify various radio technologies and their associated interferences. We use Convolutional Neural Networks (CNN) to perform signal classification and employ six well-known CNN models to train for ten signal classes. These classes include LTE, Radar, WiFi and FBMC (Filter Bank Multicarrier) and their interference combinations, which include, LTE + Radar, LTE + WiFi, FBMC + Radar, FBMC + WiFi, WiFi + Radar and Noise. The CNN models include, AlexNet, VGG16, ResNet18, SqueezeNet, InceptionV3 and ResNet50. The radio signal data sets for training and testing of CNN-based classifiers are acquired using a USRP-based experimental setup. Extensive measurements of these radio technologies (LTE, WiFi, Radar and FBMC) are done over different locations and times to generate a robust dataset. We propose a novel (spectrogram) representation called the Quarter-spectrogram (Q-spectrogram) that squeezes temporal and frequency information for input to CNN models. While considering classification accuracy, model complexity and prediction time for a single input Q-spectrogram (image), ResNet18 (CNN model) gives the best overall performance with 98% classification accuracy. While SqueezeNet (CNN model) offers the lowest model complexity which makes it very suitable for resource-constrained radio monitoring devices and also offers the least prediction time of 110 msec. Moreover, we also propose a simple WiFi classification scheme that buffers several WiFi Q-spectrograms and then makes a decision about WiFi’s presence and also gives a quantified measure of WiFi traffic density.

中文翻译：

---

使用深度学习的共享频谱监控


由于无线服务和带宽需求的不断增加，共享频谱的使用是不可避免的。频谱监控是多种无线接入技术 (RAT) 高效频谱共享的关键推动因素。在本文中，我们提出使用深度神经网络进行信号分类，以识别各种无线电技术及其相关干扰。我们使用卷积神经网络 (CNN) 进行信号分类，并采用 6 个著名的 CNN 模型来训练 10 个信号类别。这些类别包括 LTE、雷达、WiFi 和 FBMC（滤波器组多载波）及其干扰组合，其中包括 LTE + 雷达、LTE + WiFi、FBMC + 雷达、FBMC + WiFi、WiFi + 雷达和噪声。 CNN 模型包括 AlexNet、VGG16、ResNet18、SqueezeNet、InceptionV3 和 ResNet50。用于训练和测试基于 CNN 的分类器的无线电信号数据集是使用基于 USRP 的实验装置获取的。在不同地点和时间对这些无线电技术（LTE、WiFi、雷达和 FBMC）进行广泛测量，以生成可靠的数据集。我们提出了一种称为四分之一频谱图（Q 频谱图）的新颖（频谱图）表示形式，它可以压缩时间和频率信息以输入 CNN 模型。在考虑单个输入 Q 谱图（图像）的分类精度、模型复杂性和预测时间时，ResNet18（CNN 模型）提供了最佳的整体性能，分类精度为 98%。而SqueezeNet（CNN模型）提供了最低的模型复杂度，这使得它非常适合资源受限的无线电监测设备，并且还提供了110毫秒的最短预测时间。 此外，我们还提出了一种简单的 WiFi 分类方案，该方案可以缓冲多个 WiFi Q 频谱图，然后对 WiFi 的存在做出决定，并给出 WiFi 流量密度的量化测量。