Signal Detection and Classification in Shared Spectrum: A Deep Learning Approach

Zhang, Wenhan; Feng, Mingjie; Krunz, Marwan; Abyaneh, Amir Hossein Yazdani

doi:10.1109/infocom42981.2021.9488834

Cited by 28 publications

(17 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zhang et al [6] studied a similar technology classification problem of Wi-Fi, LTE, and 5G signals, where they evaluated the classification performance of CNNs and LSTMs using I/Q samples received from a single receiver. In [7], Bitar et al studied the classification of I/Q samples for Bluetooth, ZigBee, and 802.11n in the context of IoT.…”

Section: Related Workmentioning

confidence: 99%

“…However, to ease the burden of having multiple technologies implemented and interconnected on commercial devices, an alternative approach adopted in this paper, is to use a universal classifier based on Deep Neural Networks (DNNs), such as Convolutional Neural Networks (CNNs). CNN-based signal classification has been studied to fulfill different goals, including modulation classification [4,5], technology (protocol) identification [6,7], transmitter authentication [8,9], LTE spectrogram generation [10], and generation of synthetic modulated waveforms via Generative Adversarial Networks (GANs) [11]. These classifiers suggest classes based on received raw I/Q samples.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automatic Machine Learning for Multi-Receiver CNN Technology Classifiers

Yazdani-Abyaneh

Krunz

2022

Proceedings of the 2022 ACM Workshop on Wireless Security and Machine Learning

Self Cite

View full text Add to dashboard Cite

Convolutional Neural Networks (CNNs) are one of the most studied family of deep learning models for signal classification, including modulation, technology, detection, and identification. In this work, we focus on technology classification based on raw I/Q samples collected from multiple synchronized receivers. As an example use case, we study protocol identification of Wi-Fi, LTE-LAA, and 5G NR-U technologies that coexist over the 5 GHz Unlicensed National Information Infrastructure (U-NII) bands. Designing and training accurate CNN classifiers involve significant time and effort that goes to fine-tuning a model's architectural settings (e.g., number of convolutional layers and their filter size) and determining the appropriate hyperparameter configurations, such as learning rate and batch size. We tackle the former by defining architectural settings themselves as hyperparameters. We attempt to automatically optimize these architectural parameters, along with other preprocessing (e.g., number of I/Q samples within each classifier input) and learning hyperparameters, by forming a Hyperparameter Optimization (HyperOpt) problem, which we solve in a near-optimal fashion using the Hyperband algorithm. The resulting near-optimal CNN (OCNN) classifier is then used to study classification accuracy for OTA as well as simulations datasets, considering various SNR values. We show that using a larger number of receivers to construct multi-channel inputs for CNNs does not necessarily improve classification accuracy. Instead, this number should be defined as a preprocessing hyperparameter to be optimized via Hyperband. OTA results reveal that our OCNN classifiers improve classification accuracy by 24.58% compared to manually tuned CNNs. We also study the effect of min-max normalization of I/Q samples within each classifier's input on generalization accuracy over simulated datasets with SNRs other than training set's SNR, and show an average of 108.05% improvement when I/Q samples are normalized.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Automatic Machine Learning for Multi-Receiver CNN Technology Classifiers

Yazdani-Abyaneh

Krunz

2022

Proceedings of the 2022 ACM Workshop on Wireless Security and Machine Learning

Self Cite

View full text Add to dashboard Cite

show abstract

“…3 shows the receiver operating characteristic (ROC) detection performance curves of the GLRT for each setup. In addition, we compare our proposed method to two baselines: (i) end-to-end deep learning (EtE DL) [15], where a deep learning classifier is trained on both linear and nonlinear signals to perform detection directly in place of the GLRT; and (ii) data driven (DD) pre-processing [16], where the received nonlinear signal is first pre-processed in an attempt to recover the linear signal prior to applying the GLRT. In our adoption of [16], we train an autoencoder (AE) to map nonlinear signals (taken as input to the AE) to their linear counterparts (given as output by the AE).…”

Section: Detector Performancementioning

confidence: 99%

A Neural Network-Prepended GLRT Framework for Signal Detection Under Nonlinear Distortions

et al. 2022

View full text Add to dashboard Cite

Many communications and sensing applications hinge on the detection of a signal in a noisy, interference-heavy environment. Signal processing theory yields techniques such as the generalized likelihood ratio test (GLRT) to perform detection when the received samples correspond to a linear observation model. Numerous practical applications exist, however, where the received signal has passed through a nonlinearity, causing significant performance degradation of the GLRT. In this work, we propose prepending the GLRT detector with a neural network classifier capable of identifying the particular nonlinear time samples in a received signal. We show that pre-processing received nonlinear signals using our trained classifier to eliminate excessively nonlinear samples (i) improves the detection performance of the GLRT on nonlinear signals and (ii) retains the theoretical guarantees provided by the GLRT on linear observation models for accurate signal detection.

show abstract

“…Automatic modulation recognition (AMR) provides essential modulation information of the incoming radio signals, especially non-cooperative radio signals, and plays a key role in various scenarios including cognitive radio, spectrum sensing, signal surveillance, interference identification, etc [3,9,90]. It aims to detect the modulation scheme of wireless communications signals automatically without prior information, and has attracted significant research interest in recent years [51].…”

Section: Introductionmentioning

confidence: 99%