A Deep Learning Framework for Signal Detection and Modulation Classification

Abstract

Deep learning (DL) is a powerful technique which has achieved great success in many applications. However, its usage in communication systems has not been well explored. This paper investigates algorithms for multi-signals detection and modulation classification, which are significant in many communication systems. In this work, a DL framework for multi-signals detection and modulation recognition is proposed. Compared to some existing methods, the signal modulation format, center frequency, and start-stop time can be obtained from the proposed scheme. Furthermore, two types of networks are built: (1) Single shot multibox detector (SSD) networks for signal detection and (2) multi-inputs convolutional neural networks (CNNs) for modulation recognition. Additionally, the importance of signal representation to different tasks is investigated. Experimental results demonstrate that the DL framework is capable of detecting and recognizing signals. And compared to the traditional methods and other deep network techniques, the current built DL framework can achieve better performance.

Machine Learning Based Automatic Modulation Recognition for Wireless Communications: A Comprehensive Survey

“…Zha et al [84], introduced a DL framework for multisignals detection and modulation recognition. The proposed scheme can obtain the signal modulation format, center frequency, and start-stop time.…”

Blind Detection of Underwater Acoustic Communication Signals Based on Deep Learning

“…where,  is the Sigmoid function, , where  is a random real number between 0 and 1. For the classifier C , the BCE is adopted to calculate the distribution distance between the real category labels and the predicted labels og( ), (19) where, N denotes the mini-batch size. The network training and prediction is conducted with the DL library, Pytorch, on a single NVIDIA TITAN RTX GPU.…”

“…Considering the similarities between UWAC and radio communication (RC) signals, some blind detection methods for RC signals could serve useful. Blind detection algorithms for RC signals have been developed in the past decades and can be divided into two categories: conventional statistical detection theory (SDT)-based [12]- [15] and deep learning (DL)-based [16]- [19]. SDT-based methods require first designing the test statistics and then choosing appropriate thresholds or applying the support vector machines for judgement.…”

MorseNet: A Unified Neural Network for Morse Detection and Recognition in Spectrogram

“…Energy detection plays well in a spectrogram with scattered signals, but it could make mistakes when signals are densely distributed. Recently, some researchers have exploited the single shot multibox detector (SSD) network to detect multi-type signals in spectrograms [8], [9]. SSD is a common DL-based object detection method that is capable of locating signals by a bounding box (BBox) and identifying the type.…”