scispace - formally typeset
Search or ask a question
Proceedings ArticleDOI

2D-FFT Based Modulation Classification Using Deep Convolution Neural Network

TL;DR: In this paper, a convolution neural network (CNN) based automatic modulation classification (AMC) method is proposed, where two dimensional Fast Fourier Transform (2D-FFT) is used as a classification feature and a less complex and efficient deep CNN model is designed to classify the modulation schemes of different orders of PSK and QAM.
Abstract: Automatic modulation classification (AMC) has a wide range of applications in the military and civilian areas In the military, it is used for the extraction of information from unknown intercepted signals and the generation of jamming signals Civil applications include interference management and spectrum underutilization To overcome the limitations of traditional methods like maximum likelihood (ML) and feature- based (FB), deep learning (DL) networks have been developed and are being evolved Following this direction, a convolution neural network (CNN) based AMC method is proposed The two dimensional Fast Fourier Transform (2D-FFT) is used as a classification feature and a less complex and efficient deep CNN model is designed to classify the modulation schemes of different orders of PSK and QAM The developed method achieves adequate classification performance for considered five modulation schemes in the AWGN channel
Citations
More filters
Proceedings ArticleDOI
02 Mar 2022
TL;DR: This study uses images of a famous historical collection, the Dead Sea Scrolls, to propose a novel method to classify the materials of the manuscripts using the two-dimensional Fourier Transform to identify patterns within the manuscript surfaces.
Abstract: Researchers continually perform corroborative tests to classify ancient historical documents based on the physical materials of their writing surfaces. However, these tests, often performed on-site, requires actual access to the manuscript objects. The procedures involve a considerable amount of time and cost, and can damage the manuscripts. Developing a technique to classify such documents using only digital images can be very useful and efficient. In order to tackle this problem, this study uses images of a famous historical collection, the Dead Sea Scrolls, to propose a novel method to classify the materials of the manuscripts. The proposed classifier uses the two-dimensional Fourier Transform to identify patterns within the manuscript surfaces. Combining a binary classification system employing the transform with a majority voting process is shown to be effective for this classification task. This pilot study shows a successful classification percentage of up to 97% for a confined amount of manuscripts produced from either parchment or papyrus material. Feature vectors based on Fourier-space grid representation outperformed a concentric Fourier-space format.
References
More filters
Proceedings ArticleDOI
01 Jul 2017
TL;DR: Modulation scheme detection of blind signal is vital area of research now a days because of the requirement in security and communication applications, and efficient way of Classification between ASK, PSK and QAM is proposed.
Abstract: Modulation scheme detection of blind signal is vital area of research now a days because of the requirement in security and communication applications. In this paper, modulation class is identified based on the constellation graphical representation. Carrier frequency, symbol rate and phase offset are the essential parameters required for the extraction of constellation diagram, which are calculated efficiently. Efficient way of Classification between ASK, PSK and QAM is proposed in this paper. ASK and pool of PSK and QAM is separated using linear regression, and further classification between PSK and QAM has done using circle fitting.

8 citations

Proceedings ArticleDOI
01 Dec 2018
TL;DR: The simulation results for the proposed modulation scheme classifier shows that different modulation schemes are classified efficiently above 10 dB SNR in presence of Additive White Gaussian Noise.
Abstract: Modulation scheme classifier for the received RF signal is proposed in this paper. Modulation classification is an intermediate step between data detection and its demodulation for extracting the final information. Proposed method estimates the carrier frequency offset after downconversion of passband signal with estimated carrier frequency and corrects for it. Signal is sampled with high frequency and symbol rate is estimated. Sampled signal is downsampled to estimated symbol rate to extract the constellation points. For identification of modulation scheme between QAM and PSK of different orders, k-medoids clustering is used. Blindly, k medoids are estimated for k equals to 4, 8, 16 and 64 and similarity to ideal constellation structure is calculated. Final decision for modulation scheme is given in favor for which similarity with ideal constellation structure is maximum. The simulation results for the method shows that different modulation schemes are classified efficiently above 10 dB SNR in presence of Additive White Gaussian Noise. Method proposed is unsupervised and has low computational complexity.

6 citations

Journal ArticleDOI
TL;DR: This study proposes a software-defined radio based implementation of blind signal modulation recogniser (BSMR) on field-programmable gate array (FPGA), which works without any prior knowledge of the received signal.
Abstract: Blind signal modulation recognition is an essential block for designing a cognitive radio. Different algorithms are developed in the literature, but few are given with detailed implementation. This study proposes a software-defined radio based implementation of blind signal modulation recogniser (BSMR) on field-programmable gate array (FPGA), which works without any prior knowledge of the received signal. The algorithm estimates carrier frequency offset, symbol rate, symbol timing offset, and corrects the signal for these offsets to extract constellation points. It uses clustering structure formed by constellation signature in I/Q plane to detect the modulation for different orders of ASK, PSK, and QAM. The proposed algorithm is deployed on FPGA, using LabVIEW, for a reliable and reconfigurable platform. The algorithm is optimised to use minimum hardware resources and facilitate future up-gradation. The system developed by implementing the algorithm on NI-FlexRIO-7975 FPGA module with NI-5791 adapter detects modulation type in real time without any training. Signals for testing are generated using NI-PXIe-5673 (RF transmitter), and BSMR identifies the modulation type in 81.451 ms under additive white Gaussian noise channel.

3 citations