Academia.eduAcademia.edu

Outline

Title
Abstract
Figures
Introduction
Materials and Methods
Experimental Setup
Database Preparation
Results
Discussion
Conclusions
References
All Topics
Engineering
Signal Processing

Signals Intelligence System with Software-Defined Radio

Profile image of Petru CotfasPetru Cotfas

Applied Sciences

https://doi.org/10.3390/APP13085199
visibility

…

description

15 pages

link

1 file

Abstract

In this paper, we present the implementation of a system that identifies the modulation of complex radio signals. This is realized using an artificial intelligence model developed, trained, and integrated with Microsoft Azure cloud. We consider that cloud-based platforms offer enough flexibility and processing power to use them instead of conventional computers for signal processing based on artificial intelligence. We tested the implementation using a software-defined radio platform developed in GNU Radio that generates and receives real modulated signals. This process ensures that the solution proposed is viable to be used in real signal processing systems. The results obtained show that for certain modulation types, the identification is performed with a high degree of success. The use of a cloud-based platform allows quick access to the system. The user is able to identify the signal modulation using only a laptop that has access to the internet.

Figures (13)
Table 1. BladeRF 2.0 micro xA4 [18]. For the artificial neural network implementation, several solutions were analyzed. The analyzed solutions were selected in order to allow the implementation without being an expert in this field. The first two analyzed platforms were DLHUB [21] and ANNHUB [22]. Both of them are developed by the same company, ANSCenter (Sydney, Australia) [23]. The two platforms offer the user the opportunity to create training models in a simple and efficient way without the need for advanced knowledge in the field of artificial intelligence. The resulting model can be exported to multiple programming languages (LabVIEW, C++, Arduino, Python), where it can be integrated to form an entire system. Following the integrations and tests performed with these two platforms, the following disadvantages were found:
Table 1. BladeRF 2.0 micro xA4 [18]. For the artificial neural network implementation, several solutions were analyzed. The analyzed solutions were selected in order to allow the implementation without being an expert in this field. The first two analyzed platforms were DLHUB [21] and ANNHUB [22]. Both of them are developed by the same company, ANSCenter (Sydney, Australia) [23]. The two platforms offer the user the opportunity to create training models in a simple and efficient way without the need for advanced knowledge in the field of artificial intelligence. The resulting model can be exported to multiple programming languages (LabVIEW, C++, Arduino, Python), where it can be integrated to form an entire system. Following the integrations and tests performed with these two platforms, the following disadvantages were found:
Figure 1. Component interconnections. The implemented system has an architecture based on the symbiosis between the two components: hardware and software. They intertwine to create a homogeneous and efficient system. Figure 1 shows how the system components are interconnected.
Figure 1. Component interconnections. The implemented system has an architecture based on the symbiosis between the two components: hardware and software. They intertwine to create a homogeneous and efficient system. Figure 1 shows how the system components are interconnected.
How the components of the system work and communicate can be seen in Figure 2. In the upper part of Figure 2, the components that are used to train and validate the artificia intelligence network are presented. The database, after it is prepared, is loaded in the Microsoft Azure Auto ML Service, where the artificial intelligence network is configured. Following the training and validation part, the trained model is realized. In the lower part of the image, the components used to test the trained model are presented. The SDR platform is used to send and receive modulated signals. The modulated samples received are inserted into the integrated trained model (integrated into Microsoft Azure cloud) that generates the answer with the identified modulation type. In this database, we find signals that are modulated using the following 24 modulation schemes: OOK, 4ASK, 8ASK, BPSK, QPSK, 8PSK, 16PSK, 32PSK, 16APSK, 32APSK, 64APSK, 128APSK, 16QAM, 32QAM, 64QAM, 128QAM, 256QAM, AM-SSB-WC, AM-SSB-SC, AM- DSB-WC, AM-DSB-SC, FM, GMSK, and OQPSK.
How the components of the system work and communicate can be seen in Figure 2. In the upper part of Figure 2, the components that are used to train and validate the artificia intelligence network are presented. The database, after it is prepared, is loaded in the Microsoft Azure Auto ML Service, where the artificial intelligence network is configured. Following the training and validation part, the trained model is realized. In the lower part of the image, the components used to test the trained model are presented. The SDR platform is used to send and receive modulated signals. The modulated samples received are inserted into the integrated trained model (integrated into Microsoft Azure cloud) that generates the answer with the identified modulation type. In this database, we find signals that are modulated using the following 24 modulation schemes: OOK, 4ASK, 8ASK, BPSK, QPSK, 8PSK, 16PSK, 32PSK, 16APSK, 32APSK, 64APSK, 128APSK, 16QAM, 32QAM, 64QAM, 128QAM, 256QAM, AM-SSB-WC, AM-SSB-SC, AM- DSB-WC, AM-DSB-SC, FM, GMSK, and OQPSK.
Table 2. Obtained dataset. The extracted data is written in a “CSV” file to ensure compatibility with the “Azure AutoML” service that is used to train and integrate the intelligent network. It must be clearly defined which data constitutes the inputs from which the characteristics necessary for training will be extracted and which data represent the outputs according to which the classification of the obtained results will be carried out. In order to extract the samples from the dataset, a shell script was used. The script has put the data in a separate folder for each modulation and inside the modulation folder in separate folders for test and training. The extracted complex data is written to a “CSV” (comma-separated values) file, which is the final database that is used for training, validation, and testing. In Table 2, the internal structure and content of the database can be seen.
Table 2. Obtained dataset. The extracted data is written in a “CSV” file to ensure compatibility with the “Azure AutoML” service that is used to train and integrate the intelligent network. It must be clearly defined which data constitutes the inputs from which the characteristics necessary for training will be extracted and which data represent the outputs according to which the classification of the obtained results will be carried out. In order to extract the samples from the dataset, a shell script was used. The script has put the data in a separate folder for each modulation and inside the modulation folder in separate folders for test and training. The extracted complex data is written to a “CSV” (comma-separated values) file, which is the final database that is used for training, validation, and testing. In Table 2, the internal structure and content of the database can be seen.
Table 3. Accuracy of models. The most important characteristic of the trained model is the confusion matrix. It can be seen in Table 4. As can be seen in the confusion matrix, the best results are recorded for the modulations: FM, BPSK, GMSK, OOK, and 4ASK. The worst results are recorded for the modulations: 8PSK, 16APSK, 32APSK, OPSK, and 8ASK.
Table 3. Accuracy of models. The most important characteristic of the trained model is the confusion matrix. It can be seen in Table 4. As can be seen in the confusion matrix, the best results are recorded for the modulations: FM, BPSK, GMSK, OOK, and 4ASK. The worst results are recorded for the modulations: 8PSK, 16APSK, 32APSK, OPSK, and 8ASK.
Table 4. Confusion matrix.
Table 4. Confusion matrix.
Table 5. Accuracy for each modulation.
Table 5. Accuracy for each modulation.
signal-modulation-clasiffication
signal-modulation-clasiffication
Figure 4. BPSK modulation/demodulation topology. The first implemented topology can be seen in Figure 4. In this topology, “BPSK” trans- mission and rece 8-bit integers wit ption are implemented. The data source is a random one that generates h values between 0 and 255. The integers are divided into 1-bit symbols and “BPSK” modulated. The modulated symbols are then interpolated to achieve a rate of eight samples per symbol. After sampling, an RRC (root-raised-cosine) filter is applied to prepare the transmission samples. The transmission is carried out with a sampling frequency equal to 1 MHZ. The RF frequency on which the data are transmitted is equal to 2.45 GHz. The transmitted signal can be seen in Figure 5. The reception of the signal is performed on he same RF frequency as the transmission and with the same sampling frequency. The received samples are written in a “CSV” file. This file is then used in order to test the trained model.
Figure 4. BPSK modulation/demodulation topology. The first implemented topology can be seen in Figure 4. In this topology, “BPSK” trans- mission and rece 8-bit integers wit ption are implemented. The data source is a random one that generates h values between 0 and 255. The integers are divided into 1-bit symbols and “BPSK” modulated. The modulated symbols are then interpolated to achieve a rate of eight samples per symbol. After sampling, an RRC (root-raised-cosine) filter is applied to prepare the transmission samples. The transmission is carried out with a sampling frequency equal to 1 MHZ. The RF frequency on which the data are transmitted is equal to 2.45 GHz. The transmitted signal can be seen in Figure 5. The reception of the signal is performed on he same RF frequency as the transmission and with the same sampling frequency. The received samples are written in a “CSV” file. This file is then used in order to test the trained model.
Figure 6. Received BPSK signal test. 4. Discussion
Figure 6. Received BPSK signal test. 4. Discussion
Table 6. Cloud-based neural networks vs. local neural networks.
Table 6. Cloud-based neural networks vs. local neural networks.
Table 7. Comparison of cloud-based neural networks and local neural networks results. The main further research direction consists of improving the neural network model by using a database with more modulation types that have a wider range of noise and interference. Another future research direction consists of the integration of the trained model into a system that will detect modulation type in real-time and will be able to demodulate it directly without human intervention.
Table 7. Comparison of cloud-based neural networks and local neural networks results. The main further research direction consists of improving the neural network model by using a database with more modulation types that have a wider range of noise and interference. Another future research direction consists of the integration of the trained model into a system that will detect modulation type in real-time and will be able to demodulate it directly without human intervention.

Related papers

A Machine Learning Approach to Modulation Detection in Wireless Communications
Venkataramani Kumar

NAECON 2021 - IEEE National Aerospace and Electronics Conference

Autonomous Modulation Detection (AMD) in the presence of unknown channel conditions is critical in spectrum sensing and channel estimation. Existing works achieve AMD by processing raw spectrum measurement data. However, such approaches are computationally complex and time-consuming in practice. We propose a novel AMD as a conglomeration of symbol level extraction and a simplified machine learning classifier. The salient feature of our work is the development of a symbol level extraction scheme that processes physical layer spectrum measurements. The extracted features further simplify the machine learning model design that not only reduces computational complexity but also increases classification performance. The proposed scheme was evaluated on both software as well as hardware testing platforms. The evaluation results were discussed using different metrics and a comprehensive study on the performance of this scheme is also included in this work.

View PDFchevron_right
The modulation recognition approaches for software radio
kachouri abdennaceur

2008

Nowadays there are different modulation types that are used in various digital communication systems such as surveillance and control of communication systems, so that the need to find efficient methods for their discrimination becomes a necessity. In this paper, we discuss two algorithms which are used for the automatic modulation classification: the Average

View PDFchevron_right
Signal Classification and Identification for Cognitive Radio
IRJET Journal

IRJET, 2022

SDR (software-defined radio) devices have gotten a lot of interest lately because to their low cost and ease of use when it comes to hands-on testing. In cognitive radio (CR), they may be utilised to create dynamic spectrum allocation (DSA) algorithms. These CRs are currently unable to determine which DSA method is most suited for a given situation, despite much study in both machine learning and signal processing. Machine learning and statistical signal processing approaches may be used to compare the spectrum sensing algorithms for CRs and spectrum observatories in resource restricted contexts. We've decided to take on the issues of detecting multiple transmitters and automatically classifying modulation patterns (AMC). Multiple transmitter identification algorithms using machine learning and statistical signal processing are evaluated side by side. For multi-transmitter identification, the machine learning method has an accuracy of 70 percent and 80 percent for two and five user systems, respectively, while the statistical signal processing technique has an accuracy of 50 percent for two and five user systems, respectively. Machine learning beats the signal processing technique for 1000 test samples in AMC, even if both algorithms have 100% accuracy beyond 10 dB for 100 test samples (64-QAM is an exception). Signal processing techniques in both situations take a fraction of the time needed by machine learning algorithms, according to the time comparison.

View PDFchevron_right
Compact automatic modulation recognition using over-the-air signals and FOS features
beei iaes, Obiseye Obiyemi, Abdultaofeek Abayomi

Bulletin of Electrical Engineering and Informatics , 2022

The recent deployment of automatic modulation recognition (AMR) for cognitive radio (CR) systems has significantly enhanced spectrum sensing capabilities. The utilization of real-time over-the-air digital radio frequency (RF) data for the development of a digital spectrum sensing model based on the automatic modulation classification (AMC) is presented in this study as a step for incorporating opportunistic spectrum sensing onto the NomadicBTS architecture. Some digital modulation techniques were studied for second-generation (2G) through fourth-generation (4G) technology. The raw RF signal dataset was digitized and curated, while non-complex first-order statistical (FOS) features were used with algorithms based on the Scaled conjugate gradient (SCG) and Levenberg-Marquardt (LM) to find the best learning algorithm for the generated AMR model. The results show that the developed AMR model has a very high likelihood of correctly classifying signals, with distinct patterns for each of the features of FOS. The results are compared to reveal a least mean square error (MSE) of 0.0131 with a maximum accuracy of 93.5 percent when the model was trained with seventy (70) neurons in the hidden layer using the LM method. The best model's accuracy will allow for the most precise identification of spectrum holes in the bands under consideration.

View PDFchevron_right
Fast Deep Learning for Automatic Modulation Classification
Diyu Yang

arXiv: Signal Processing, 2019

In this work, we investigate the feasibility and effectiveness of employing deep learning algorithms for automatic recognition of the modulation type of received wireless communication signals from subsampled data. Recent work considered a GNU radio-based data set that mimics the imperfections in a real wireless channel and uses 10 different modulation types. A Convolutional Neural Network (CNN) architecture was then developed and shown to achieve performance that exceeds that of expert-based approaches. Here, we continue this line of work and investigate deep neural network architectures that deliver high classification accuracy. We identify three architectures-namely, a Convolutional Long Short-term Deep Neural Network (CLDNN), a Long Short-Term Memory neural network (LSTM), and a deep Residual Network (ResNet)-that lead to typical classification accuracy values around 90% at high SNR. We then study algorithms to reduce the training time by minimizing the size of the training data set, while incurring a minimal loss in classification accuracy. To this end, we demonstrate the performance of Principal Component Analysis in significantly reducing the training time, while maintaining good performance at low SNR. We also investigate subsampling techniques that further reduce the training time, and pave the way for online classification at high SNR. Finally, we identify representative SNR values for training each of the candidate architectures, and consequently, realize drastic reductions of the training time, with negligible loss in classification accuracy. I. INTRODUCTION Automatic modulation classification plays an important role in modern wireless communication. It finds applications in various commercial and military areas. For example, Software Defined Radios (SDR) use blind recognition of the modulation type to quickly adapt to various communication systems, without requiring control overhead. In military settings, friendly signals should be securely received, while hostile signals need to be efficiently recognized typically without prior information. Under such conditions, advanced real-time signal processing and blind modulation recognition techniques are required. Modulation recognition may also prove to be an essential capability for identifying the source(s) of received wireless signals, which can enable various intelligent decisions for a context-aware autonomous wireless communication system.

View PDFchevron_right
Automatic signal recognition for a flexible spectrum management
Luca De Vito

The paper presents the prototype of an automatic digital modulation classifier, to be used for signal recognition in frequency bands managed in a flexible way. The prototype is based on a Data Acquisition System, consisting of an Analog-to-Digital converter embedded in an evaluation board, a frame grabber and a Personal Computer. The modulation classifier is able to recognize the most used digital modulations. An experimental validation of the realized prototype in a radio environment is also provided.

View PDFchevron_right
Comparison of Automatic Modulation Classification Techniques
ibrahim khider

Journal of Communications

The advancement of digital communication and technology triggered new challenges related to the channel and radio spectrum utilization. From the other hand, real-time communications are keen of time where requests need to be processed in very short time. Automatic modulation is one of promising approaches that relies on pretrained classifiers in order to recognize the type of modulation techniques used by the transmitter. Considering that noise is dominating between the transmitter and receiver, the task of automatic modulation classification is become harder. Noise is destroying the obvious features of the signals and degrade the classification accuracy. The modulation identification technique is made to recognize the type of modulation using the deep learning technology. This paper is listing the common stat of the arts used in automatic modulation classification along with their performance measures. It was realized that deep learning classifier manifested in Conventional Neural ...

View PDFchevron_right
Automatic digital modulation recognition using artificial neural network and genetic algorithm
M L Dennis Wong

Signal Processing, 2004

View PDFchevron_right
Experiences with using GNU Radio for Real-time Wireless Signal Classification
Samuel Ramirez

2018

The ability to monitor the wireless spectrum in real-time is important in a variety of environments including high-security and control-system environments such as power plants and military facilities, as well as shared spectrum environments such as the 3.5 GHz band model that was announced by the Federal Communications Commission (FCC). In all of these cases, real-time detection and classification of signals while minimizing missed detections and misclassifications is paramount. Motivated by these important applications, we built a real-time system for spectrum monitoring and analysis which uses GNU Radio and Universal Software Radio Peripheral (USRP) X310s. In this paper, we focus on the GNU Radio-specific implementation challenges we face as well as the approaches we take to tackle these challenges. We also present our experiences with our implementation. We show that in some instances, particularly message passing, we can achieve a substantial improvement in processing performan...

View PDFchevron_right
COMMUNICATION SIGNALS MODULATIONS CLASSIFICATION BASED ON NEURAL NETWORK ALGORITHMS
YAHYA BENREMDANE

Computer Science & Information Technology (CS & IT), 2023

This paper aims to find an automatic solution for the modulation’s classification of different types of radio signals by relying on Artificial Intelligence. This project is part of a long process of Communications Intelligence looking for an automatic solution to demodulate, decode and decipher communication signals. Our work therefore consisted in the choice of the database needed for supervised deep learning, the evaluation of existing techniques on raw communication signals, and the proposal of a solution based on deep learning networks allowing to classify the types of modulation with an optimal ratio (computation time / accuracy). We first carried out a research work on the existing models of automatic classification in order to use them as a reference. We consequently proposed an ensemble learning approach based on tuned ResNet and Transformer Neural Network that is efficient at extracting multi- scale features from the raw I/Q sequence data and also considers the challenge of predicting in low Signal Noise Ratio (SNR) conditions. In the end, we delivered an architecture that is easy to handle and apply to communication signals. This solution has an optimal and robust architecture that automatically determines the type of modulation with an accuracy up to 95%.

View PDFchevron_right

References (27)

  1. Garg, V.K. (Ed.) Fourth Generation Systems and New Wireless Technologies. In The Morgan Kaufmann Series in Networking, Wireless Communications & Networking, Morgan Kaufmann; Elsevier: Amsterdam, The Netherlands, 2007; pp. 1-22. ISBN 9780123735805.
  2. Javier, A.; Marian, U.; Dongho, Y. Integrating software-defined radios. In Computing in Communication Networks; Frank, H.P.F., Fabrizio, G., Patrick, S., Eds.; Academic Press: Cambridge, MA, USA, 2020; pp. 413-427. ISBN 9780128204887. [CrossRef]
  3. Tato, A. Software Defined Radio: A Brief Introduction. Proceedings 2018, 2, 1196. [CrossRef]
  4. Zhang, R.; Li, J.; Wu, J. A universal algorithm of modulation and demodulation. J. Electron. 2002, 19, 289-295. [CrossRef]
  5. Wang, C.; Qu, Y.; Tang, Y.P.T. IQ quadrature demodulation algorithm used in heterodyne detection. Infrared Phys. Technol. 2015, 72, 191-194. [CrossRef]
  6. Merz, R.; Botteron, C.; Farine, P.A. A novel low complexity data demodulation algorithm for pulse position modulation. Digit. Signal Process. 2012, 22, 535-543. [CrossRef]
  7. AI in Software Defined Radio. Available online: https://www.ni.com/ro-ro/innovations/white-papers/19/artificial- intelligence-in-software-defined-sigint-systems.html#section-1134962763 (accessed on 16 December 2022).
  8. Bonati, L.; Polese, M.; D'Oro, S.; Basagni, S.; Melodia, T. OpenRAN Gym: AI/ML development, data collection, and testing for O-RAN on PAWR platforms. Comput. Netw. 2023, 220, 109502. [CrossRef]
  9. Shevitski, B.; Watkins, Y.; Man, N.; Girard, M. Digital Signal Processing Using Deep Neural Networks. arXiv 2021, arXiv:2109.10404.
  10. Choi, J.; Dongryul, P.; Suil, K.; Seungyoung, A. Implementation of a Noise-Shaped Signaling System through Software-Defined Radio. Appl. Sci. 2022, 12, 641. [CrossRef]
  11. DARPA Colosseum. Available online: https://www.mwrf.com/technologies/test-measurement/article/21848345/darpas- colosseum-emulates-em-environments (accessed on 16 December 2022).
  12. O'Shea, T.J.; Roy, T.; Clancy, T.C. Over-the-air deep learning based radio signal classification. IEEE J. Sel. Top. Signal Process. 2018, 12, 168-179. [CrossRef]
  13. Krizhevsky, A.; Sutskever, I.; Hinton, G.E. Imagenet classification with deep convolutional neural networks. In Proceedings of the Advances in Neural Information Processing Systems, Lake Tahoe, NV, USA, 3-6 December 2012; pp. 1097-1105.
  14. Sainath, T.; Weiss, R.J.; Wilson, K.; Senior, A.W.; Vinyals, O. Learning the speech front-end with raw waveform cldnns. In Proceedings of the 16th Annual Conference of the International Speech Communication Association (INTERSPEECH 2015), Dresden, Germany, 6-10 September 2015.
  15. O'Shea, T.J.; Corgan, J.; Clancy, T.C. Convolutional radio modulation recognition networks. In Proceedings of the Engineering Applications of Neural Networks, Aberdeen, UK, 2-5 September 2016; pp. 213-226.
  16. Sadeghi, M.; Larsson, E.G. Adversarial attacks on deep-learning based radio signal classification. IEEE Wirel. Commun. Lett. 2018, 8, 213-216. [CrossRef]
  17. Shi, Y.; Davaslioglu, K.; Sagduyu, Y.E.; Headley, W.C.; Fowler, M.; Green, G. Deep learning for RF signal classification in unknown and dynamic spectrum environments. In Proceedings of the 2019 IEEE International Symposium on Dynamic Spectrum Access Networks (DySPAN), Newark, NJ, USA, 11-14 November 2019; IEEE: Piscataway, NJ, USA, 2019; pp. 1-10.
  18. Bonati, L.; Polese, M.; D'Oro, S.; Basagni, S.; Melodia, T. Open, programmable, and virtualized 5G networks: State-of-the-art and the road ahead. Comput. Netw. 2020, 182, 107516. [CrossRef]
  19. Rugeles, J.D.J.; Guillen, E.P.; Cardoso, L.S. A Technical Review of Wireless security for the Internet of things: Software Defined Radio perspective. arXiv 2020, arXiv:2009.10171. [CrossRef]
  20. DLHUB Homepage. Available online: https://www.anscenter.com/ans-ai-products/ANS-Deep-Learning-Studio (accessed on 16 December 2022).
  21. ANNHUB Homepage. Available online: https://www.anscenter.com/ans-ai-products/ANS-Machine-Learning-Studio (ac- cessed on 16 December 2022).
  22. Anscenter Homepage. Available online: https://www.anscenter.com/ (accessed on 16 December 2022).
  23. Azure AutoML Description. Available online: https://docs.microsoft.com/en-us/azure/machine-learning/concept-automated- ml (accessed on 16 December 2022).
  24. GNU Radio Homepage. Available online: https://wiki.gnuradio.org/index.php/Main_Page (accessed on 16 December 2022).
  25. RF Database. Available online: https://www.deepsig.ai/datasets (accessed on 16 December 2022).
  26. Azure Container Instances. Available online: https://azure.microsoft.com/en-us/services/container-instances/ (accessed on 16 December 2022).
  27. Disclaimer/Publisher's Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.

Related papers

Artificial Neural Network based Automatic Modulation Classification over a Software Defined Radio Testbed
Jithin Jagannath

Automatic modulation classification (AMC) is an essential component of several intelligent communication systems. In this paper, we design and evaluate a practical AMC system that can be readily deployed to provide robust performance in various real-time commercial scenarios. Thus, our main goal is to develop a robust AMC algorithm with low computational complexity for easy implementation and practical deployment. To this end, we utilize recently revitalized machine learning based approaches used for various classification purposes. In our proposed AMC architecture, we first propose various statistics that serve as features of the AMC signals; next, we design an artificial neural network (ANN) based classifier that performs AMC over a wide range of SNRs. We employ Nesterov accelerated adaptive moment (NADAM) estimation technique to improve the classification performance of our ANN. Further, to establish the practical feasibility of our proposed architecture, we implement it on a SDR testbed. The proposed ANN-based classifier is shown to outperforms the hybrid hierarchical AMC (HH-AMC) [1] system and is flexible enough to easily expand the dictionary of modulation formats for other applications.

View PDFchevron_right
Implementation of Digital Modulation Identification on Signal Processing Platform for Software Defined Radio Extended
Ahmed Bakhraiba

Software Defined Radio (SDR) has been used by many military and commercial communication applications. The need to identify the digital modulation type of an incoming radio signal is important in order to design an intelligent system that can be used for different applications. This paper describes an approach to extract the transient characteristics of the digital modulated signal using the wavelet transform technique, allowing a simple identification process. A method for identify the modulated signal scheme from the wavelet transform is described, and the performance of the identifier is investigated through simulation for different signal to noise ratio (SNR) values, showed that the system identification performance is improved more than 95% when SNR more than 9dB for all the proposed modulated signal in the system.

View PDFchevron_right
Intelligent Digital Signal Modulation Recognition using Machine Learning
Sadegh Aminifar

Journal of Computer Science

In recent years, modulation type recognition has received a lot of attention across the board. There are several methods to detect modulation types, but there are only a few effective methods to handle signals with a higher level of noise. This study introduces an approach to verify the ability of different machine learning algorithms to automatically manage noise in detecting digital modulations. This research examines two of the most common digital modulations, Phase Shift Keying and Quadrature Phase Shift Keying. A signal noise rate ranging from-10 to +25 dB is used to identify these modulations and use PCA to reduce the number of features and the data complexity. We used machine learning algorithms like Decision Tree, Random Forest, Support Vectors Machine and k-nearest neighbors to identify the modulation type. Our proposed method considers signals' features after proper shifting of the IQ and RF signals samples. The findings show that the proposed method successfully recognizes the signals with higher noise levels. The random forest algorithm presents better results with low noise levels and SVM with higher noise levels.

View PDFchevron_right
Machine Learning Based Automatic Modulation Recognition for Wireless Communications: A Comprehensive Survey
bachir jdid

IEEE Access

The rapid development of information and wireless communication technologies together with the large increase in the number of end-users have made the radio spectrum more crowded than ever. Besides, providing a stable and reliable service is challenging, as electromagnetic environments are evolving and becoming more sophisticated. Accordingly, there is an urgent need for more reliable and intelligent communication systems that can improve the spectrum efficiency and the quality of service to provide agile management of network resources, so as to better meet the needs of future wireless users. Specifically, Automatic Modulation Recognition (AMR) plays an essential role in most intelligent communication systems especially with the emergence of Software Defined Radio (SDR). AMR is an indispensable task while performing spectrum sensing in Cognitive Radio (CR). Thanks to the significant advancements in Deep Learning (DL) applications, new and powerful tools have been provided which can tackle problems in this space. Thus, today, integrating DL models into AMR has gained the attention of many researchers. This work aims to provide a comprehensive state-of-the-art review of the most recent Machine Learning (ML) based AMR methods for Single-Input Single-Output (SISO) and Multiple-Input Multiple-Output (MIMO) systems. Furthermore, the architecture of each model will be identified along with a detailed comparison in terms of specifications and performance. Finally, an outline of the open problems, challenges, and potential research directions is provided along with discussion and conclusion.

View PDFchevron_right
Practical signal detection and classification in gnu radio
Nasser Aliraqi

SDR Forum Technical Conference ( …, 2007

View PDFchevron_right

Related topics

  • Computer Science
  • Software Defined Radio
  • Software
    • 580 California St., Suite 400
    San Francisco, CA, 94104
    © 2025 Academia. All rights reserved