Over-the-Air Modulation Classification using Deep Learning in Fading Channels for Cognitive Radio

K R Arjun; T P Surekha

doi:10.17485/IJST/v14i46.2073

Article

Over-the-Air Modulation Classification using Deep Learning in Fading Channels for Cognitive Radio

VIEWS 1649
PDF 437

Indian Journal of Science and Technology

DOI: 10.17485/IJST/v14i46.2073

Year: 2021, Volume: 14, Issue: 46, Pages: 3360-3369

Original Article

Over-the-Air Modulation Classification using Deep Learning in Fading Channels for Cognitive Radio

K R Arjun^1,*, T P Surekha²

¹ Research Scholar, Department of Electronics & Communication, Vidyavardhaka College of Engineering, Mysore, 570002, India
² Professor, Department of Electronics & Communication, Vidyavardhaka College of Engineering, Mysore, 570002, India

*Corresponding author email: [email protected]

Received Date:02 December 2021, Accepted Date:23 December 2021, Published Date:24 December 2021

This work is licensed under a Creative Commons Attribution 4.0 International License.

Abstract

Background/Objectives: The ability to recognize the type of modulation is a critical function of Cognitive Radio. The objective of this study is to increase the modulation classification efficiency in Over-The-Air (OTA) signals by utilizing channel characteristics that are strong. Methods: In this work, we demonstrate how to classify Over-The-Air modulation using a deep learning technique under various fading channels simulating real-time data. The network recognizes eight different digital modulation schemes and three different analogue modulation methods. Each modulation scheme will consist of 10,000 frames with 1024 samples per frame and a sampling rate of 200 kHz. Each sample will pass through fading channels prior to training, with 80% of samples are for training, 10% for validation, and 10% for testing. Six convolutional layers and one fully linked layer comprise our network. The final convolution layer is followed by a batch normalization layer, an activation layer utilizing rectified linear units (ReLUs), and a maximum pooling layer. As a result, the final convolution layer contains soft-max activation instead of the maximum pooling layer. Findings: Modulation categorization OTA is done with two separate ADALM-PLUTO SDRs working in various channel configurations. Network-I has a forecast accuracy of 91.4 percent using 12 Mini-Batch Size and 256 Epochs, whereas Network-II has a prediction accuracy of 95.3 percent using 24 Mini-Batch Size and 128 Epochs. There are a number of ways in which SDR technology can aid to make computer-generated data more realistic, such as adopting alternative channel models. Novelty: Using Software Defined Radio hardware; the same network was used to analyze various fading situations, such as Rayleigh, Rician or Lognormal distributions, and to optimize the network topology by adjusting hyper-parameters to increase accuracy.

Keywords: Cognitive Radios (CR), Fading Channel, OTA, SDR, and Modulation

References

Danesh K, Vasuhi S, S. An effective spectrum sensing in cognitive radio networks using improved convolution neural network by glow worm swarm algorithm. Transactions on Emerging Telecommunications Technologies. 2021;32(11):e4328. Available from: https://doi.org/10.1002/ett.4328
López D, Rivas E, Gualdron O. Primary user characterization for cognitive radio wireless networks using a neural system based on Deep Learning. Artificial Intelligence Review. 2017;52(1):169–195. doi: 10.1007/s10462-017-9600-4
Gravelle C, Zhou R. SDR Demonstration of Signal Classification in Real-Time Using Deep Learning. 2019 IEEE Globecom Workshops (GC Wkshps). 2019;p. 1–5. doi: 10.1109/GCWkshps45667.2019.9024661
Li W, Zhang K, Lei W, Shen R. Dynamic cooperative spectrum sensing in cognitive radio networks. 2011 International Conference on Computational Problem-Solving (ICCP). 2011;10:1354–1358. doi: 10.1109/iccps.2011.6089785
Jdid B, Hassan K, Dayoub I, Lim WH, Mokayef M. Machine Learning Based Automatic Modulation Recognition for Wireless Communications: A Comprehensive Survey. IEEE Access. 2021;9:57851–57873. doi: 10.1109/ACCESS.2021.3071801
Goyal SB, Bedi P, Kumar J, Varadarajan V. Deep learning application for sensing available spectrum for cognitive radio: An ECRNN approach. Peer-to-Peer Networking and Applications. 2021;14:3235–3249. doi: 10.1007/s12083-021-01169-4
Stephan T, Al-Turjman F, SJ, Balusamy B. Energy and spectrum aware unequal clustering with deep learning based primary user classification in cognitive radio sensor networks. International Journal of Machine Learning and Cybernetics. 2021;12(11):3261–3294. doi: 10.1007/s13042-020-01154-y
O'shea TJ, Roy T, Clancy TC. Over-the-Air Deep Learning Based Radio Signal Classification. IEEE Journal of Selected Topics in Signal Processing. 2018;12(1):168–179. doi: 10.1109/jstsp.2018.2797022
Wang Y, Liu M, Yang J, Gui G. Data-Driven Deep Learning for Automatic Modulation Recognition in Cognitive Radios. IEEE Transactions on Vehicular Technology. 2019;68(4):4074–4077. doi: 10.1109/tvt.2019.2900460
Hanna S, Dick C, Cabric D. Signal Processing Based Deep Learning for Blind Symbol Decoding and Modulation Classification. IEEE Journal on Selected Areas in Communications. . doi: 10.1109/JSAC.2021.3126088
Lu H, Bo L. WDLReconNet: Compressive Sensing Reconstruction With Deep Learning Over Wireless Fading Channels. IEEE Access. 2019;7:24440–24451. doi: 10.1109/access.2019.2900715
Awe OP, Babatunde DA, Lambotharan S, Assadhan B. Second order Kalman filtering channel estimation and machine learning methods for spectrum sensing in cognitive radio networks. Wireless Networks. 2021;27:3273–3286. doi: 10.1007/s11276-021-02627-w
Zheng S, Chen S, Qi P, Zhou H, Yang X. Spectrum sensing based on deep learning classification for cognitive radios. China Communications. 2020;17(2):138–148. doi: 10.23919/JCC.2020.02.012
Nasser A, Chaitou M, Mansour A, Yao KC, Charara H. A Deep Neural Network Model for Hybrid Spectrum Sensing in Cognitive Radio. Wireless Personal Communications. 2021;118(1):281–299. doi: 10.1007/s11277-020-08013-7
Nasser A, Chaitou M, Mansour A, Yao KC, Charara H. A Deep Neural Network Model for Hybrid Spectrum Sensing in Cognitive Radio. Wireless Personal Communications. 2021;118(1):281–299. doi: 10.1007/s11277-020-08013-7
Xu T, Darwazeh I. Deep Learning for Over-the-Air Non-Orthogonal Signal Classification. 2020 IEEE 91st Vehicular Technology Conference (VTC2020-Spring). 2020;p. 1–5. doi: 10.1109/VTC2020-Spring48590.2020.9128869
Ahmed R, Chen Y, Hassan B. Deep residual learning-based cognitive model for detection and classification of transmitted signal patterns in 5G smart city networks. Digital Signal Processing. 120:2022. doi: 10.1016/j.dsp.2021.103290
Li X, Fang J, Cheng W, Duan H, Chen Z, Li H. Intelligent Power Control for Spectrum Sharing in Cognitive Radios: A Deep Reinforcement Learning Approach. IEEE Access. 2018;6:25463–25473. doi: 10.1109/access.2018.2831240
Singh Chauhan P, Kumar S, Kumar Upaddhyay V, Mishra R, Kumar B, Soni SK. Performance analysis of ED over air-to-ground and ground-to-ground fading channels: A unified and exact solution. AEU - International Journal of Electronics and Communications. 138:2021. doi: 10.1016/j.aeue.2021.153839
O’mahony GD, Mccarthy KG, Harris PJ, Murphy CC. Developing a Low-Order Statistical Feature Set Based on Received Samples for Signal Classification in Wireless Sensor Networks and Edge Devices. IoT. 2021:449–475. doi: 10.3390/iot2030023

Copyright

© 2021 © 2021 Arjun & Surekha. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

Published By Indian Society for Education and Environment (iSee)