Real-Time and Embedded Deep Learning on FPGA for RF Signal Classification

We designed and implemented a deep learning based RF signal classifier on the Field Programmable Gate Array (FPGA) of an embedded software-defined radio platform, DeepRadio™, that classifies the signals received through the RF front end to different modulation types in real time and with low power. This classifier implementation successfully captures complex characteristics of wireless signals to serve critical applications in wireless security and communications systems such as identifying spoofing signals in signal authentication systems, detecting target emitters and jammers in electronic warfare (EW) applications, discriminating primary and secondary users in cognitive radio networks, interference hunting, and adaptive modulation. Empowered by low-power and low-latency embedded computing, the deep neural network runs directly on the FPGA fabric of DeepRadio™, while maintaining classifier accuracy close to the software performance. We evaluated the performance when another SDR (USRP) transmits signals with different modulation types at different power levels and DeepRadio™receives the signals and classifies them in real time on its FPGA. A smartphone with a mobile app is connected to DeepRadio™to initiate the experiment and visualize the classification results. With real radio transmissions over the air, we show that the classifier implemented on DeepRadio™achieves high accuracy with low latency (microsecond per sample) and low energy consumption (microJoule per sample), and this performance is not matched by other embedded platforms such as embedded graphics processing unit (GPU).

[1]  Anthony Ephremides,et al.  Jamming games in wireless networks with incomplete information , 2011, IEEE Communications Magazine.

[2]  Yalin E. Sagduyu,et al.  A Unified Solution to Cognitive Radio Programming, Test and Evaluation for Tactical Communications , 2017, IEEE Communications Magazine.

[3]  David A. Wagner,et al.  Towards Evaluating the Robustness of Neural Networks , 2016, 2017 IEEE Symposium on Security and Privacy (SP).

[4]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[5]  Yalin E. Sagduyu,et al.  Deep Learning for Launching and Mitigating Wireless Jamming Attacks , 2018, IEEE Transactions on Cognitive Communications and Networking.

[6]  Kemal Davaslioglu,et al.  Adversarial Deep Learning for Cognitive Radio Security: Jamming Attack and Defense Strategies , 2018, 2018 IEEE International Conference on Communications Workshops (ICC Workshops).

[7]  Stratis Ioannidis,et al.  DeepRadioID: Real-Time Channel-Resilient Optimization of Deep Learning-based Radio Fingerprinting Algorithms , 2019, MobiHoc.

[8]  Dong-Ho Cho,et al.  Deep Sensing: Cooperative Spectrum Sensing Based on Convolutional Neural Networks , 2017, ArXiv.

[9]  Jakob Hoydis,et al.  An Introduction to Deep Learning for the Physical Layer , 2017, IEEE Transactions on Cognitive Communications and Networking.

[10]  Petri Mähönen,et al.  The Importance of Being Earnest: Performance of Modulation Classification for Real RF Signals , 2018, 2018 IEEE International Symposium on Dynamic Spectrum Access Networks (DySPAN).

[11]  Sofie Pollin,et al.  Deep Learning Models for Wireless Signal Classification With Distributed Low-Cost Spectrum Sensors , 2017, IEEE Transactions on Cognitive Communications and Networking.

[12]  Jin Wang,et al.  Semi-supervised Learning with Generative Adversarial Networks on Digital Signal Mod-ulation Classification , 2018 .

[13]  Volkan Isler,et al.  QoS and Jamming-Aware Wireless Networking Using Deep Reinforcement Learning , 2019, MILCOM 2019 - 2019 IEEE Military Communications Conference (MILCOM).

[14]  Jun Won Choi,et al.  Deep neural network-based automatic modulation classification technique , 2016, 2016 International Conference on Information and Communication Technology Convergence (ICTC).

[15]  Kemal Davaslioglu,et al.  Generative Adversarial Network for Wireless Signal Spoofing , 2019, WiseML@WiSec.

[16]  Osvaldo Simeone,et al.  A Very Brief Introduction to Machine Learning With Applications to Communication Systems , 2018, IEEE Transactions on Cognitive Communications and Networking.

[17]  Yangyu Fan,et al.  Unsupervised feature learning and automatic modulation classification using deep learning model , 2017, Phys. Commun..

[18]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[19]  Geoffrey Ye Li,et al.  Power of Deep Learning for Channel Estimation and Signal Detection in OFDM Systems , 2017, IEEE Wireless Communications Letters.

[20]  Yi Shi,et al.  Distributed cognitive radio network architecture, SDR implementation and emulation testbed , 2015, MILCOM 2015 - 2015 IEEE Military Communications Conference.

[21]  Yu-Dong Yao,et al.  Modulation classification using convolutional Neural Network based deep learning model , 2017, 2017 26th Wireless and Optical Communication Conference (WOCC).

[22]  Simon Haykin,et al.  Cognitive radio: brain-empowered wireless communications , 2005, IEEE Journal on Selected Areas in Communications.

[23]  Yalin E. Sagduyu,et al.  Spectrum Data Poisoning with Adversarial Deep Learning , 2018, MILCOM 2018 - 2018 IEEE Military Communications Conference (MILCOM).

[24]  Yi Shi,et al.  IoT Network Security from the Perspective of Adversarial Deep Learning , 2019, 2019 16th Annual IEEE International Conference on Sensing, Communication, and Networking (SECON).

[25]  T. Charles Clancy,et al.  Convolutional Radio Modulation Recognition Networks , 2016, EANN.

[26]  Jin Wei,et al.  Deep learning-based automated modulation classification for cognitive radio , 2016, 2016 IEEE International Conference on Communication Systems (ICCS).

[27]  Junshan Zhang,et al.  Spectrum shaping via network coding in cognitive radio networks , 2011, 2011 Proceedings IEEE INFOCOM.

[28]  T. Charles Clancy,et al.  Over-the-Air Deep Learning Based Radio Signal Classification , 2017, IEEE Journal of Selected Topics in Signal Processing.

[29]  Yun Lin,et al.  Semi-Supervised Learning with Generative Adversarial Networks on Digital Signal Modulation Classification , 2018 .

[30]  Kemal Davaslioglu,et al.  Generative Adversarial Learning for Spectrum Sensing , 2018, 2018 IEEE International Conference on Communications (ICC).

[31]  Geoffrey Ye Li,et al.  A Model-Driven Deep Learning Network for MIMO Detection , 2018, 2018 IEEE Global Conference on Signal and Information Processing (GlobalSIP).

[32]  Walid Saad,et al.  Machine Learning for Wireless Networks with Artificial Intelligence: A Tutorial on Neural Networks , 2017, ArXiv.

[33]  Kemal Davaslioglu,et al.  Deep Learning for RF Signal Classification in Unknown and Dynamic Spectrum Environments , 2019, 2019 IEEE International Symposium on Dynamic Spectrum Access Networks (DySPAN).