TY - GEN
T1 - FPGA Deployment of Deep Neural Network for Modulation Recognition
AU - Xu, Zhuang
AU - Luo, Yunxiang
AU - Yao, Wei
AU - Yang, Xi
AU - Peng, Shengliang
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - Modulation recognition is an important task in intelligent communications, and modulation recognition using deep neural network has gained considerable attention due to the rapid advancement of deep learning technology. However, implementing modulation recognition using deep neural network on a general-purpose platform is time-consuming, which makes it difficult to meet the high-speed and real-time requirements of practical applications. To address the issue, this paper proposes a field-programmable gate array (FPGA) deployment system for modulation recognition network. The proposed system leverages parallel computing and pipeline methods to significantly enhance the inference speed of the modulation network, Experiment results show that FPGA as a hardware accelerator can run parallel calculations up to 139 times faster than the ARM Cortex-A9 processor.
AB - Modulation recognition is an important task in intelligent communications, and modulation recognition using deep neural network has gained considerable attention due to the rapid advancement of deep learning technology. However, implementing modulation recognition using deep neural network on a general-purpose platform is time-consuming, which makes it difficult to meet the high-speed and real-time requirements of practical applications. To address the issue, this paper proposes a field-programmable gate array (FPGA) deployment system for modulation recognition network. The proposed system leverages parallel computing and pipeline methods to significantly enhance the inference speed of the modulation network, Experiment results show that FPGA as a hardware accelerator can run parallel calculations up to 139 times faster than the ARM Cortex-A9 processor.
UR - https://www.scopus.com/pages/publications/85174713358
U2 - 10.1109/CYBER59472.2023.10256533
DO - 10.1109/CYBER59472.2023.10256533
M3 - 会议稿件
AN - SCOPUS:85174713358
T3 - Proceedings of 13th IEEE International Conference on CYBER Technology in Automation, Control, and Intelligent Systems, CYBER 2023
SP - 1397
EP - 1402
BT - Proceedings of 13th IEEE International Conference on CYBER Technology in Automation, Control, and Intelligent Systems, CYBER 2023
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 13th IEEE International Conference on CYBER Technology in Automation, Control, and Intelligent Systems, CYBER 2023
Y2 - 11 July 2023 through 14 July 2023
ER -