Automatic modulation recognition(AMR) of radar signals is a currently active area, especially in electronic reconnaissance, where systems need to quickly identify the intercepted signal and formulate corresponding interference measures on computationally limited platforms. However, previous methods generally have high computational complexity and considerable network parameters, making the system unable to detect the signal timely in resource-constrained environments. This letter firstly proposes an efficient modulation recognition network(EMRNet) with tiny and low latency models to match the requirements for mobile reconnaissance equipments. One-dimensional residual depthwise separable convolutions block(1D-RDSB) with an adaptive size of receptive fields is developed in EMRNet to replace the traditional convolution block. With 1D-RDSB, EMRNet achieves a high classification accuracy and dramatically reduces computation cost and network paraments. The experiment results show that EMRNet can achieve higher precision than existing 2D-CNN methods, while the computational cost and parament amount of EMRNet are reduced by about 13.93× and 80.88×, respectively.
Kuiyu CHEN
Nanjing University of Science and Technology
Jingyi ZHANG
Nanjing University of Science and Technology
Shuning ZHANG
Nanjing University of Science and Technology
Si CHEN
Nanjing University of Science and Technology
Yue MA
Nanjing University of Science and Technology
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Kuiyu CHEN, Jingyi ZHANG, Shuning ZHANG, Si CHEN, Yue MA, "EMRNet: Efficient Modulation Recognition Networks for Continuous-Wave Radar Signals" in IEICE TRANSACTIONS on Electronics,
vol. E106-C, no. 8, pp. 450-453, August 2023, doi: 10.1587/transele.2022ECS6006.
Abstract: Automatic modulation recognition(AMR) of radar signals is a currently active area, especially in electronic reconnaissance, where systems need to quickly identify the intercepted signal and formulate corresponding interference measures on computationally limited platforms. However, previous methods generally have high computational complexity and considerable network parameters, making the system unable to detect the signal timely in resource-constrained environments. This letter firstly proposes an efficient modulation recognition network(EMRNet) with tiny and low latency models to match the requirements for mobile reconnaissance equipments. One-dimensional residual depthwise separable convolutions block(1D-RDSB) with an adaptive size of receptive fields is developed in EMRNet to replace the traditional convolution block. With 1D-RDSB, EMRNet achieves a high classification accuracy and dramatically reduces computation cost and network paraments. The experiment results show that EMRNet can achieve higher precision than existing 2D-CNN methods, while the computational cost and parament amount of EMRNet are reduced by about 13.93× and 80.88×, respectively.
URL: https://global.ieice.org/en_transactions/electronics/10.1587/transele.2022ECS6006/_p
Copy
@ARTICLE{e106-c_8_450,
author={Kuiyu CHEN, Jingyi ZHANG, Shuning ZHANG, Si CHEN, Yue MA, },
journal={IEICE TRANSACTIONS on Electronics},
title={EMRNet: Efficient Modulation Recognition Networks for Continuous-Wave Radar Signals},
year={2023},
volume={E106-C},
number={8},
pages={450-453},
abstract={Automatic modulation recognition(AMR) of radar signals is a currently active area, especially in electronic reconnaissance, where systems need to quickly identify the intercepted signal and formulate corresponding interference measures on computationally limited platforms. However, previous methods generally have high computational complexity and considerable network parameters, making the system unable to detect the signal timely in resource-constrained environments. This letter firstly proposes an efficient modulation recognition network(EMRNet) with tiny and low latency models to match the requirements for mobile reconnaissance equipments. One-dimensional residual depthwise separable convolutions block(1D-RDSB) with an adaptive size of receptive fields is developed in EMRNet to replace the traditional convolution block. With 1D-RDSB, EMRNet achieves a high classification accuracy and dramatically reduces computation cost and network paraments. The experiment results show that EMRNet can achieve higher precision than existing 2D-CNN methods, while the computational cost and parament amount of EMRNet are reduced by about 13.93× and 80.88×, respectively.},
keywords={},
doi={10.1587/transele.2022ECS6006},
ISSN={1745-1353},
month={August},}
Copy
TY - JOUR
TI - EMRNet: Efficient Modulation Recognition Networks for Continuous-Wave Radar Signals
T2 - IEICE TRANSACTIONS on Electronics
SP - 450
EP - 453
AU - Kuiyu CHEN
AU - Jingyi ZHANG
AU - Shuning ZHANG
AU - Si CHEN
AU - Yue MA
PY - 2023
DO - 10.1587/transele.2022ECS6006
JO - IEICE TRANSACTIONS on Electronics
SN - 1745-1353
VL - E106-C
IS - 8
JA - IEICE TRANSACTIONS on Electronics
Y1 - August 2023
AB - Automatic modulation recognition(AMR) of radar signals is a currently active area, especially in electronic reconnaissance, where systems need to quickly identify the intercepted signal and formulate corresponding interference measures on computationally limited platforms. However, previous methods generally have high computational complexity and considerable network parameters, making the system unable to detect the signal timely in resource-constrained environments. This letter firstly proposes an efficient modulation recognition network(EMRNet) with tiny and low latency models to match the requirements for mobile reconnaissance equipments. One-dimensional residual depthwise separable convolutions block(1D-RDSB) with an adaptive size of receptive fields is developed in EMRNet to replace the traditional convolution block. With 1D-RDSB, EMRNet achieves a high classification accuracy and dramatically reduces computation cost and network paraments. The experiment results show that EMRNet can achieve higher precision than existing 2D-CNN methods, while the computational cost and parament amount of EMRNet are reduced by about 13.93× and 80.88×, respectively.
ER -