基于随机共振和多尺度特征融合调制识别方法

doi:10.12305/j.issn.1001-506X.2026.06.30

Abstract

Abstract:

Automatic modulation recognition （AMR） is critical for non-cooperative communication in complex electromagnetic environments such as electronic warfare and spectrum monitoring. However, existing methods suffer from noise interference and insufficient feature extraction capabilities under low signal-to-noise ratio （SNR） conditions. To address this, an AMR method integrating stochastic resonance （SR） and a dual-input SR network （DualSR-Net）is proposed. By jointly leveraging raw inphase quadrature（IQ） data and SR-enhanced IQ data, noise energy conversion and multi-scale feature fusion are used to enhance recognition robustness. Experiment demonstrates classification accuracy improvements of 3%–6.5% across the full SNR range compared to existing methods, especially in low SNR (?8?0 dB) scenarios, it is improved by 5.7%–9.6%, which is significantly better than the mainstream model. The dual-channel architecture combines time-frequency enhancement with deep feature learning, offering a new solution for reliable modulation classification in harsh environments.

Key words: automatic modulation recognition (AMR), stochastic resonance, feature fusion

CLC Number:

TN 975

Penghao WANG, Di HE, Mingyi YOU, Xiping GUO. Modulation recognition method based on stochastic resonance and multi-scale features fusion[J]. Systems Engineering and Electronics, 2026, 48(6): 2096-2104.

Figures/Tables 11

Fig.1

Fig.2

Fig.3

Fig.4

Table 1

Table 2

Fig.5

Fig.6

Table 3

Table 4

Table 5

References 21

1	ZHANG X X, CHEN X F, WANG Y, et al. Lightweight automatic modulation classification via progressive differentiable architecture search[J]. IEEE Trans. on Cognitive Communications and Networking, 2023, 9 (6): 1519- 1530. doi: 10.1109/TCCN.2023.3306391
2	陈杰豪, 王江. 基于循环谱的去模糊调制识别算法[J]. 现代电子技术, 2024, 47 (15): 47- 52.
	CHEN J H, WANG J. Deblurring modulation recognition algorithm based on cyclic spectrum[J]. Modern Electronic Technology, 2024, 47 (15): 47- 52.
3	江汉, 胡林, 李文, 等. 信号调制识别的对抗样本攻防技术研究进展[J]. 数据采集与处理, 2023, 38 (6): 1235- 1256.
	JIANG H, HU L, LI W, et al. Research progress of adversarial attack and defense for signal modulation recognition[J]. Journal of Data Acquisition & Processing, 2023, 38 (6): 1235- 1256.
4	SU W, XU J L , ZHOU M C. Real-time modulation classification based on maximum likelihood[J]. IEEE Communications Letters, 2008, 12(11): 801–803.
5	ZHANG X L, GE T T, CHEN Z M. Automatic modulation recognition of communication signals based on instantaneous statistical characteristics and SVM classifier[C]// Proc. of the IEEE Asia-Pacific Conference on Antennas and Propagation, 2018: 344–346.
6	KOSTIS T, MANOLIS S, GEORGE V, et al. Phasma: an automatic modulation classification system based on random forest[C]// Proc. of the IEEE International Symposium on Dynamic Spectrum Access Networks, 2017.
7	O’SHEA T J, CORGAN J, CLANCY T C, et al. Convolutional radio modulation recognition networks[C]//Proc. of the International Conference on Engineering Applications of Neural Networks, 2016: 213−226.
8	NATHAN E, TIM O. Deep architectures for modulation recognition[C]// Proc. of the IEEE International Symposium on Dynamic Spectrum Access Networks, 2017.
9	NJOKU J, MANUEL EUGENIO M, WANSU L. CGDNet: efficient hybrid deep learning model for robust automatic modulation recognition[J]. IEEE Networking Letters, 2021, 3 (2): 47- 51. doi: 10.1109/LNET.2021.3057637
10	ZHANG F X, LUO C B, XU J L, et al. An efficient deep learning model for automatic modulation recognition based on parameter estimation and transformation[J]. IEEE Communications Letters, 2021, 25 (10): 3287- 3290. doi: 10.1109/LCOMM.2021.3102656
11	HAMIDI-RAD S, JAIN S. MCformer: a transformer based deep neural network for automatic modulation classification[C]// Proc. of the IEEE Global Communications Conference, 2021.
12	HU Y Q, LI C Z, WANG X B, et al. Modulation recognition of optical and electromagnetic waves based on transfer learning[J]. Optik （Stuttgart）, 2023, 291, 171359. doi: 10.1016/j.ijleo.2023.171359
13	DING C R, XU D Y. Deep automatic modulation classification using deformation-insensitive color constellation[C]// Proc. of the IEEE 97th Vehicular Technology Conference , 2023.
14	LIU F G, PAN J Y, ZHOU R L. Contrastive learning-based multimodal fusion model for automatic modulation recognition[J]. IEEE Communications Letters, 2024, 28 (1): 78- 82. doi: 10.1109/LCOMM.2023.3343053
15	CHEN T, ZHENG S L, QIU K F, et al. Augmenting radio signals with wavelet transform for deep learning-based modulation recognition[J]. IEEE Trans. on Cognitive Communications and Networking, 2024, 10 (6): 2029- 2044. doi: 10.1109/TCCN.2024.3400525
16	胡茑庆. 随机共振微弱特征信号检测理论与方法[M]. 北京: 国防工业出版社, 2012.
	HU N Q. Theory and method of detecting weak characteristic signals in random resonance[M]. Beijing: National Defense Industry Press, 2012.
17	刘斌, 范翔宇, 张自伟, 等. 基于自适应尺度变换-双稳态随机共振模型的BPSK信号检测算法[J]. 系统工程与电子技术, 2022, 44 (7): 2084- 2095. doi: 10.12305/j.issn.1001-506X.2022.07.03
	LIU B, FAN X Y, ZHANG Z W, et al. Detection algorithm of BPSK signal based on adaptive scale change-bistable stochastic resonance model[J]. Systems Engineering and Electronics, 2022, 44 (7): 2084- 2095. doi: 10.12305/j.issn.1001-506X.2022.07.03
18	沈志翀, 马金全, 石丰源. 基于随机共振与深度残差网络的调制识别分析[J]. 信息工程大学学报, 2022, 23 (2): 155- 160. doi: 10.3969/j.issn.1671-0673.2022.02.005
	SHEN Z C, MA J Q, SHI F Y. Modulation recognition analysis based on stochastic resonance and deep residual network[J]. Journal of Information Engineering University, 2022, 23 (2): 155- 160. doi: 10.3969/j.issn.1671-0673.2022.02.005
19	李少旋, 何迪, 王巍, 等. 面向小型载荷的宽带通信信号随机共振检测方法[J]. 信号处理, 2024, 40 (4): 671- 681.
	LI S X, HE D, WANG W, et al. A stochastic resonance detection method for broadband communication signals in small loads[J]. Journal of Signal processing, 2024, 40 (4): 671- 681.
20	COLLINS J, CHOW C, IMHOFF T. Aperiodic stochastic resonance in excitable systems[J]. Physical Review. E,, 1995, 52 (4): 3321- 3324.
21	O’SHEA T J, WEST N E. Radio machine learning datasetgeneration with GNU radio[C]// Proc. of the 6th GNU Radio Conference, 2016.

参数	描述
信号样本长度	128
SNR范围/ dB	−20:2:18
样本数	220000
采样率/kHz	200

$a,b $参数组合	−8 ~ 0 dB平均准确率	0 dB以上平均准确率	全SNR平均准确率
（0.8,3.7）	70.4	92.7	63.6
（0.3,2.2）	69.9	92.1	63.1
（0.2,1）	70.7	92.9	63.7

模型	−8~ 0 dB 平均准确率	0 dB以上平均准确率	全SNR 平均准确率
LSTM	62.5	89.7	60.1
CGDNet	61.1	84.5	57.2
PET-CGDNN	63.3	90.2	60.7
文献[11]方法	65.0	84.4	58.1
DualSR-Net	70.7	92.9	63.7

输入信号	−8 ~ 0 dB 平均准确率	0 dB以上平均准确率	全SNR 平均准确率
DWT数据	68.7	90.7	62.3
AP数据	64.5	91.3	61.2
SR数据	70.7	92.9	63.7

模型	−8~0 dB 平均准确率	0 dB以上平均准确率	全SNR 平均准确率
移除IQ输入	69.6	92.1	63.0
移除SR输入	67.9	91.6	62.5
IQ,SR双输入	70.7	92.9	63.7

Modulation recognition method based on stochastic resonance and multi-scale features fusion

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 11

References 21

Related Articles 15

Recommended Articles

Metrics

Comments

[1]	Qiongdan HUANG, Lulu LIU, Jiejing HAN, Jiapeng WANG, Shilin KANG. Image super-resolution reconstruction based on differential feature back-projection fusion [J]. Systems Engineering and Electronics, 2026, 48(6): 1809-1818.
[2]	Yuanguang CHEN, Xiaokai LIU, Siyao XIAO, Shunsheng ZHANG, Hongyuan CUI, Xiaoying CHEN, Ying LIU. Radar intelligent target detection method using spatio-temporal feature fusion under low signal-to-noise ratio [J]. Systems Engineering and Electronics, 2026, 48(5): 1523-1531.
[3]	Hongyu TIAN, Songhu GE, Yu GUO, Zhongpu CUI, Xiao LIANG. Communication interference recognition method based on multi-feature fusion under low interference-to-noise ratio conditions [J]. Systems Engineering and Electronics, 2026, 48(3): 1061-1071.
[4]	Yao WANG, Huiqi XU, Silei CAO, Lei WANG. Detection algorithm of ship critical parts based on deep learning [J]. Systems Engineering and Electronics, 2026, 48(2): 410-421.
[5]	Hengyan LIU, Jun FANG, Qing LING, Wenjun YAN, Keyuan YU, Limin ZHANG. Emitter individual identification method based on 1D-2D-GRU-ResNet [J]. Systems Engineering and Electronics, 2026, 48(2): 727-735.
[6]	Weihong FU, Wenhong PENG, Naian LIU. SAR image small target detection method with hybrid attention optimization [J]. Systems Engineering and Electronics, 2025, 47(8): 2519-2526.
[7]	Dongping ZHOU, Hang RUAN, Minghui SHA, Chongyu WANG, Nianqiang CUI, Yaobing LU. Complex waveform modulation recognition based on feature fusion with Fast-CNN [J]. Systems Engineering and Electronics, 2025, 47(7): 2165-2175.
[8]	Wanying ZHANG, Youbing GAO, Zeyi LI, Pengfei LI, Wei ZHANG. Background signal suppression algorithm based on dual-path feature fusion net [J]. Systems Engineering and Electronics, 2025, 47(7): 2406-2413.
[9]	Jie JIANG, Qing LING, Wenjun YAN, Kai LIU. Multi-source ship image fusion detection method based on MFFDet-R [J]. Systems Engineering and Electronics, 2025, 47(2): 390-397.
[10]	Yong WANG, Boya ZHANG. Ship target detection method in SAR images based on feature fusion and location enhancement [J]. Systems Engineering and Electronics, 2025, 47(11): 3586-3597.
[11]	Juan WEI, Dehua HE, Fangli NING. Acoustic scene classification based on adaptive multi-branch convolution [J]. Systems Engineering and Electronics, 2025, 47(10): 3148-3154.
[12]	Zishuo HAN, Xiquan FAN, Qiang FU, Chuanyan MA, Dongdong ZHANG. Target detection based on multi-source information fusion from the perspective of drones [J]. Systems Engineering and Electronics, 2025, 47(1): 52-61.
[13]	Lei YU, Qiuyue DENG, Liying ZHENG, Haoyu WU. Second-order progressive feature fusion network for image super-resolution reconstruction [J]. Systems Engineering and Electronics, 2024, 46(2): 391-400.
[14]	Fengtao XUE, Tianyu SUN, Yimin YANG, Jian YANG. Rotated ship target detection algorithm in SAR images based on global feature fusion [J]. Systems Engineering and Electronics, 2024, 46(12): 4044-4053.
[15]	Jiayi LUO, Xuanpeng LI, Jianghao LI, Qifan XUE, Feng YANG, Weigong ZHANG. Radiation signal sorting method based on PDW multi-feature fusion [J]. Systems Engineering and Electronics, 2024, 46(1): 80-87.