虚警率约束下基于噪声分数池阈值标定机制的DSSS信号智能检测

张韬; 唐小妹; 孙广富

doi:10.11999/JEIT260414

虚警率约束下基于噪声分数池阈值标定机制的DSSS信号智能检测

doi: 10.11999/JEIT260414 cstr: 32379.14.JEIT260414

1.
国防科技大学电子科学学院长沙 410073
2.
导航与时空技术国家级重点实验室长沙 410073

基金项目: 国家自然科学基金重点项目(62531025)

详细信息

作者简介:
张韬：女，博士生，研究方向为卫星导航信号智能接收，邮箱为　17810228973@163.com

唐小妹：女，研究员，研究方向为导航信号体制设计、导航安全对抗等，邮箱为　txm_nnc@126.com

孙广富：男，研究员，研究方向为卫星导航技术等

通讯作者:
唐小妹　txm_nnc@126.com

中图分类号: TN965.5
计量
- 文章访问数: 51
- HTML全文浏览量: 25
- PDF下载量: 0
- 被引次数: 0
出版历程
- 收稿日期: 2026-04-08
- 修回日期: 2026-07-28
- 录用日期: 2026-07-28
- 网络出版日期: 2026-08-07

Intelligent Detection of DSSS Signals Under False-Alarm Rate Constraints Based on a Noise Score-Pool Threshold Calibration Mechanism

1.
College of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, China National Key Laboratory for Positioning, Navigation and Timing Technology, Changsha 410073, China
2.
National Key Laboratory for Positioning, Navigation and Timing Technology, Changsha 410073, China

Funds: Supported by the National Natural Science Foundation of China (62531025)

摘要

摘要: 针对弱信号场景下导航直扩信号传统检测方法性能受限，以及现有深度学习检测模型普遍缺乏有效虚警率控制机制的问题，该文提出了一种虚警率可控的直扩信号深度学习检测方法。该方法创新性地提出了基于噪声分数池的检测阈值自适应标定机制，同时设计了适配I/Q信号一维序列输入的改进的残差神经网络。通过统计噪声数据集经网络处理后输出的置信度分数的经验分布，根据预设虚警率来标定检测判决阈值，从而将深度学习模型纳入经典的恒虚警率评估框架。此外，该文验证了有无归一化处理的数据预处理策略对弱信号检测的影响。仿真结果表明，该文所提模型整体检测性能较传统自相关方法提升3～4 dB，无归一化处理策略相较于归一化处理性能提升约1 dB。在非理想的高斯色噪声环境下，该模型同样展现出优于传统方法的检测性能与稳健的泛化能力。
- 信号检测 /
- 直接序列扩频 /
- 深度学习 /
- 虚警率 /
- 阈值标定
Abstract: Objective To address the performance degradation of GNSS signal detection in weak-signal environments and the lack of false alarm rate (FAR) control in existing deep learning models, this study investigates a detection method under a constant false alarm rate (CFAR) constraint to enhance receiver reliability and practicality. Methods This study models the detection of direct sequence spread spectrum signals as a binary classification problem and proposes a comprehensive DL-based detection framework. The methodology is centered on three core innovations. First, an adaptive one-dimensional residual neural network (1D-ResNet-18) is designed to suit the characteristics of I/Q sampled time-series data. Key modifications include adjusting the input convolution kernels to 1×3 and removing the initial maximum pooling layer to prevent the loss of fine-grained features inherent in weak signals. Second, a "noise score pool threshold calibration" mechanism is introduced. By inputting a large volume of pure noise samples into the trained network, an empirical distribution of confidence scores for the "signal present" category is constructed. Decision thresholds are then dynamically determined based on the quantiles corresponding to preset FAR levels. Third, an unnormalized data preprocessing strategy is adopted, as it is demonstrated that preserving the original signal amplitude information is beneficial for network learning under low signal-to-noise ratio (SNR) conditions. The model's performance was rigorously validated using a simulated GPS L1 C/A signal dataset under various SNRs, FAR settings, and non-ideal colored noise environments. Results and Discussions Experimental results demonstrate significant performance gains achieved by the proposed method. At a FAR of 0.01, the detection probability approaches 100% at an SNR of –8 dB, marking a substantial improvement over traditional techniques. A systematic comparison of different FAR settings (0.0001, 0.001, and 0.01) indicates that while the detection probability curve predictably shifts as the FAR decreases, overall performance remains consistently high. Furthermore, the unnormalized data preprocessing strategy consistently outperformed the normalized strategy, introducing a performance gain of approximately 1 dB in the low SNR range. Compared with traditional autocorrelation detection methods, the deep learning model exhibits a significant overall detection performance improvement of 3 to 4 dB across various false alarm rates. Notably, the method also displayed robust generalization in untrained, non-ideal colored noise environments. Conclusions The proposed method effectively bridges data-driven deep learning with classical detection theory, resolving the lack of FAR control in neural networks. By balancing high sensitivity with precise false alarm management, this work provides a practical and robust framework for navigation signal processing in complex environments.
- Signal detection /
- Direct sequence spread spectrum /
- Deep learning /
- False alarm rate /
- Threshold calibration

HTML全文

图 1 DSSS信号生成框架图

下载: 全尺寸图片幻灯片

图 2 本文模型检测流程图

下载: 全尺寸图片幻灯片

图 3 改进的ResNet-18网络结构图

下载: 全尺寸图片幻灯片

图 4 残差块结构图

下载: 全尺寸图片幻灯片

图 5 模型训练曲线

下载: 全尺寸图片幻灯片

图 6 不同虚警率下的检测性能

下载: 全尺寸图片幻灯片

图 7 不同虚警率下模型分类性能

下载: 全尺寸图片幻灯片

图 8 有无归一化处理的检测性能对比

下载: 全尺寸图片幻灯片

图 9 本文模型与传统方法的检测性能对比

下载: 全尺寸图片幻灯片

图 10 不同色噪程度下本文模型的检测性能

下载: 全尺寸图片幻灯片

图 11 不同色噪程度下本文模型与传统方法检测性能对比

下载: 全尺寸图片幻灯片

表 1 N网络层输出维度

网络层名称	输出特征维度	网络层名称	输出特征维度
Input	2×2048	Layer3-Block2	256×256
Conv1	64×1024	Layer4-Block1	512×128
Layer1-Block1	64×1024	Layer4-Block2	512×128
Layer1-Block2	64×1024	Avgpool	512×1
Layer2-Block1	128×512	FC	512×1
Layer2-Block2	128×512	Softmax	1×2
Layer3-Block1	256×256	Output	1×2

下载: 导出CSV

表 2 训练参数

参数	值
Initial Learning Rate	0.0001
Max Epochs	50
Mini Batch Size	64
Freeze BN	True
Dropout	0.3
Optimizer	AdamW

下载: 导出CSV

表 3 模型结构参数消融实验结果

模型设置	$ {P}_{\mathrm{d}} $(-12 dB)	$ {P}_{\mathrm{d}} $(-11 dB)	$ {P}_{\mathrm{d}} $(-10 dB)	$ {P}_{\mathrm{d}} $(-9 dB)	$ {P}_{\mathrm{d}} $(-8 dB)	达到$ {P}_{\mathrm{d}} $=1所需SNR (dB)
本文模型	30.67%	45.33%	73.33%	89.33%	100%	-8
消融模型1	25.33%	38.00%	67.33%	84.00%	97.33%	-7
消融模型2	23.33%	41.33%	62.00%	86.67%	99.33%	-7

下载: 导出CSV

参考文献(19)

[1]	HALDER N and MURTHY C R. Channel estimation and data detection in DS-spread channels: A unified framework, novel algorithms, and waveform comparison[J]. IEEE Transactions on Signal Processing, 2025, 73: 4108–4123. doi: 10.1109/TSP.2025.3608021.
[2]	DENG Zhongliang, JIA Buyun, TANG Shihao, et al. Fine frequency acquisition scheme in weak signal environment for a communication and navigation fusion system[J]. Electronics, 2019, 8(8): 829. doi: 10.3390/electronics8080829.
[3]	GUO Wenfei, NIU Xiaoji, GUO Chi, et al. A new FFT acquisition scheme based on partial matched filter in GNSS receivers for harsh environments[J]. Aerospace Science and Technology, 2017, 61: 66–72. doi: 10.1016/j.ast.2016.11.017.
[4]	BORIO D and LACHAPELLE G. A non-coherent architecture for GNSS digital tracking loops[J]. Annals of Telecommunications, 2009, 64(9/10): 601–614. doi: 10.1007/s12243-009-0114-1.
[5]	LIN Mengying, LUO Yimei, ZHU Xuefen, et al. Optimal GPS acquisition algorithm in severe ionospheric scintillation scene[J]. Electronics, 2023, 12(6): 1343. doi: 10.3390/electronics12061343.
[6]	WU Chao, XU Luping, ZHANG Hua, et al. An improved acquisition method for GNSS in high dynamic environments: Differential acquisition based on compressed sensing theory[J]. Navigation, 2017, 64(1): 23–34. doi: 10.1002/navi.173.
[7]	朱政宇, 殷梦琳, 姚信威, 等. AI赋能的通感算一体化关键技术研究综述[J]. 电子与信息学报, 2025, 47(10): 3426–3438. doi: 10.11999/JEIT250242. ZHU Zhengyu, YIN Menglin, YAO Xinwei, et al. Overview of the research on key technologies for AI-powered integrated sensing, communication and computing[J]. Journal of Electronics & Information Technology, 2025, 47(10): 3426–3438. doi: 10.11999/JEIT250242.
[8]	李云, 杨松林, 邢智童, 等. 多尺度特征注意力网络下的卫星信号识别研究[J]. 电子与信息学报, 2025, 47(6): 1792–1802. doi: 10.11999/JEIT250126. LI Yun, YANG Songlin, XING Zhitong, et al. Study on satellite signal recognition with multi-scale feature attention network[J]. Journal of Electronics & Information Technology, 2025, 47(6): 1792–1802. doi: 10.11999/JEIT250126.
[9]	樊盛华, 尹航, 刘俭, 等. 融合双分支优化SAM与全局-局部协同匹配的单样本目标检测方法[J]. 电子与信息学报, 2025, 47(12): 4665–4676. doi: 10.11999/JEIT250982. FAN Shenghua, YIN Hang, LIU Jian, et al. A one-shot object detection method fusing dual-branch optimized SAM and global-local collaborative matching[J]. Journal of Electronics & Information Technology, 2025, 47(12): 4665–4676. doi: 10.11999/JEIT250982.
[10]	WEI Fei, ZHENG Shilian, ZHOU Xiaoyu, et al. Detection of direct sequence spread spectrum signals based on deep learning[J]. IEEE Transactions on Cognitive Communications and Networking, 2022, 8(3): 1399–1410. doi: 10.1109/TCCN.2022.3174609.
[11]	BORHANI-DARIAN P, LI Haoqing, WU Peng, et al. Deep learning of GNSS acquisition[J]. Sensors, 2023, 23(3): 1566. doi: 10.3390/s23031566.
[12]	MORADI N, NEZHADSHAHBODAGHI M, and MOSAVI M R. GPS signal acquisition based on deep convolutional neural network and post-correlation methods[J]. GPS Solutions, 2023, 27(3): 132. doi: 10.1007/s10291-023-01469-7.
[13]	GU Hanqing, LIU Xiaxia, XU Lu, et al. DSSS signal detection based on CNN[J]. Sensors, 2023, 23(15): 6691. doi: 10.3390/s23156691.
[14]	ZHANG Shuang, LIU Feng, HUANG Yuang, et al. Adaptive detection of direct-sequence spread-spectrum signals based on knowledge-enhanced compressive measurements and artificial neural networks[J]. Sensors, 2021, 21(7): 2538. doi: 10.3390/s21072538.
[15]	DUAN Lei, LI Chuanjun, and ZHANG Qingpu. Optimizing the computational effort of satellite signal acquisition based on mean recognition convolutional neural network[J]. Journal of Physics: Conference Series, 2023, 2493(1): 012001. doi: 10.1088/1742-6596/2493/1/012001.
[16]	QIU Ye, MA Xinjie, LI Xinglong, et al. An end-to-end approach for enhanced weak signal detection in time–frequency analysis[J]. IEEE Transactions on Aerospace and Electronic Systems, 2025, 61(6): 19383–19398. doi: 10.1109/TAES.2025.3618514.
[17]	LIU Yang, LIU Peng, SHI Yu, et al. Deep learning-enhanced signal detection for communication systems[J]. PLoS One, 2025, 20(5): e0324916. doi: 10.1371/journal.pone.0324916.
[18]	WANG Bo, SHEN Lei, WANG Huaxia, et al. Direct sequence spread spectrum (DSSS) signal detection based on eigenvalues local binary pattern residual network (EL-ResNet)[J]. Signal, Image and Video Processing, 2024, 18(5): 4741–4751. doi: 10.1007/s11760-024-03110-7.
[19]	ZHANG Mingzhen. Communication signal detection technology based on residual neural network and DenseNet[J]. Discover Applied Sciences, 2025, 7(10): 1058. doi: 10.1007/s42452-025-07676-w.