Global Navigation Satellite Systems (GNSS) are vulnerable to both suppressive and spoofing interference in complex electromagnetic environments, while traditional identification methods exhibit limited performance in dynamic scenarios. To address this, a novel identification framework integrating deep feature enhancement with a lightweight classifier was proposed. First, mathematical models and a mixed sample set for seven typical interference types were systematically constructed. Then, a feature enhancement module based on a long short-term memory network with an Attention mechanism (LSTM-Attention) was proposed. This module adaptively learned dependencies from raw features, focused on key information, and generated more discriminative 20-dimensional deep features. Finally, a structurally simple multi-layer perceptron (MLP) was employed for efficient classification. Experimental results show that the proposed method achieves an accuracy of 96.1% and an F1-score of 96.0% on an independent test set, significantly outperforming various traditional machine learning and complex deep learning models. Its effectiveness and interpretability are further confirmed through confusion matrix analysis and feature importance evaluation. It demonstrates that, through deep feature enhancement, a classifier of moderate complexity can enhance computational efficiency while maintaining high accuracy, offering a feasible approach for the practical application of GNSS anti-jamming techniques.
WU Chuan-yu, JI Yuan-fa, SUN Xi-yan.
GNSS Interference Recognition Method Based on Time-frequency Feature Enhancement and Deep Learning[J].
Science Technology and Engineering, 2026, 26(28): 12253-12263 DOI:10.12404/j.issn.1671-1815.2600758
JinRuimin, GuoYi, YangHuiyun, et al. GNSS weak interference detection and recognition technology based on navigation receiver[J]. Global Positioning System, 2022, 47(6): 91-95.
XuYajun, GaoTianlu, HaoBoyang, et al. Adaptive GNSS interference blind detection method based on random matrix theory[J]. Science Technology and Engineering, 2025, 25(29): 12691-12698.
[6]
FangJ X T, YueJ, XuB, et al. A post-correlation graphical way for continuous GNSS spoofing detection[J]. Measurement, 2023, 216: 112974.
[7]
吉宁. GNSS欺骗信号检测方法研究[D]. 北京: 中国科学院大学, 2024.
[8]
JiNing. Research on GNSS spoofing signal detection methods[D]. Beijing: University of Chinese Academy of Sciences, 2024.
[9]
Van der MerweJ R, FrancoD C, FeiglT, et al. Optimal machine learning and signal processing synergies for low-resource GNSS interference classification[J]. IEEE Transactions on Aerospace and Electronic Systems, 2024, 60(3): 2705-2721.
[10]
RaghuvanshiA, BisnathS, BondJ. Analysis of GNSS radio frequency interference and impacts on GNSS receiver parameters[J]. GPS Solutions, 2025, 29(4): 196.
[11]
张通. 卫星导航系统压制干扰检测与识别技术研究[D]. 济南: 山东大学, 2023.
[12]
ZhangTong. Research on suppression jamming detection and recognition technologyfor satellite navigation systems[D]. Jinan: Shandong University, 2023.
[13]
WangY W, KouY H, ZhaoY, et al. Detection of synchronous spoofing on a GNSS receiver using weighted double ratio metrics[J]. GPS Solutions, 2022, 26(3): 91.
ZhuangXuebin, NiuBen, LinZijian, et al. Multi-parameter spoofing interference detection method based on gated parallel CNN-Transformer neural network[J]. Journal of Electronics & Information Technology, 2025, 47(6): 2005-2014.
[16]
ChenX, HeD, YanX Y, et al. GNSS interference type recognition with fingerprint spectrum DNN method[J]. IEEE Transactions on Aerospace and Electronic Systems, 2022, 58(5): 4745-4760.
WangXiaoyan, YangJingjing, HuangMing, et al. Research status and prospects of GNSS interference and spoofing detection[J]. Journal of Signal Processing, 2023, 39(12): 2131-2152.
[19]
ChenF Q, LiuZ, HuangL, et al. GNSS interference mitigation method based on deep learning[J]. Frontiers in Physics, 2025, 13: 1535906.
[20]
WangX Y, YangJ J, PengZ X, et al. Hilbert signal envelope-based multi-features methods for GNSS spoofing detection[J]. Computers & Security, 2024, 144: 103959.
[21]
ChenZ K, LiJ Z, LiJ, et al. GNSS multiparameter spoofing detection method based on support vector machine[J]. IEEE Sensors Journal, 2022, 22(18): 17864-17874.
[22]
IqbalA, AmanM N, SikdarB. A deep learning based induced GNSS spoof detection framework[J]. IEEE Transactions on Machine Learning in Communications and Networking, 2024, 2: 457-478.
[23]
FerreR M, De La FuenteA, LohanE S. Jammer classification in GNSS bands via machine learning algorithms[J]. Sensors, 2019, 19(22): 4841.
[24]
MohammadN, LiY C, AlK S, et al. Machine learning modeling of GPS features with applications to UAV location spoofing detection and classification[J]. Computers & Security, 2023, 126:103085.
XiLing, GuXuran, WangYi. Analysis of navigation deception signal characteristics in TEXBAT scenarios[J]. Global Positioning System, 2024, 49(6): 89-94.
[27]
ZhuX F, HuaT, YangF, et al. Global positioning system spoofing detection based on support vector machines[J]. IET Radar, Sonar & Navigation, 2022, 16(2): 224-237.
[28]
JiangY, ZhangR, SunB, et al. GNSS-IR soil moisture retrieval using multi-satellite data fusion based on random forest[J]. Remote Sensing, 2024, 16(18): 3428.
[29]
LiZ, LuT D, YuK G, et al. Interpolation of GNSS position time series using GBDT, XGBoost, and RF machine learning algorithms and models error analysis[J]. Remote Sensing, 2023, 15(18): 4374.
[30]
ZanjaniN M M, SedighyH S. Hybrid CNN architectures for detecting and classification of GNSS jamming attacks[J]. GPS Solutions, 2025, 29(3): 115.
XiangWenqiang, ShaoWei, LuoShaohui, et al. Simulation of soil moisture in permafrost region of the Qinghai-Tibet Plateau based on LSTM model[J]. Science Technology and Engineering, 2025, 25(31): 13236-13245.
YangRenzheng, HuangYanguo, HeXuan. Short-term wind power prediction based on SSA-BiLSTM and singular spectrum analysis[J]. Science Technology and Engineering, 2024, 24(22): 9392-9399.
[35]
LuC X, WangZ, WuZ L, et al. Global ocean wind speed retrieval from GNSS reflectometry using CNN-LSTM network[J]. IEEE Transactions on Geoscience and Remote Sensing, 2023, 61: 3276173.
[36]
SuZ G, ZhengG Q, WangG D, et al. An IDBO-optimized CNN-BiLSTM model for load forecasting in regional integrated energy systems[J]. Computers & Electrical Engineering, 2025, 123:110013.
[37]
NguyenL T, HockingD T. Penalty learning for optimal partitioning using multilayer perceptron[J]. Statistics and Computing, 2025, 35(5): 153.
[38]
WuC Y, JiY F, SunX Y. GNSS interference identification driven by eye pattern features: ICOA-CNN-ResNet-BiLSTM optimized deep learning architecture[J]. Entropy, 2025, 27(9): 938.