| 207 | 0 | 72 |
| Downloads | Citas | Reads |
To address the chanllenges of nonlinear and non-stationary echo signal analysis of low-slow-small(LSS)targets in radar signal processing, a hybrid time-frequency analysis approach was proposed by constructing a combined model based on empirical mode decomposition(EMD) and principal component analysis(PCA). The proposed model compensated for the shortcomings of traditional methods in terms of computational redundancy and loss of local features. First, the EMD method was applied to adaptively decompose the original radar echo signal into a series of intrinsic mode function(IMF)components, accurately capturing the local timefrequency characteristics. Second, the PCA method was employed to reduce the dimensionality of the energy spectra of the IMF components to extract the principal features, effectively reducing data redundancy, and preserving key information. Finally, an experimental verification was conducted using the LSS target dataset published in the Journal of Radars. The results demonstrate that the proposed EMD-PCA method achieves mean values of 0.061 9 pixels for the root mean square error(RMSE),19.1185 dB for the peak signal to noise ratio(PSNR), and 0.8482 for the structural similarity index(SSIM), corresponding to 38.65% reduction in RMSE and improvement of 14.54%, and 22.29% in PSNR and SSIM, respectively, compared to the standalone EMD model. The results indicate that the proposed method can significantly improve the accuracy and reliability of feature extraction from complex radar signals, providing a technical reference for the accurate detection and analysis of LSS targets.
[1]于淼，张耀鲁，徐泽辰，等．基于MEEMD-HHT的分布式光纤振动传感系统信号特征提取方法[J]．红外与激光工程，2021,50(7):207-218.YU M, ZHANG Y L, XU Z C, et al. Signal feature extraction method based on MEEMD-HHT for distributed optical fiber vibration sensing system[J].Infrared and Laser Engineering,2021,50(7):207-218.
[2] FARHAN M A A, SONI K, THELEGTHOTI M K, et al. Islanding detection using empirical mode decomposition and artificial neural network for inverter interfaced distributed generation[J].Journal of the Institution of Engineers(India):Series B,2025,106(1):15-30.
[3]谢跃雷，刘信，梁文斌．基于权重不可知神经网络的旋翼无人机检测[J]．电讯技术，2022,62(1):46-53.XIE Y L, LIU X, LIANG W B. Micro-motion feature detection of rotary-wing UAV based on weight agnostic neural network[J]. Telecommunication Engineering,2022,62(1):46-53.
[4]宿利平，严志豪，王辉，等．基于EEMD-HHT的隧道爆破振动信号分析[J]．施工技术（中英文），2023,52(12):21-26.SU L P,YAN Z H,WANG H,et al.Blasting vibration signal analysis of tunnel based on EEMDHHT[J].Construction Technology,2023,52(12):21-26.
[5]陈小龙，袁旺，杜晓林，等．多波段FMCW雷达低慢小探测数据集（LSS-FMCWR-1.0）及高分辨微动特征提取方法[J]．雷达学报，2024,13(3):539-553.CHEN X L,YUAN W,DU X L,et al.Multiband FMCW radar LSS-target detection dataset(LSS-FMCWR-1.0)and high-resolution micromotion feature extraction method[J]. Journal of Radars,2024,13(3):539-553.
[6]单宝琛，陈晔，郑宾，等．基于HHT的激光超声缺陷检测分析[J]．应用激光，2020,40(4):745-750.SHAN B C,CHEN Y,ZHENG B,et al.Laser ultrasonic flaw detection analysis based on HHT[J].Applied Laser,2020,40(4):745-750.
[7] DU Z H,ZHU T F,LIN M L,et al.A novel mutation in human EMD gene and mitochondrial dysfunction in emerin knockdown cardiomyocytes[J]. Journal of Cellular and Molecular Medicine,2022,26(19):5054-5066.
[8] MA C X,HUANG X T,WANG K,et al.Prediction of remaining parking spaces based on EMDLSTM-BiLSTM neural network[J].Journal of Traffic and Transportation Engineering(English Edition),2025,12(1):201-213.
[9] DELANEY P G, EISNER Z J, THULLAH A H, et al. Evaluating feasibility of a novel mobile emergency medical dispatch tool for lay first responder prehospital response coordination in Sierra Leone:a simulation-based study[J]. Injury, 2023,54(1):5-14.
[10] SUN R,CAO H,FU Y,et al.Development of IMBs-qPCR method for detection of foodborne Salmonella[J].International Food Research Journal,2023,30(4):978-991.
[11]李茂，杨录，张艳花．基于EMD及主成分分析的缺陷超声信号特征提取研究[J]．中国测试，2018,44(2):118-121,133.LI M, YANG L, ZHANG Y H. Research on feature extraction of ultrasonic flaw signal based on EMD and principal component analysis[J]. China Measurement&Test, 2018, 44(2):118-121,133.
[12]张银波，李思宁，姜鹏，等．PCA特征提取和弹性BP神经网络的水下气泡识别[J]．红外与激光工程，2021,50(6):209-215.ZHANG Y B,LI S N,JIANG P,et al.Underwater bubble recognition based on PCA feature extraction and elastic BP neural network[J]. Infrared and Laser Engineering,2021,50(6):209-215.
[13]TEIXEIRA V S, LABITZKY V, SCHUMACHER U, et al. Use of electrical impedance spectroscopy to distinguish cancer from normal tissues with a four electrode terminal setup[J]. Current Directions in Biomedical Engineering,2020,6(3):341-344.
[14] NGUYEN G H,HUA Y T H,NGUYEN L C,et al. Image enhancement using bidimensional empirical mode decomposition and morphological operations for brain tumor detection and classification[J]. Asian Pacific Journal of Cancer Prevention,2024,25(9):3327-3336.
[15]何炜琨，孙景波，王晓亮，等．基于RSP-CFD方法的小型旋翼无人机微动特征提取[J]．信号处理，2021,37(3):399-408.HE W K,SUN J B,WANG X L,et al.Micromotion feature extraction of micro-rotor UAV based on RSP-CFD method[J]. Journal of Signal Processing,2021,37(3):399-408.
[16]YE X Y, MA X D, PAN Z Y, et al. Denoising complex-valued diffusion MR images using a two-step,nonlocal principal component analysis approach[J].Magnetic Resonance in Medicine,2025,93(6):2473-2487.
[17]章鹏飞，李刚，霍超颖，等．基于双雷达微动特征融合的无人机分类识别[J]．雷达学报，2018,7(5):557-564.ZHANG P F,LI G,HUO C Y,et al.Classification of drones based on micro-doppler radar signatures using dual radar sensors[J].Journal of Radars,2018,7(5):557-564.
[18]韩晓伟，田晓蓓．基于HHT及主成分分析的光缆识别信号特征提取[J]．河北工业科技，2022,39(5):381-387.HAN X W,TIAN X B.Feature extraction method of optical cable identification based on HHT and PCA[J]. Hebei Journal of Industrial Science and Technology,2022,39(5):381-387.
[19]XIE S J,LIN H,MA T X,et al.Prediction of joint roughness coefficient via hybrid machine learning model combined with principal components analysis[J]. Journal of Rock Mechanics and Geotechnical Engineering,2025,17(4):2291-2306.
[20]肖璞，殷一鸣．一种基于PCA降维的SIFT算法[J]．现代计算机，2020(34):15-18,43.XIAO P,YIN Y M.A dimension reduction SIFT algorithm based on PCA[J]. Modern Computer,2020(34):15-18,43.
[21] PATHAK S S, MANE S J, VESMAWALA G R, et al. Prediction of compressive strength of concrete using multilayer perception network, generalized feedforward network, principal component analysis network, time lagged recurrent network,recurrent network[J]. Asian Journal of Civil Engineering,2025,26(1):431-450.
[22]张朝伟，夏赛强，杨军，等．低信噪比条件下直升机微动特征提取方法[J]．雷达科学与技术，2021,19(6):689-696.ZHANG C W, XIA S Q, YANG J, et al. An extraction method for helicopters micro-motion features under low SNR[J]. Radar Science and Technology,2021,19(6):689-696.
[23]LIU X L,SU M M,ZHANG J L,et al.Analysis of multiple physical fields and the study of optimal design method for PCA[J].Journal of Computational Methods in Sciences and Engineering,2024,24(6):3504-3516.
[24] ZHANG X Q,CHEN H Y,WEN Y H,et al.A new water level prediction model based on ESMD-VMD-WSD-ESN[J]. Stochastic Environmental Research and Risk Assessment, 2023, 37(8):3221-3241.
[25]TAVISHA S,SEEMA B,PRIYANKA G,et al.Assessment of terminal heat stress tolerance in doubled haploids derived from synthetic hexaploid wheat(Triticum aestivum L)using genetic variability and PCA-based cluster analyses[J]. Journal of Experimental Agriculture International,2024,46(11):333-352.
Basic Information:
DOI：10.20189/j.cnki.CN/61-1527/E.202503005
China Classification Code:TN957.51
Citation Information:
[1]YU Ye,MAO Xinqian,JIN Guodong ,et al.EMD-PCA Combination-Based Micromotion Feature Extraction Method of Low-Slow-Small Targets[J].Journal of Rocket Force University of Engineering,2025,39(03):45-53.DOI:10.20189/j.cnki.CN/61-1527/E.202503005.
Fund Information:
国家自然科学基金（12403080）; 国家资助博士后研究人员计划（GZC20233565）; 中国博士后科学基金面上项目（2024M764304）; 陕西省自然科学基础研究计划（2023-JC-QN-0027）
2025-06-16
2025-06-16
2025-06-16