检索结果-内蒙古大学图书馆

Interpretable Deep Probabilistic Model for HRR Radar signal and its Application to Target Recognition

IEEE JOURNAL OF SELECTED TOPICS IN signal processing 2022年第4期16卷 775-790页

作者： Liao, Leiyao Du, Lan Chen, Jian Xidian Univ Natl Lab Radar Signal Proc Xian 710071 Peoples R China

With the advent of neural network, unprecedented advancements have been achieved in many tasks, including radar signal processing. However, a key disadvantage of the current methods is the black-box structure, which makes it hard to interpret or assess the hidden representations of data. In this paper, by combining the physical generative mechanism of the high range resolution (HRR) radar signal with neural network, we develop an interpretable deep probabilistic model to learn the latent features from HRR radar signals that can characterize the physical structure of targets. In detail, based on the radar target's scattering center model which describes the HRR radar signal as the summation of echoes from the scattering centers, a deep probabilistic model is constructed to depict the generative process from the scattering centers to observations, where the latent features comprise the locations and amplitudes of scattering centers. Considering that the locations of scattering centers are nearly invariable and the amplitudes of them are fluctuant for the signals within a small angular range, our model defines the shared locations and independent amplitudes of scattering centers for the signals in a small angular range, aiming to improve the robustness of interpretable feature extraction model. In addition, our model performs probabilistic inference on the posterior distribution of latent features with high preciseness. With the proposed model, we further design a recognition scheme based on the minimum reconstruction error criterion. Experiments on the measured HRR radar dataset validate the effectiveness of our model on learning interpretable features and superior recognition performance.

关键词： Radar Scattering Feature extraction Target recognition Radar scattering Probabilistic logic Neural networks Radar automatic target recognition (RATR) interpretability neural network variational inference minimum reconstruction error

来源：评论

学校读者我要写书评

暂无评论

Imaging Ultrasound Scattering targets using Density-Enhanced Chaotic Compressive Sampling

Imaging Ultrasound Scattering Targets using Density-Enhanced...

引用

Asia-Pacific-signal-and-Information-processing-Association Annual Summit and Conference (APSIPA ASC)

作者： Luong Thi Theu Tran Quang Huy Tran Thi Thuy Quynh Duc-Tan Tran Hoa Binh Univ Hanoi Vietnam Hanoi Pedag Univ 2 Fac Phys Hanoi Vietnam VNU Univ Engn & Technol Fac Elect & Telecommun Hanoi Vietnam Phenikaa Univ Fac Elect & Elect Engn Hanoi 12116 Vietnam

ISBN: (纸本)9798350300673

The ultrasound imaging method is a highly promising technique used in various fields. The utilization of ultrasound technique's backscattering could also allow humans to observe objects as small as the size of the incident wavelength. However, the employing backscattering approach requires high computational calculations and poses a significant obstacle to the production of equipment using the ultrasonic method. In this work, we utilized the pseudo-random compression sampling method in the extended DBIM model, which takes tissue density factor. This is necessary because tissue density provides quantitative information about soft tissue and serves as an image contrast source. This method combines pseudo-random measurement and compressed sensing data recovery technique. The simulation results have proved the effectiveness of the proposed CCS-DBIM method. In terms of imaging quality, at compression ratios as low as 0.5, the large difference in imaging quality is evident. After 5 iterations, the normalization error of the DBIM and CCS-DBIM methods was 0.8828 and 0.5281 respectively, i.e. a 40% reduction in normalization errors when the number of measurements was only half of the variables. The disadvantage of the proposed CCS-DBIM method is that the imaging time is significantly greater than that of the DBIM method. However, with today's parallel computing technology, large amounts of data and computational time will no longer be a big problem.

关键词： Ultrasonic imaging distorted Born iterative method pseudo-random scattered data Born approximation

来源：评论

学校读者我要写书评

暂无评论

Sea Surface small Target Detection using Tri-median Normalized Doppler Spectrum Feature 16

Sea Surface Small Target Detection using Tri-median Normaliz...

引用

16th International Conference on signal processing Systems, ICSPS 2024

作者： Guo, Zi-Xun Wu, Kang-Hui Bai, Xiao-Hui Su, Jia Fan, Yi-Fei Gong, Yan-Yun Wang, Ling Shui, Peng-Lang School of Electronics and Information Northwestern Polytechnical University Xi’an710072 China School of Information Xi’an University of Finance and Economics Shaanxi Xi’an710100 China The National Laboratory of Radar Signal Processing Xidian University Xi’an710071 China

ISBN: (纸本)9781510689251

This letter aims to develop a detector for detecting small targets on the sea surface based on feature utilization median normalization. At the long observation time, sea clutter and returns with target show differences of Doppler amplitude spectra (DAS). The median normalized DAS (MNDAS) is used to enhance the Doppler characteristics of returns with target, which is computed from the DAS of the cell under test and its neighboring reference cells. From the MNDAS, three salient features can be extracted for the detection, including the non-zero interval length, vector entropy and global accumulation in the MNDAS. The three features are combined into 3D feature vectors. Considering that the returns with target and their feature vectors cannot be used in the training, one semi-supervised classifier based on the convexhull learning algorithm is built by the feature vectors of sea clutter only. Finally, a new detector based on feature utilization median normalization which can control the false alarm rate precisely is constructed. Through the experiments on the IPIX and CSIR radar databases and one offshore experimental data using an unmanned aerial vehicle with a corner reflector, the proposed detector attains competitive performance and lower computation cost with the TF-tri-feature-based detector. © 2025 SPIE.

关键词： Vectors

来源：评论

学校读者我要写书评

暂无评论

Detection Framework of FDIA for Smart Grid Based on Mode Decomposition and Gradient Boosting Decision

引用

JOURNAL OF ELECTRICAL ENGINEERING & TECHNOLOGY 2025年 1-23页

作者： Zhang, Jing Zhou, Kun Wang, Lulu Yang, Yang Li, Yingna Kunming Univ Sci & Technol Fac Informat Engn & Automat Kunming 650500 Yunnan Peoples R China Kunming Univ Sci & Technol Yunnan Prov Key Lab Artificial Intelligence Kunming 650500 Yunnan Peoples R China Kunming Univ Sci & Technol Yunnan Prov Key Lab Comp Technol Applicat Kunming 650500 Yunnan Peoples R China

The escalating frequency of cyberattacks poses a significant threat to the security of Cyber-Physical Systems. Recent studies have revealed that a specific type of cyberattack, known as false data injection attacks(FDIA), can easily breach the defense mechanisms of energy systems. As attack detection technology improves, attackers must prudently choose their targets and distribute discreetly small-scale resources to minimize the risk of detection. Without access to eliminate the strong coupling relationship between buses within single time domain, we propose a FDIA detection framework that can detect independent buses, which presents the characteristics of attack under the multi-mode perspective. The framework employs Variational Mode Decomposition and Fast Independent Component Analysis to extract the distinctive features of FDIA signals across various frequencies. Additionally, the framework utilizes the results obtained from Particle Swarm Optimization to replace the predetermined thresholds of Extreme Gradient Boosting on an individual bus, thereby augmenting both the detection accuracy and interpretability of the model. Simulation results of the IEEE-14 bus system demonstrate the efficient detection of attacks on individual buses by the proposed FDIA detection framework. Furthermore, the study evaluates the impact of attack intensity on the framework's performance in the presence of specific noise interference, thus confirming the method's high effectiveness and robustness.

关键词： Cyber-physical system security signal processing False data injection attacks Smart grid Machine learning

来源：评论

学校读者我要写书评

暂无评论

Transcriptome analysis and functional identification of transfer RNA-derived fragments in grape leaves exposed to UV-C radiation

引用

PLANT PHYSIOLOGY AND BIOCHEMISTRY 2025年 219卷 109425页

作者： Li, Yang Kong, Lingchao Mu, Huayuan Wang, Jiayu Li, Furui Kuang, Yangfu Duan, Wei Fan, Peige Yuan, Ling Liang, Zhenchang Wang, Lijun Chinese Acad Sci Inst Bot Beijing Key Lab Grape Sci & Enol Beijing 100093 Peoples R China Chinese Acad Sci Inst Bot State Key Lab Plant Divers & Specilaty Crops Beijing 100093 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China Chinese Natl Bot Garden Beijing 100093 Peoples R China Univ Kentucky Kentucky Tobacco Res & Dev Ctr Dept Plant & Soil Sci Lexington KY 40546 USA

Transfer RNA-derived fragments (tRFs) are noncoding small RNAs derived from transfer RNAs (tRNAs) in microorganisms, animals and plants. In plants, tRFs are known to respond to environmental stimuli, including heat, oxidative stress and UV radiation;however, their specific functions in horticultural plants, such as grapevine, remain poorly understood. In this study, we used RNA-seq to identify differentially expressed genes (DEGs) in grape leaves exposed to UV-C radiation. A total of 1329 and 8055 of genes were differentially expression after 1 and 6 h of UV-C treatment, respectively. We identified a large number of secondary metabolism-related genes in the DEGs, including genes involved in stilbene and flavonoid biosynthesis. Noticeably, the stilbene biosynthesisrelated gene was induced earlier than the other genes in the phenylalanine metabolic pathway. We also conducted small RNA-seq and identified differentially expressed (DE) miRNAs and their targets. To explore whether the tRFs involved in UV-C response, further analysis of the small RNA-seq data revealed 23 down-regulated and 41 up-regulated DE tRFs. Gene ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) showed that the target genes of these tRFs are involved in multiple biological processing, including hormone signal transduction and metabolite synthesis. To validate the function of tRFs, tRF39 and tRF45 were selected and overexpressed in tobacco leaves, and the expression levels of their target genes were inhibited. Our study suggests that the tRFs may regulate multiple biological processes in response to UV-C exposure in grapevine. Our findings provide a foundation for further elucidating the regulatory mechanisms of tRFs in horticultural crops.

关键词： small RNA tRNA fragments UV-C radiation Phenylalanine metabolic pathway Grapevine

来源：评论

学校读者我要写书评

暂无评论

Learning adaptive detection and tracking collaborations with augmented UAV synthesis for accurate anti-UAV system

引用

EXPERT SYSTEMS WITH APPLICATIONS 2025年 282卷

作者： Liu, Shihan Xu, Tianyang Zhu, Xue-Feng Wu, Xiao-Jun Kittler, Josef Jiangnan Univ Sch Artificial Intelligence & Comp Sci Wuxi Peoples R China Univ Surrey Ctr Vis Speech & Signal Proc CVSSP Guildford GU2 7XH England

In recent years, Unmanned Aerial Vehicles (UAVs) have witnessed a significant use upsurge across various domains. However, their low cost and elusive size have raised significant security concerns. In particular, UAVs, imaged in the infrared mode, located in a cluttered background and being relatively small targets, pose formidable challenges. To this end, in this paper, we propose a novel approach for accurate UAVs perception. The core innovation lies in learning an adaptive detection and tracking collaboration mechanism, supported by a novel method of training data augmentation (ADTC). During the test phase, ADTC begins by leveraging the detector to identify the potential target candidates within the image frame. These candidates are then refined by an adaptive selection module, where a Kalman filter is deployed to model and predict the motion trajectory of each candidate. The best result of the predicted trajectories with the detected candidates is adopted as the output. The adaptive selection module filters out less confident objects, efficiently decreasing processing time. Furthermore, we construct a new dataset Anti-MUAV15 to evaluate the performance of ADTC in multipleUAV scenarios. Our approach has been rigorously evaluated through qualitative and quantitative experiments on the Anti-UAV, AntiUAV600 and Anti-MUAV15 datasets. The experimental results demonstrate that our method outperforms state-of-the-art anti-UAV solutions in terms of robustness and precision, without imposing additional computational burden. The code and dataset are available at https://***/Shihan0325/AntiMUAV15.

关键词： Anti-UAV system Object detection Visual tracking data augmentation

来源：评论

学校读者我要写书评

暂无评论

A Convolutional Neural Network for Ultrasound Plane Wave Image Segmentation With a small Amount of Phase Array Channel data

引用

IEEE TRANSACTIONS ON ULTRASONICS FERROELECTRICS AND FREQUENCY CONTROL 2022年第7期69卷 2270-2281页

作者： Zhang, Fuben Luo, Lin Zhang, Yu Gao, Xiaorong Li, Jinlong Southwest Jiaotong Univ Dept Sch Phys Sci & Technol Chengdu 610031 Peoples R China

Single-angle plane wave has a huge potential in ultrasound high frame rate imaging, which, however, has a number of difficulties, such as low imaging quality and poor segmentation results. To overcome these difficulties, an end-to-end convolutional neural network (CNN) structure from single-angle channel data was proposed to segment images in this article. The network removed the traditional beamforming process and used raw radio frequency (RF) data as input to directly obtain segmented image. The signal features at each depth were extracted and concatenated to obtain the feature map by a special depth signal extraction module, and the feature map was then put into the residual encoder and decoder to obtain the output. A simulated hypoechoic cysts dataset of 2000 and an actual industrial defect dataset of 900 were used for training separately. Good results have been achieved in both simulated medical cysts segmentation and actual industrial defects segmentation. Experiments were conducted on both datasets with phase array sparse element data as input, and segmentation results were obtained for both. On the whole, this work achieved better quality segmented images with shorter processing time from single-angle plane wave channel data using CNNs;compared with other methods, our network has been greatly improved in intersection over union (IOU), F1 score, and processing time. Also, it indicated that the feasibility of applying deep learning in image segmentation can be improved using phase array sparse element data as input.

关键词： Image segmentation Imaging Ultrasonic imaging Feature extraction Array signal processing Radio frequency Acoustics Beamforming convolutional neural network (CNN) phase array sparse element data segmentation signal features single-angle plane wave

来源：评论

学校读者我要写书评

暂无评论

Improvement of small Target Detection Algorithm Based on SSD

Improvement of Small Target Detection Algorithm Based on SSD

引用

signal processing and Intelligent Computing (SPIC), International Conference on

作者： Yuzhi Li Fang Li Xiaolin Zhou Xiangyang Yin Shuhui Li Jinchi Dai Ce Zhang Shenyang Ligong University Shenyang China Emergency Management Bureau Rizhao China North China Electric Power University Beijing China

ISBN: (数字)9798350368888

ISBN: (纸本)9798350368895

To address the issues of imbalanced target distribution within the dataset and the deficiency of high-level semantic information in the lower-level feature maps for small target detection, this paper proposes a small target detection algorithm grounded in feature fusion. The algorithm builds upon the SSD framework. To enhance the detection background for small targets, a data augmentation technique is employed, bolstering the model's generalization capacity for small and medium-sized targets. To augment the semantic information in the lower-level feature maps, a feature fusion module is incorporated, injecting high-level semantic data into the low-level feature map. Comparative experiments conducted on the dataset demonstrate the algorithm's effectiveness, showing improved overall detection performance and enhanced accuracy for small and medium-sized targets.

关键词： Accuracy Target recognition Computational modeling Semantics signal processing algorithms Object detection signal processing Feature extraction data augmentation data models

来源：评论

学校读者我要写书评

暂无评论

Remote sensing aircraft small object detection algorithm based on YOLOv5

Remote sensing aircraft small object detection algorithm bas...

引用

2024 International Conference on Image, signal processing, and Pattern Recognition, ISPP 2024

作者： Qiu, Yijuan Xue, Jiefeng Zhang, Jie Jiang, Ping Zhang, Gang Lei, Tao National Key Laboratory of Optical Field Manipulation Science and Technology Chinese Academy of Sciences Sichuan Chengdu610209 China Institute of Optics and Electronics Chinese Academy of Sciences Sichuan Chengdu610209 China University of Chinese Academy of Sciences Beijing100049 China Southwest University of Science and Technology 621010 China

ISBN: (纸本)9781510680425

With the rapid development of remote sensing technology, remote sensing images play an important role in the agricultural field, geological field, and natural disaster detection. The size of aircraft in complex scenes in remote sensing images is extremely small, and aircraft of different models have similar shapes. Therefore, improving the accuracy of aircraft target recognition is a challenging task. We propose an improved aircraft small target recognition method based on yolov5, which can improve the recognition accuracy of aircraft targets while ensuring the speed of the model. The specific content is as follows: To address the problem of lack of remote sensing aircraft training sets, we use existing public remote sensing images to combine with aircraft model images. Most of the aircraft models only occupy a dozen to twenty pixels in the 1k*1k image, and perform Scale the generated data set;in order to better combine features of different scales and obtain higher-level feature fusion, introduce the BiFPN module with more residual connections and more complete feature fusion;use the SE attention mechanism to learn the weights of different features, extract information that is more important for detection and improve model performance;in view of the small size of the aircraft, a detection method based on Wasserstein distance such as NWD (Normalized Wasserstein Distance) is selected as the loss function. © 2024 SPIE.

关键词： Training aircraft

来源：评论

学校读者我要写书评

暂无评论

Research on the Enhancement Method of small Moving targets with Low signal-to-Noise Ratio

Research on the Enhancement Method of Small Moving Targets w...

引用

Conference on AOPC - Optical Sensing, Imaging, and Display Technology

作者： Li, Kun Piao, Yupeng Qian, Weixian Nanjing Univ Sci & Technol Sch Elect & Opt Engn Nanjing 210094 Jiangsu Peoples R China Shanghai Aerosp Control Technol Inst 1555 Zhongchun Rd Shanghai 201109 Peoples R China

ISBN: (纸本)9781510661905;9781510661912

small moving targets with low signal-to-noise ratio have the characteristics of weak intensity and small size. For stationary targets, it can be enhanced by the time-domain multi-frame accumulation algorithm. However, for small moving targets, the traditional direct multi-frame accumulation method cannot effectively enhance the target due to the change of the position of the target between frames and the spread of target energy. Based on this feature, this paper proposes an enhancement method based on uniform moving small targets. Because the target moves at a uniform speed between frames, the target smear image can be obtained by directly accumulating multiple frames of the collected target image sequence according to the stationary target, and then according to the smear information, the real moving speed of the target can be reversed. Finally, according to this speed, the small target image sequence is shifted and accumulated by multiple frames. In order to verify the effectiveness of the proposed method, the experiment is designed to simulate the motion of a small target by carrying a faint point light source on a motorised slide at constant speed, collecting data for correlation processing. The experimental results show that the method proposed in this paper can quickly and accurately estimate the speed of the small target moving between frames. The accumulation of small target images shifted according to this speed can significantly enhance the target and improve the signal-to-noise ratio.

关键词： Time domain multi-frame accumulation low signal-to-noise ratio target trailing detection target enhancement

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：