检索结果-南通市图书馆

Drone-YOLOv7: small target detection in UAV remote sensing images using YOLOv7-tiny with dynamic head

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Optoelectronics Letters 2025年

作者： Yang Ye Yang sen Tong Jigang wang Zenghui Tianjin University of Technology Department of Electrical Engineering， University of South Africa

In the task of detecting targets in unmanned aerial vehicles （UAVs） aerial images， the challenge arises from small size and wide scale span of targets， making their location， extraction and feature distinction difficult. Similar categories are susceptible to confusion. To address these issues， an improved YOLOv7-tiny aerial detection algorithm is proposed. Firstly， to improve the identification of small targets， a small target detection layer is added while removing the maximum target detection layer to enhance the localization ability of small targets and make the model lightweight. Secondly， a CBAM （Convolutional Block Attention Module） attention mechanism is incorporated at the connection between the backbone and neck to focus on the target area and eliminate interference. Additionally， to further enhance the classification and location capabilities of the targets， the detection head is replaced with a dynamic head （DYHead） with a unified channel number to fuse scale， space and task awareness in a single module. Finally， to overcome the difficulty of extracting features， the neck is replaced with a CS-FPN （Cross-Scale Feature Pyramid Network） structure with cross-scale connections to amplify feature fusion. Comparative experiments on the VisDrone2021 dataset show that the proposed model can improve mAP50and mAP0.5:0.95by 8.3% and 6.1%， respectively， compared to the original YOLOv7-tiny model， and significant improvements are also observed on CARPK and SeaDronesSee datasets.

关键词：

High-dense nanocrystalline W-based alloy prepared by hot isostatic pressing with uniform microstructure, ultrahigh hardness and good thermal stability

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Tungsten 2025年第1期7卷 120-136页

作者： Zao-Ming Wu Lin He Lin-sen Ye Xiao-Feng Yang Jia-Jia Zhang Hong-Bo Lei Institute of Materials China Academy of Engineering Physics

High-density uniform microstructure nanocrystalline W-10wt.% Cr-5wt.% Y（W-10Cr-5Y） alloy with an average grain size of 85 nm and a relative density of 99.8% was successfully prepared.W-Cr-Y alloys with different amounts of second-phase particles were prepared by high-energy ball milling and hot isostatic pressing *** effects of composition design,ball milling parameters,and sintering parameters on the microstructure of W-Cr-Y alloys were studied.A feasible technology for controlling the synthesis of high-density nanocrystalline W-based alloys has been *** microstructure analysis of nanocrystalline W-10Cr-5Y alloy shows that there are two types of doping in the second phase:intergranular doping and intragranular *** "uniform distribution YOx-rich particles" effectively suppresses the grain growth of W and leads to the formation of nanocrystalline W-10Cr-5Y alloy.W-10Cr-5Y has an ultra-high hardness,with a Vickers hardness of 1312±12 kgf·***-temperature annealing treatment shows that W-10Cr-5Y has good thermal stability at 1000 and1100℃,as demonstrated by the comparison of Vickers hardness and grain size between annealed and unannealed alloys.

关键词： Hot isostatic pressing Microstructure Nanocrystalline tungsten Thermal stability Vickers hardness

Point-voxel dual transformer for LiDAR 3D object detection

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Optoelectronics Letters 2025年

作者： Tong Jigang Yang Fanhang Yang sen Du Shengzhi Tianjin Key Laboratory for Control Theory & Applications in Complicated Systems and Intelligent Robot La-boratory， Tianjin University of Technology， 391 Binshui West Road Department of Electrical Engineering， Tshwane University of Technology

Deep learning for point clouds faces the challenge of their inherent unordered nature， which makes traditional CNN-like methods not directly applicable. However， due to the inherent permutation invariance， transformers provide solutions to unordered points problems faced in LiDAR-based object detection. In this paper， a two-stage LiDAR 3D object detection framework is presented， namely Point-Voxel Dual Transformer (PV-DT3D)， which is a transformer-based method. In the proposed PV-DT3D， point-voxel fusion features are used for proposal refinement. Specifically， in the PV-DT3D， keypoints are sampled from entire point cloud scene and used to encode representative scene features via a proposal-aware voxel set abstraction module. Subsequently， following the generation of proposals by the region proposal networks (RPN)， the internal encoded keypoints are fed into dual transformer encoder-decoder architecture. In 3D object detection， the proposed PV-DT3D is the first to take advantage of both pointwise transformer and channel-wise architecture to capture contextual information from the perspective of spatial and channel dimensions. Experiments conducted on the highly competitive KITTI 3D car detection leaderboard show that， the PV-DT3D achieves superior detection accuracy among state-of-the-art point-voxel-based methods.

关键词：

Hyperbolic cosine transformer for LiDAR 3D object detection

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Optoelectronics Letters 2025年

作者： Tong Jigang Yang Fanhang Yang sen Du Shengzhi Tianjin Key Laboratory for Control Theory & Applications in Complicated Systems and Intelligent Robot Laboratory， Tianjin University of Technology Department of Electrical Engineering， Tshwane University of Technology

Recently， Transformer has achieved great success in computer vision. However， it is constrained because the spatial and temporal complexity grows quadratically with the number of large points in 3D object detection applications from point clouds. Previous point-wise methods are suffering from time consumption and limited receptive fields to capture information among points. To address these limitations， we propose the cosh-attention， which reduces the computation complexity of space and time from the quadratic order to linear order with respect to the number of points. In the cosh-attention， the traditional softmax operator is replaced by non-negative ReLU activation and hyperbolic-cosine-based operator with re-weighting mechanism. Then based on the key component， cosh-attention， we present a two-stage hyperbolic cosine transformer (ChTR3D) for 3D object detection from point clouds. It refines proposals by applying cosh-attention in linear computation complexity to encode rich contextual relationships among points. Extensive experiments on the widely used KITTI dataset and Waymo Open Dataset demonstrate that， compared with vanilla attention， the cosh-attention significantly improves the inference speed with competitive performance. Experiment results show that， among two-stage state-of-the-art methods using point-level features to refine proposals， the proposed ChTR3D is the fastest one.

关键词：

Local-contrastive-learning machine with both generalization and adversarial robustness: A statistical physics analysis

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Science China(Physics,Mechanics & Astronomy) 2025年第1期Mechanics & Astronomy) .卷 109-123页

作者： Mingshan Xie Yuchen wang Haiping Huang PMI Lab School of Physics Sun Yat-sen University Guangdong Provincial Key Laboratory of Magnetoelectric Physics and Devices Sun Yat-sen University

Distinct from human cognitive processing, deep neural networks trained by backpropagation can be easily fooled by adversarial examples. To design a semantically meaningful representation learning, we discard backpropagation, and instead, propose a local contrastive learning, where the representations for the inputs bearing the same label shrink(akin to boson) in hidden layers,while those of different labels repel(akin to fermion). This layer-wise learning is local in nature, being biologically plausible.A statistical mechanics analysis shows that the target fermion-pair-distance is a key parameter. Moreover, the application of this local contrastive learning to MNIST benchmark dataset demonstrates that the adversarial vulnerability of standard perceptron can be greatly mitigated by tuning the target distance, i.e., controlling the geometric separation of prototype manifolds.

关键词： machine learning statistical mechanics adversarial robustness neural networks

Enhanced subacute ischemic stroke treatment via multistage drug delivery system design for combination therapy

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Science China Chemistry 2025年

作者： Xihan Xu Juan-Juan Li Jiamin Li Hui-Yan Zhang Yilin Qi Bing-sen Shi Tianqi Li Shan-Shan Su Weitao Zhao Chang Chen Zhongying Gong Huiyu Liu Ke-Rang wang Dong-Sheng Guo Xue Xue State Key Laboratory of Medicinal Chemical Biology College of Pharmacy Nankai University College of Chemistry State Key Laboratory of Elemento-Organic Chemistry Key Laboratory of Functional Polymer Materials (Ministry of Education) Frontiers Science Center for New Organic Matter Collaborative Innovation Center of Chemical Science and EngineeringNankai University College of Chemistry and Materials Science State Key Laboratory of New Pharmaceutical Preparations and Excipients Key Laboratory of Medicinal Chemistry and Molecular Diagnosis (Ministry of Education) Key Laboratory of Chemical Biology of Hebei Province Hebei Research Center of the Basic Discipline of Synthetic Chemistry Hebei University Department of Neurology Tianjin First Central Hospital School of Medicine Nankai University Beijing Advanced Innovation Center for Soft Matter Science and Engineering State Key Laboratory of Organic-Inorganic Composites Beijing Laboratory of Biomedical Materials Bionanomaterials & Translational Engineering Laboratory Beijing Key Laboratory of BioprocessBeijing University of Chemical Technology

The management of acute ischemic stroke remains challenging due to its abrupt onset and the narrow treatment window,resulting in high rates of disability and *** therapy for neuroprotection and neurorepair strategies provided new hopes for subacute stroke *** we designed a multistage nanodelivery system that matches the unique microenvironment of the subacute phase of stroke,which utilizes calixarene as a building block to effectively load the neuroprotective drug *** calixarene is designed with glycosidic linkages targeting the glucose transporter 1 (GLUT1)on the blood-brain barrier (BBB) and azo bonds that are responsive to hypoxic ***,the decomposed calixarene molecules themselves possess intrinsic bio-activation to modulate inflammatory responses,achieving a multistage therapeutic approach that transitions from targeting to release and finally to *** approach combines anti-inflammation and neuroprotection,providing a multi-level treatment *** system was validated in a rat model of permanent middle cerebral artery occlusion (pMCAO),demonstrating that intravenous administration of the nanodelivery system repairs brain damage and improves motor function 24 h post-pMCAO *** work offers a precise and integrative strategy for stroke patients missing the acute therapy window to improve functional recovery and enhance the effect of comprehensive treatment.

关键词：

Meningeal lymphatic vessel crosstalk with central nervous system immune cells in aging and neurodegenerative diseases

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Neural Regeneration Research 2025年第3期20卷 763-778页

作者： Minghuang Gao Xinyue wang Shijie Su Weicheng Feng Yaona Lai Kongli Huang Dandan Cao Qi wang Science and Technology Innovation Center Guangzhou University of Chinese MedicineGuangzhouGuangdong ProvinceChina Institute of Clinical Pharmacology Guangzhou University of Chinese MedicineGuangzhouGuangdong ProvinceChina The Sixth Affiliated Hospital Sun Yat-sen UniversityGuangzhouGuangdong ProvinceChina

Meningeal lymphatic vessels form a relationship between the nervous system and periphery, which is relevant in both health and disease. Meningeal lymphatic vessels not only play a key role in the drainage of brain metabolites but also contribute to antigen delivery and immune cell activation. The advent of novel genomic technologies has enabled rapid progress in the characterization of myeloid and lymphoid cells and their interactions with meningeal lymphatic vessels within the central nervous system. In this review, we provide an overview of the multifaceted roles of meningeal lymphatic vessels within the context of the central nervous system immune network, highlighting recent discoveries on the immunological niche provided by meningeal lymphatic vessels. Furthermore, we delve into the mechanisms of crosstalk between meningeal lymphatic vessels and immune cells in the central nervous system under both homeostatic conditions and neurodegenerative diseases, discussing how these interactions shape the pathological outcomes. Regulation of meningeal lymphatic vessel function and structure can influence lymphatic drainage, cerebrospinal fluid-borne immune modulators, and immune cell populations in aging and neurodegenerative disorders, thereby playing a key role in shaping meningeal and brain parenchyma immunity.

关键词： central nervous system meningeal lymphatic vessels immunity myeloid cells lymphatic cells neurodegenerative disease

维普期刊数据库

Design of a terahertz slotted waveguide array antenna based on photonic crystal

在线全文

学校读者我要写书评

暂无评论

Optoelectronics Letters 2025年

作者： PAN Wu YE Kuan ZHANG Zhen LI Renpu QIU sen HUANG Lei College of Photoelectronic Engineering， Chongqing University of Posts and Telecommunications Chongqing Municipal Key Laboratory of Photoelectric Information sensing and Transmission Technology， Chongqing University of Posts and Telecommunications Laboratory of Quantum Information Technology， Chongqing University of Posts and Telecommunications

In this paper， a terahertz slotted waveguide array antenna is designed based on photonic crystal， which can realize efficient radiation of terahertz waves. The electromagnetic wave is fed from the rectangular waveguide at the bottom of the antenna， coupled to photonic crystal waveguide through photonic crystal cavity， and radiated outward through slots at the top layer of antenna. The simulation results show that the antenna achieves a peak gain of 13.45dBi at 360 GHz， a half-power beamwidth of 10.9o， and a side lobe level of -13.9dB. The antenna based on photonic crystal has the advantages of low profile， low loss， and high radiation efficiency， which can be applied to terahertz wireless communication systems.

关键词：

Method for Evaluating Digital Video Electromagnetic Information Leakage from Video Cable

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2021年第5期30卷 978-985页

作者： wang sen QIU Yang TIAN Jin AECC Aero Engine Control System Institute Electromagnetic Compatibility Laboratory Xidian University

Electromagnetic emissions from electrical information equipment may contain useful information and lead to information leakage. In order to detect the electromagnetic information leakage of digital video cable,a rapid testing method for computer video information leakage detection without reconstructing the displayed image is proposed. In this method, the electromagnetic radiation spectrum of typical image transmitted by HDMI cable is simulated. Then the electromagnetic radiation spectrum of the computer when transmitting the same image as the typical image is obtained by conduction and radiation EMC test methods. Finally, the correlation between the spectrum of simulation and the test spectrum is analyzed, and the correlation coefficient is used to judge whether the computer has produced the electromagnetic leakage of video information. The analysis and test results show that when the correlation coefficient is greater than 0.5, the electromagnetic leakage of computer video information can be judged.

关键词： lead rapid testing method computer video information leakage detection displayed image electrical information equipment evaluating digital video electromagnetic information leakage test spectrum typical image electromagnetic leakage electromagnetic radiation spectrum HDMI cable correlation coefficient electromagnetic emissions digital video broadcasting electromagnetic compatibility digital video cable