检索结果-内蒙古大学图书馆

15th International Conference on Microwave and Millimeter Wave technology, ICMMT 2023

作者： Lu, Yong-Han Ma, Jing Li, Zhi-Hao Huang, Jia-Jia Mo, Kun-Shan Peng, Lin Guilin541004 China Education Department of Guangxi Zhuang Autonomous Region Guilin541004 China Beijing Simulation Center Science and Technology on Special System Simulation Laboratory Beijing100854 China

ISBN: (纸本)9798350338874

This paper proposes a W-band all-dielectric lens antenna with the characteristic flat-top beam. The lens loaded on the horn is composed of 10 concentric elliptical rings and a tapered matching layer. Its geometries are optimized by the non-dominated sorting genetic algorithm II (NSGA-II). The lens antenna designed at 92-97 GHz achieves a beamwidth of 40° with ripple level less than 1 dB in E-plane and H-plane. In addition, the proposed antenna can be prototyped easily using 3D-printing technology with low cost. © 2023 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

The Comparison of Different Visual Features for Visual Odometry

The Comparison of Different Visual Features for Visual Odome...

引用

2018 IEEE CSAA Guidance, Navigation and Control Conference, CGNCC 2018

作者： Jiang, Yuehan Wang, Qing Dong, Chaoyang Zhou, Min Zhong, Kewei Beihang University School of Automation Science and Electrical Engineering Beijing100191 China Science and Technology on Special System Simulation Laboratory Beijing Simulation Center Beijing100854 China Shanghai Aerospace Control Technology Institute Shanghai201100 China

ISBN: (纸本)9781538611715

For robots to work effectively, the availability of a map with detailed information surrounding the workspace is an important requirement for indoor and outdoor tasks. This is usually achieved with using visual odometry techniques with feature-based methods. In this paper, we compare the performance of three different feature extraction methods: Scale Invariant Feature Transform (SIFT), Speed Up Robust Features (SURF) and Oriented FAST Rotated BRIEF (ORB). This paper presents experimental results on standard evaluation datasets and all experiments use measurement of the number of image correspondences as well as the ratio of good matched for the evaluation purpose. The results of experiments demonstrate that the performances of three methods in processing time, matching capability and accuracy. SIFT presents its stability in most scenarios although it is very slow. SURF is faster than SIFT and outperform SIFT on some scenarios. ORB is the most efficient feature and shows strong performance. © 2018 IEEE.

关键词： Vision

来源：评论

学校读者我要写书评

暂无评论

DPNet: Dynamic Pooling Network for Accurate and Efficient Size-Aware Tiny Object Detection

引用

IEEE Internet of Things Journal 2025年

作者： Gong, Luqi Chen, Haotian Chen, Yikun Yao, Tianliang Li, Chao Zhao, Shuai Han, Guangjie Beijing University of Posts and Telecommunications School of Computer Science Beijing China Zhejiang Lab Research Center for Space Computing System Hangzhou China Southwest Jiaotong University SWJTU-LEEDS Joint School Chengdu China LTD Guangdong Zhiyun City construction Technology Co Zhuhai China Tongji University College of Electronic and Information Engineering Department of Control Science and Engineering Shanghai China Hohai University Key Laboratory of Maritime Intelligent Network Information Technology Ministry of Education China

In unmanned aerial systems, especially in complex environments, accurately detecting tiny objects is crucial. Resizing images is a common strategy to improve detection accuracy, particularly for small objects. However, simply enlarging images significantly increases computational costs and the number of negative samples, severely degrading detection performance and limiting its applicability. This paper proposes a Dynamic Pooling Network (DPNet) for tiny object detection to mitigate these issues. DPNet employs a flexible down-sampling strategy by introducing a factor (df) to relax the fixed down-sampling process of the feature map to an adjustable one. Furthermore, we design a lightweight predictor to predict df for each input image, which will be used to decrease the resolution of feature map in backbone. Thus, we achieve input-aware down-sampling. We design an Adaptive Normalization Module (ANM) to make a unified detector well compatible with different dfs. At the same time, we also design a guidance loss to supervise the predictor’s training. DPNet realizes the dynamic allocation of computing resources to trade off detection accuracy and efficiency through this. Experiments on the TinyCOCO and TinyPerson datasets show that our DPNet can save over 35% and 25% GFLOPs, respectively, while maintaining comparable detection *** code will be made publicly available. © 2014 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

MTL-JER: Meta-Transfer Learning for Low-Resource Joint Entity and Relation Extraction 3

MTL-JER: Meta-Transfer Learning for Low-Resource Joint Entit...

引用

3rd International Conference on Neural Networks, Information and Communication Engineering, NNICE 2023

作者： Peng, Da Pei, Zhongmin Mo, Delin Space Engineering University Science and Technology on Complex Electronic System Simulation Laboratory Beijing China Institute of War Studies Academy of Military Sciences

ISBN: (纸本)9798350335972

Joint entity and relation extraction has achieved impressive advances in NLP, such as document understanding and knowledge graph construction. The typical methods for entity and relation extraction typically break down the joint task into several smaller components or stages for ease of implementation, but this leads to a loss of the interconnected knowledge in the triple. Hence, we propose to model the triple in one module jointly. Furthermore, the labeling of a joint entity and relation extraction tasks is costly and domain-specific;therefore, it is important to improve its performance on low-resource data and domain adaption. To address this issue, we suggest using two sources that are rich in information, namely pre-trained models on large data and multi-domain text corpora. Pretraining allows us to provide the model with the fundamental ability to perform joint entity and relationship extraction. Second, through meta-learning on multi-domain text, we can improve the model's generalization capabilities, enabling it to perform well even with limited data. We present MTL-JER, a Meta-Transfer Learning method for Joint Entity and Relation Extraction in low-resource settings in this paper. Using exhaustive experiments on five datasets, we prove that our model obtains optimal results. © 2023 IEEE.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Planting area and production decreased for winter-triticeae crops but increased for rapeseed in Ukraine with climatic impacts dominating

引用

Geography and Sustainability 2025年第2期6卷 108-116页

作者： Jichong Han Yuchuan Luo Zhao Zhang Jialu Xu Yi Chen Senthold Asseng Jonas Jägermeyr Christoph Müller Jørgen E Olesen Reimund Rötter Fulu Tao Joint International Research Laboratory of Catastrophe Simulation and Systemic Risk Governance School of National Safety and Emergency ManagementBeijing Normal UniversityZhuhai 519087China School of Systems science Beijing Normal UniversityBeijing 100875China Chongqing Jinfo Mountain Karst Ecosystem National Observation and Research Station School of Geographical SciencesSouthwest UniversityChongqing 400715China Key Laboratory of Land Surface Pattern and Simulation Institute of Geographical Sciences and Natural Resources ResearchChinese Academy of SciencesBeijing 100101China Technical University of Munich Department of Life Science EngineeringDigital AgricultureHEF World Agricultural Systems CenterFreisingGermany NASA Goddard Institute for Space Studies New YorkNYUSA Columbia University Center for Climate Systems ResearchNew YorkNYUSA Potsdam Institute for Climate Impacts Research(PIK) Member of the Leibniz AssociationPotsdamGermany Department of Agroecology Aarhus UniversityTjeleDenmark University of Götingen Tropical Plant Production and Agricultural Systems Modelling(TROPAGS)GötingenGermany University of Götingen Centre for Biodiversity and Sustainable Land Use(CBL)GötingenGermany College of Resources and Environment University of Chinese Academy of SciencesBeijing 100049China

On-time mapping dynamics of crop area,yield,and production is important for global food *** information,however,is often not ***,we used satellite information,a spectral-phenology integration approach for mapping crop area,and a machine learning model for predicting yield in the war-stricken *** found that in Ukraine crop area and production declined in 2022 relative to 2017–2021 and 2021 for wintertriticeae crops,which was invaded before the cropping season in February of that *** the same time,crop area and production for rapeseed increased in Ukraine,with yields consistently lower by 6.5%relative to *** low precipitation and the Russian-Ukrainian conflict-related factors contributed to such yield variations by-1.3%and-0.9%for winter-triticeae crops and-4.2%and-0.5%for rapeseed in *** demonstrate a robust framework for monitoring country-wide crop production dynamics in near real-time,serving as an early-foodsecurity-warning system.

关键词： Food security Conflict Machine learning Production Satellite

来源：评论

学校读者我要写书评

暂无评论

Affinity Propagation for Hyperspectral Band Selection 2

Affinity Propagation for Hyperspectral Band Selection

引用

2018 2nd International Symposium on Resource Exploration and Environmental science, REES 2018

作者： Ren, Zhiwei Wu, Lingda Department of Graduate Management Space Engineering University Beijing101416 China Science and Technology on Complex Electronic System Simulation Laboratory Space Engineering University Beijing101416 China

Because hyperspectral images have the characteristics of high correlation between bands and strong information redundancy, the reduction in dimension of hyperspectral images is an important step in the pre-processing of hyperspectral images. Band selection can preserve the physical meaning of the original data while reducing dimension and has application in many aspects. Affinity Propagation Clustering (AP) is a clustering method proposed by Fray et al. in 2007. AP clusters based on the correlation between data points and treats all data points as potential cluster centers. This paper proposes a band selection method based on AP clustering, which introduces wavelet transform into the calculation of similarity and preference value in clustering algorithm. The dimensionality reduction results are input into the minimum distance classifier for classification, and the classification accuracy was calculated. The dataset is validated by the Indiana Pines dataset. The experimental results verify the effectiveness of the proposed method. © Published under licence by IOP Publishing Ltd.

关键词： Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

A Position Probability Prediction Method of Marine Moving Targets for Optimization Search by Satellite

A Position Probability Prediction Method of Marine Moving Ta...

引用

2024 IEEE International Conference on Control science and systems Engineering, ICCSSE 2024

作者： Zheng, Xiao Peng, Xiaodong Guo, Zhiyuan Qiang, Huimin Zhao, Junbao University of Chinese Academy of Science Laboratory of System Simulation and Concurrent Design Technology National Space Science Center Chinese Academy of Sciences Beijing China Beijing Remote Sensing Information Institute Beijing China

ISBN: (纸本)9798331517199

Marine moving ship target search has great application demand and development prospects in marine surveillance, marine search and rescue, customs anti-smuggling, and other aspects. Satellites are a vital means of searching for marine moving targets. Ground coverage for imaging satellites is relatively limited;the vast marine area makes searching for marine moving ships challenging. Target position prediction, used as the guidance information for satellite detection to reduce the uncertainty of the target position and improve search efficiency, is an essential approach to achieving target optimization search. This paper proposes a target position prediction method based on joint learning of multi-source factors for optimal satellite search of marine moving targets. Firstly, it analyzes the characteristics of marine moving targets and the factors affecting motion. Then, it puts forward the motion prediction model based on a deep neural network, integrating multifactor, like the state of the moving target, environmental attributes such as nautical charts, meteorology and hydrology, and kinematic constraints, to predict the target positional distribution probability. Finally, the target search strategy based on the maximum sum of the distribution probabilities of the satellite coverage area is adopted to improve target detection probability. The experiment results show that the prediction method can realize the target positional distribution probability prediction, reduce the uncertainty search when making the satellite search plan, and improve efficiency. © 2024 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Impact of phase signal formulations on tilt-to-length coupling noise in the LISA test mass interferometer

arXiv

引用

arXiv 2025年

作者： Edwards, Paul Dave, Megha Weaver, Alexander Zhao, Mengyuan Fulda, Paul Mueller, Guido Wanner, Gudrun University of Florida Physics Department University of Florida Department of Physics 2001 Museum Road GainesvilleFL32611 United States Callinstr. 38 HannoverD-30167 Germany Institute for Gravitational Physics Leibniz Universität Hannover Callinstr. 38 HannoverD-30167 Germany Key Laboratory of Electronics and Information Technology for Space System National Space Science Center Chinese Academy of Sciences No.1 Nanertiao Zhongguancun Haidian district Beijing100190 China

Tilt-to-length (TTL) coupling in the Laser Interferometer space Antenna (LISA) can generate spurious displacement noise that potentially affects the measurement of gravitational wave signals. In each test mass interferometer, the coupling of misalignments with spacecraft angular jitter produces noise in the longitudinal pathlength signal. This signal comes from the phase readout combinations of an interfering measurement beam and a local reference beam at a quadrant photodetector, but various formulations exist for its calculation. Selection of this pathlength signal formulation affects the TTL coupling noise. We therefore simulated two pathlength signal candidates, the complex sum and the averaged phase, and evaluated their performance in the LISA test mass interferometer under the assumption of static alignment imperfections. All simulations were performed using three different methods with cross-checked results. We find with all three methods that the averaged phase is the choice with equal or less TTL coupling noise in four out of the five test cases. Finally, we show that the non-linear TTL contributions in the test mass interferometer to be negligible in all our test-cases, no matter which formulation of pathlength signal is chosen. © 2025, CC BY-NC-ND.

关键词： Laser interferometry

来源：评论

学校读者我要写书评

暂无评论

A maneuvering penetration strategy via integrated flight/propulsion guidance and control method for air-breathing hypersonic vehicle

A maneuvering penetration strategy via integrated flight/pro...

引用

2018 IEEE CSAA Guidance, Navigation and Control Conference, CGNCC 2018

作者： Xue, Kong Guodong, Ning Ming, Yang Songyan, Wang Harbin Institute of Technology Control and Simulation Center and Science and Technology Complex System Control and Intelligent Agent Cooperation Laboratory China Beijing Electro-Mechanical Institute China Harbin Institute of Technology Control and Simulation Center China

ISBN: (纸本)9781538611715

Given a maneuvering control strategy for air-breathing hypersonic vehicle, which adopt the compound integrated flight/propulsion guidance and control method, further excavation the capability of scramjet to run stable and low fuel consumption, on this basis, implement accelerate snake maneuver, improve the survival probability of weapons, guarantee the practical application ability of the project. Take one certain type of air-breathing hypersonic vehicle as an example, on the basis of an accurate simulation model, several groups of simulation analysis are carried out, the simulation results show that the method is effective and reliable. © 2018 IEEE.

关键词： Hypersonic vehicles

来源：评论

学校读者我要写书评

暂无评论

DeePMD-kit v3: A Multiple-Backend Framework for Machine Learning Potentials

arXiv

引用

arXiv 2025年

作者： Zeng, Jinzhe Zhang, Duo Peng, Anyang Zhang, Xiangyu He, Sensen Wang, Yan Liu, Xinzijian Bi, Hangrui Li, Yifan Cai, Chun Zhang, Chengqian Du, Yiming Zhu, Jia-Xin Mo, Pinghui Huang, Zhengtao Zeng, Qiyu Shi, Shaochen Qin, Xuejian Yu, Zhaoxi Luo, Chenxing Ding, Ye Liu, Yun-Pei Shi, Ruosong Wang, Zhenyu Bore, Sigbjørn Løland Chang, Junhan Deng, Zhe Ding, Zhaohan Han, Siyuan Jiang, Wanrun Ke, Guolin Liu, Zhaoqing Lu, Denghui Muraoka, Koki Oliaei, Hananeh Singh, Anurag Kumar Que, Haohui Xu, Weihong Xu, Zhangmancang Zhuang, Yong-Bin Dai, Jiayu Giese, Timothy J. Jia, Weile Xu, Ben York, Darrin M. Zhang, Linfeng Wang, Han School of Artificial Intelligence and Data Science Unversity of Science and Technology of China Hefei China AI for Science Institute Beijing100080 China DP Technology Beijing100080 China Academy for Advanced Interdisciplinary Studies Peking University Beijing100871 China State Key Lab of Processors Institute of Computing Technology Chinese Academy of Sciences Beijing100871 China University of Chinese Academy of Sciences Beijing China Baidu Inc. Beijing China Department of Computer Science University of Toronto TorontoON Canada Department of Chemistry Princeton University PrincetonNJ08540 United States University of Chinese Academy of Sciences Beijing100871 China State Key Laboratory of Physical Chemistry of Solid Surfaces iChEM College of Chemistry and Chemical Engineering Xiamen University Xiamen361005 China College of Integrated Circuits Hunan University Changsha410082 China State Key Laboratory of Advanced Technology for Materials Synthesis and Processing Center for Smart Materials and Device Integration School of Material Science and Engineering Wuhan University of Technology Wuhan430070 China College of Science National University of Defense Technology Changsha410073 China Hunan Key Laboratory of Extreme Matter and Applications National University of Defense Technology Changsha410073 China ByteDance Research Beijing100098 China Ningbo Institute of Materials Technology and Engineering Chinese Academy of Sciences Ningbo315201 China College of Materials Science and Opto-Electronic Technology University of Chinese Academy of Sciences Beijing100049 China Key Laboratory of Theoretical and Computational Photochemistry of Ministry of Education College of Chemistry Beijing Normal University Beijing100875 China Department of Geosciences Princeton University PrincetonNJ08544 United States Department of Applied Physics and Applied Mathematics Columbia University New YorkNY10027 United States IKKEM Fujian Xiamen361005 China Graduate

In recent years, machine learning potentials (MLPs) have become indispensable tools in physics, chemistry, and materials science, driving the development of software packages for molecular dynamics (MD) simulations and related applications. These packages, typically built on specific machine learning frameworks such as TensorFlow, PyTorch, or JAX, face integration challenges when advanced applications demand communication across different frameworks. The previous TensorFlow-based implementation of DeePMD-kit exemplified these limitations. In this work, we introduce DeePMD-kit version 3, a significant update featuring a multi-backend framework that supports TensorFlow, PyTorch, JAX, and PaddlePaddle backends, and demonstrate the versatility of this architecture through the integration of other MLPs packages and of Differentiable Molecular Force Field. This architecture allows seamless backend switching with minimal modifications, enabling users and developers to integrate DeePMD-kit with other packages using different machine learning frameworks. This innovation facilitates the development of more complex and interoperable workflows, paving the way for broader applications of MLPs in scientific research. Copyright © 2025, The Authors. All rights reserved.

关键词： Molecular dynamics

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：