检索结果-内蒙古大学图书馆

Sensitivity analysis of Structural Dynamic Behavior Based on the Sparse Polynomial Chaos Expansion and Material Point Method

引用

Computer Modeling in Engineering & sciences 2025年第2期142卷 1515-1543页

作者： Wenpeng Li Zhenghe Liu Yujing Ma Zhuxuan Meng Ji Ma Weisong Liu Vinh Phu Nguyen Key Laboratory of In-situ Property-improving Mining of Ministry of Education Taiyuan University of TechnologyTaiyuan030024China Academy of Military Science Beijing100091China College of Mechanical and Vehicle Engineering Taiyuan University of TechnologyTaiyuan030024China Department of Civil Engineering Monash UniversityClaytonVIC 3800Australia

This paper presents a framework for constructing surrogate models for sensitivity analysis of structural dynamics *** models involving deformation,such as collisions,vibrations,and penetration,are devel-oped using the material point *** reduce the computational cost of Monte Carlo simulations,response surface models are created as surrogate models for the material point system to approximate its dynamic *** adaptive randomized greedy algorithm is employed to construct a sparse polynomial chaos expansion model with a fixed order,effectively balancing the accuracy and computational efficiency of the surrogate *** on the sparse polynomial chaos expansion,sensitivity analysis is conducted using the global finite difference and Sobol *** examples of structural dynamics are provided to demonstrate the effectiveness of the proposed method in addressing structural dynamics problems.

关键词： Structural dynamics deformation material point method sparse polynomial chaos expansion adaptive randomized greedy algorithm sensitivity analysis

来源：评论

学校读者我要写书评

暂无评论

Underwater acoustic target recognition using line enhancement and deep neural network

引用

Chinese Journal of Acoustics 2024年第4期43卷 452-467页

作者： YU Xueyang CHI Cheng LI Shuqiu LI Derui Institute of Acoustics Chinese Academy of SciencesBeijing 100190 University of Chinese Academy of Sciences Beijing 100049 Key Laboratory of Science and Technology on Advanced Underwater Acoustic Signal Processing Chinese Academy of SciencesBeijing 100190

To enhance the features of underwater acoustic target signals,and improve the performance of underwater acoustic target recognition based on deep neural network,a target recognition method using line enhancement and deep neural network is *** method focuses on the narrowband information enhancement and sets an adaptive line enhancement filter at the front end of the VGGish *** signals are processed by the line enhancement filter and input into the network to extract deep features,and then these features are classified by a *** effectiveness of the method is verified by the actual underwater acoustic *** component analysis is performed on the deep feature set of the underwater acoustic signals,and the results show that the compactness of the deep feature set obtained after line enhancement is significantly *** proposed method can obtain a recognition accuracy of 94.83%on the test dataset,which is improved by 5.48%compared to the case without line enhancement,and it is also more robust under the condition of low signal-to-noise ratio.

关键词： underwater method verified

来源：评论

学校读者我要写书评

暂无评论

Graph Prompt Clustering

引用

IEEE Transactions on Pattern analysis and Machine Intelligence 2025年第7期47卷 5794-5805页

作者： Chen, Man-Sheng Lai, Pei-Yuan Liao, De-Zhang Wang, Chang-Dong Lai, Jian-Huang Sun Yat-sen University School of Computer Science and Engineering Guangzhou510275 China Guangxi Zhuang Autonomous Region Information Center Guangxi Key Laboratory of Digital Infrastructure Nanning530219 China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou510006 China Ministry of Education Key Laboratory of Machine Intelligence and Advanced Computing Beijing100816 China South China Technology Commercialization Center Guangzhou510006 China Guangdong University of Technology School of Information Engineering Guangzhou510006 China Guangdong Key Laboratory of Information Security Technology Guangzhou510033 China Ministry of Education Beijing100044 China

Due to the wide existence of unlabeled graph-structured data (e.g., molecular structures), the graph-level clustering has recently attracted increasing attention, whose goal is to divide the input graphs into several disjoint groups. However, the existing methods habitually focus on learning the graphs embeddings with different graph reguralizations, and seldom refer to the obvious differences in data distributions of distinct graph-level datasets. How to characteristically consider multiple graph-level datasets in a general well-designed model without prior knowledge is still challenging. In view of this, we propose a novel Graph Prompt Clustering (GPC) method. Within this model, there are two main modules, i.e., graph model pretraining as well as prompt and finetuning. In the graph model pretraining module, the graph model is pretrained by a selected source graph-level dataset with mutual information maximization and self-supervised clustering regularization. In the prompt and finetuning module, the network parameters of the pretrained graph model are frozen, and a groups of learnable prompt vectors assigned to each graph-level representation are trained for adapting different target graph-level datasets with various data distributions. Experimental results across six benchmark datasets demonstrate the impressive generalization capability and effectiveness of GPC compared with the state-of-the-art methods. © 1979-2012 IEEE.

关键词： Graph embeddings

来源：评论

学校读者我要写书评

暂无评论

From Global to Hybrid: A Review of Supervised Deep Learning for 2D Image Feature Representation

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第6期6卷 1540-1560页

作者： Dong, Xinyu Wang, Qi Deng, Hongyu Yang, Zhenguo Ruan, Weijian Liu, Wu Lei, Liang Wu, Xue Tian, Youliang Guizhou University State Key Laboratory of Public Big Data College of computer science Guiyang550025 China Guangdong University of Technology Guangzhou510006 China Chinese Academy of Sciences Shenzhen Institute of Advanced Technology Shenzhen518000 China AI Research of *** Beijing100101 China

Computer vision is the science that aims to enable computers to emulate human visual perception, and it encompasses various techniques and methods for extracting and interpreting information from two-dimensional images. Supervised deep 2D image feature representation is a fundamental problem in computer vision that applies deep learning techniques to extract and process information from a given 2D image under supervised settings. The goal is to obtain a feature vector that can be utilized for various downstream computer vision applications. The quality of supervised deep 2D image feature representation algorithms directly affects the performance of downstream applications. However, most of the existing vision research only explores supervised deep 2D image feature representation for specific subtasks. Therefore, a comprehensive discussion on this topic is needed. In this paper, we propose a taxonomy of supervised deep 2D image feature representation methods based on four categories: global representation, region representation, hash representation, and hybrid representation, and we introduce their typical approaches. Furthermore, we perform a comparative analysis of the representative methods on three fundamental tasks: image classification, object detection, and semantic segmentation, as well as other common tasks. We also discuss the limitations of supervised deep 2D image feature representation and investigate future directions in image representation to facilitate the advancement of computer vision through image representation. © 2020 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Unbound^(28)O,the heaviest oxygen isotope observed:a cutting-edge probe for testing nuclear models

引用

Nuclear science and Techniques 2024年第2期35卷 1-2页

作者： Jian-Guo Li Bai-Shan Hu Shuang Zhang Fu-Rong Xu School of Physics and State Key Laboratory of Nuclear Physics and TechnologyPeking UniversityBeijing 100871China Institute of Modern Physics Chinese Academy of SciencesLanzhou 730000China Southern Center for Nuclear-Science Theory(SCNT) Institute of Modern PhysicsChinese Academy of SciencesHuizhou 516000China

The beyond-dripline oxygen isotopes^(27,28)O were recently observed at RIKEN,and were found to be unbound decaying into^(24)O by emitting *** unbound feature of the heaviest oxygen isotope,^(28)O,provides an excellent test for stateof-the-art nuclear *** atomic nucleus is a self-organized quantum manybody system comprising specific numbers of protons Z and neutrons N.

关键词： testing quantum system

来源：评论

学校读者我要写书评

暂无评论

Design and application of skin disease biosensor based on Terahertz metasurface 10

Design and application of skin disease biosensor based on Te...

引用

Infrared, Millimeter-Wave, and Terahertz Technologies X 2023

作者： Yang, Zhou Zhang, Fan Han, Yuke Bi, Hao You, Rui Tong, Meng Key Laboratory of Ministry of Education for Optoelectronic Measurement Technology and Instruments Beijing Information Science and Technology University Beijing100192 China Beijing Laboratory of Biomedical Testing Technology and Instruments Beijing Information Science and Technology University Beijing100192 China Second Affiliated Hospital of Harbin Medical University Harbin150000 China

ISBN: (纸本)9781510668010

Skin disease is one of the most common diseases affecting human health, and it is vital to detect and diagnose it rapidly and accurately through skin tissue. Terahertz metasurface sensors (THz MSs) offer the advantages of label-free and sensitive detection by virtue of the capacity to perceptively sense changes in the refractive index of substances and the dielectric environment on their surfaces. In this paper, an array of quadrupole metal split-ring resonators (SRRs) was proposed. For the purpose of achieving a high Q-factor and sensitivity at the same time, parameters including cell size and opening gap are tuned. On account of the centrosymmetric cell structure of the sensor, angle sensitivity-related experimental errors could be essentially eliminated. Resonant cavities and connecting arms excite LC resonance on metasurfaces upon interaction with THz waves, resulting in two resonant dips in the transmission spectrum. Using photolithographic processing techniques, periodic metallic patterns were formed on a thin quartz substrate to create the metasurface. In the experiments, skin disease tissue samples were taken from patients, and the transmission spectra of the metasurface sensor covered with skin tissue were obtained by a terahertz frequency domain spectroscopy system. The result shows that resonant frequencies of the sensors covered by skin tissues of disease are shifted towards the lower frequency region compared with normal tissues. This dual resonance frequency sensor made it possible to visually distinguish between diseased and normal tissues by analyzing the resonance frequency shift with superior sensing performance and accuracy without the necessity of analyzing the complex terahertz intrinsic spectrum and refractive index of the samples. © 2023 SPIE.

关键词： Refractive index

来源：评论

学校读者我要写书评

暂无评论

An Internet of Things based scalable framework for disaster data management

引用

Journal of Safety science and Resilience 2022年第2期3卷 136-152页

作者： Zhiming Ding Shan Jiang Xinrun Xu Yanbo Han Institute of Software Chinese Academy of Sciences Beijing 100190China University of Chinese Academy of Sciences Beijing 100049China North China University of Technology Beijing 100144China Beijing Key Laboratory on Integration and Analysis of Large-scale Stream Data BeijingChina

In recent years, undesirable disasters attacked the cities frequently, leaving heavy casualties and serious economiclosses. Meanwhile, disaster detection based on the Internet of Things(IoT) has become a hot spot that benefitedfrom the established development of smart city construction. And the IoT is visibly sensitive to the managementand monitoring of disasters, but massive amounts of monitoring data have brought huge challenges to datastorage and data analysis. This article develops a new and much more general framework for disaster emergencymanagement under the IoT environment. The framework is a bottom-up integration of highly scalable Raw DataStorages(RD-Stores) technology, hybrid indexing and queries technology, and machine learning technology foremergency disasters. Experimental results show that hybrid index and query technology have better performanceunder the condition of supporting multi-modal retrieval, and providing a better solution to offer real-time retrievalfor the massive sensor sampling data in the IoT. In addition, further works to evaluate the top-level sub-applicationsystem in this framework were performed based on the GPS trajectory data of 35,000 beijing taxis and thevolumetric ground truth data of 7,500 images. The results show that the framework has desirable scalability andhigher utility.

关键词： Disaster data management IoT Disaster detection Big data Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Prognostic prediction models for postoperative patients with stageⅠtoⅢcolorectal cancer based on machine learning

引用

World Journal of Gastrointestinal Oncology 2024年第12期16卷 4597-4613页

作者： Xiao-Lin Ji Shuo Xu Xiao-Yu Li Jin-Huan Xu Rong-Shuang Han Ying-Jie Guo Li-Ping Duan Zi-Bin Tian Department of Gastroenterology Beijing Key Laboratory for Helicobacter Pylori Infection and Upper Gastrointestinal DiseasesPeking University Third HospitalBeijing 100191China Beijing Aerospace Wanyuan Science Technology Co. Ltd.China Academy of Launch Vehicle TechnologyBeijing 100176China Department of Gastroenterology The Affiliated Hospital of Qingdao UniversityQingdao 266003Shandong ProvinceChina Institute of Automation Qilu University of Technology(Shandong Academy of Sciences)Jinan 250014Shandong ProvinceChina

BACKGROUND Colorectal cancer(CRC)is characterized by high heterogeneity,aggressiveness,and high morbidity and mortality *** machine learning(ML)algorithms,patient,tumor,and treatment features can be used to develop and validate models for predicting *** addition,important variables can be screened and different applications can be provided that could serve as vital references when making clinical decisions and potentially improving patient outcomes in clinical *** To construct prognostic prediction models and screen important variables for patients with stageⅠtoⅢ*** More than 1000 postoperative CRC patients were grouped according to survival time(with cutoff values of 3 years and 5 years)and assigned to training and testing cohorts(7:3).For each 3-category survival time,predictions were made by 4 ML algorithms(all-variable and important variable-only datasets),each of which was validated via 5-fold cross-validation and bootstrap *** variables were screened with multivariable regression *** performance was evaluated and compared before and after variable screening with the area under the curve(AUC).SHapley Additive exPlanations(SHAP)further demonstrated the impact of important variables on model *** were constructed for practical model *** Our ML models performed well;the model performance before and after important parameter identification was consistent,and variable screening was *** highest pre-and postscreening model AUCs 95%confidence intervals in the testing set were 0.87(0.81-0.92)and 0.89(0.84-0.93)for overall survival,0.75(0.69-0.82)and 0.73(0.64-0.81)for disease-free survival,0.95(0.88-1.00)and 0.88(0.75-0.97)for recurrence-free survival,and 0.76(0.47-0.95)and 0.80(0.53-0.94)for distant metastasis-free *** cross-validation and bootstrap validation were performed in both the training and testing *** SHAP values of the important va

关键词： Colorectal cancer Machine learning Prognostic prediction model Survival times Important variables

来源：评论

学校读者我要写书评

暂无评论

LAMOST MRS-N Observation of the W80 Region

引用

Research in Astronomy and Astrophysics 2022年第7期22卷 161-175页

作者： Yao Li Chao-Jian Wu Yong-Qiang Yao Wei Zhang Jia Yin Juan-Juan Ren Chih-Hao Hsia Rui Zhuang Jian-Jun Chen Yu-Zhong Wu Hui Zhu Bin Li Yong-Hui Hou Meng-Yuan Yao Hong Wu National Astronomical Observatories Chinese Academy of SciencesBeijing 100101China School of Astronomy and Space Science University of Chinese Academy of SciencesBeijing 100049China CAS Key Laboratory of Optical Astronomy National Astronomical ObservatoriesChinese Academy of SciencesBeijing 100101China CAS Key Laboratory of Space Astronomy and Technology National Astronomical ObservatoriesChinese Academy of SciencesBeijing 100101China State Key Laboratory of Lunar and Planetary Sciences Macao University of Science and TechnologyTaipaMacaoChina University of Science and Technology Beijing Beijing 100083China Purple Mountain Observatory Chinese Academy of SciencesNanjing 210008China University of Science and Technology of China Hefei 230026China Nanjing Institute of Astronomical Optics&Technology National Astronomical ObservatoriesChinese Academy of SciencesNanjing 210042China China Academy of Aerospace Electronics Technology Beijing 100094China

The spectral observations and analysis for the W80 region are presented by using the data of Medium-Resolution Spectroscopic Survey of Nebulae(MRS-N) with the Large Sky Area Multi-Object Fiber Spectroscopic Telescope(LAMOST).A total of 2982 high-quality nebular spectra have been obtained in the 20 square degree field of view which covers the W80 complex,and the largest sample of spectral data has been established for the first *** relative intensities,radial velocities(RVs),and full widths at half maximum(FWHMs) are measured with the high spectral resolution of LAMOST MRS-N,for Ha λ6563?,[NⅡ] λλ6548 A,6584 A,and [SⅡ] λλ6716A,6731 A emission *** the field of view of the whole W80 region,the strongest line emissions are found to be consistent with the bright nebulae NGC 7000,IC 5070,and LBN 391,and weak line emissions also exist in the Middle Region,where no bright nebulae are detected by the wide-band optical *** large-scale spectral observations of the W80 region reveal the systematic spatial variations of RVs and FWHMs,and several unique structural features.A "curved feature" to the east of NGC 7000,and a "jet feature" to the west of LBN 391 are detected to be showing larger RVs.A "wider FWHM region" is identified in the eastern part of NGC *** variations of[S Ⅱ]/Ha ratios display a gradient from southwest to northeast in the NGC 7000 region,and manifest a ring shape around the "W80 bubble" ionized by an O-type star in *** spectral and multi-band observations are guaranteed to investigate in detail the structural features.

关键词： surveys (ISM:)HII regions ISM:molecules ISM:bubbles methods:statistical

来源：评论

学校读者我要写书评

暂无评论

A Simulation of Calibration and Map-making Errors of the Tianlai Cylinder Pathfinder Array

引用

Research in Astronomy and Astrophysics 2023年第10期23卷 281-298页

作者： Kaifeng Yu Fengquan Wu Shifan Zuo Jixia Li Shijie Sun Yougang Wang Xuelei Chen National Astronomical Observatories Chinese Academy of SciencesBeijing 100101China Key Laboratory of Radio Astronomy and Technology Chinese Academy of SciencesBeijing 100101China School of Astronomy and Space Science University of Chinese Academy of SciencesBeijing 100049China Key Laboratory of Cosmology and Astrophysics(Liaoning)&College of Sciences Northeastern UniversityShenyang 110819China Center of High Energy Physics Peking UniversityBeijing 100871China

The Tianlai cylinder array is a pathfinder for developing and testing 21 cm intensity mapping *** this paper,we use numerical simulation to assess how its measurement is affected by thermal noise and the errors in calibration and map-making process,and the error in the sky map reconstructed from a drift scan *** we consider only the single frequency,unpolarized *** beam is modeled by fitting to the electromagnetic simulation of the antenna,and the variations of the complex gains of the array elements are modeled by Gaussian *** visibility data are generated and run through our data processing *** find that the accuracy of the current calibration is limited primarily by the absolute calibration,where the error comes mainly from the approximation of a single dominating point *** then studied the m-mode map-making with the help of Moore-Penrose *** find that discarding modes with singular values smaller than a threshold could generate visible artifacts in the *** impacts of the residue variation of the complex gain and thermal noise are also *** thermal noise in the map varies with latitude,being minimum at the latitude passing through the zenith of the *** angular power spectrum of the reconstructed map show that the current Tianlai cylinder pathfinder,which has a shorter maximum baseline length in the North-South direction,can measure modes up to l■2πb_(NS)/λ~200 very well,but would lose a significant fraction of higher angular modes when noise is *** results help us to identify the main limiting factors in our current array configuration and data analysis procedure,and suggest that the performance can be improved by reconfiguration of the array feed positions.

关键词： techniques:interferometric telescopes cosmology:observations (cosmology:)diffuse radiation radio continuum:general

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：