检索结果-南通市图书馆

OAAFormer:Robust and Efficient Point Cloud Registration Through Overlapping-Aware Attention in Transformer

Journal of Computer Science & Technology 2024年第4期39卷 755-770页

作者： Jun-Jie Gao Qiu-Jie Dong Rui-An Wang Shuang-Min Chen Shi-qing xin Chang-He Tu Wenping Wang School of Computer Science and Technology Shandong UniversityQingdao 266237China School of Information and Technology Qingdao University of Science and TechnologyQingdao 266061China College of Engineering Texas A&M UniversityTexasTX 77843U.S.A.

In the domain of point cloud registration,the coarse-to-fine feature matching paradigm has received significant attention due to its impressive *** paradigm involves a two-step process:first,the extraction of multilevel features,and subsequently,the propagation of correspondences from coarse to fine ***,this approach faces two notable ***,the use of the dual Softmax operation may promote one-to-one correspondences between superpoints,inadvertently excluding valuable ***,it is crucial to closely examine the overlapping areas between point clouds,as only correspondences within these regions decisively determine the actual *** these issues,we propose OAAFormer to enhance correspondence *** the one hand,we introduce a soft matching mechanism to facilitate the propagation of potentially valuable correspondences from coarse to fine *** the other hand,we integrate an overlapping region detection module to minimize mismatches to the greatest extent ***,we introduce a region-wise attention module with linear complexity during the fine-level matching phase,designed to enhance the discriminative capabilities of the extracted *** on the challenging 3DLoMatch benchmark demonstrate that our approach leads to a substantial increase of about 7%in the inlier ratio,as well as an enhancement of 2%-4%in registration ***,to accelerate the prediction process,we replace the Conventional Random Sample Consensus(RANSAC)algorithm with the selection of a limited yet representative set of high-confidence correspondences,resulting in a 100 times speedup while still maintaining comparable registration performance.

关键词： point cloud registration coarse-to-fine overlapping region feature matching Transformer

来源：

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

Automatic recognition of depression based on audio and video:A review

引用

World Journal of Psychiatry 2024年第2期14卷 225-233页

作者： Meng-Meng Han xing-Yun Li xin-Yu Yi Yun-Shao Zheng Wei-Li Xia Ya-Fei Liu qing-Xiang Wang Shandong Mental Health Center Shandong UniversityJinan 250014Shandong ProvinceChina Key Laboratory of Computing Power Network and Information Security Ministry of EducationShandong Computer Science Center(National Supercomputer Center in Jinan)Qilu University of Technology(Shandong Academy of Sciences)Jinan 250353Shandong ProvinceChina Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and TechnologyQilu University of Technology(Shandong Academy of Sciences)Jinan 250353Shandong ProvinceChina Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer ScienceJinan 250353Shandong ProvinceChina Department of Ward Two Shandong Mental Health CenterShandong UniversityJinan 250014Shandong ProvinceChina

Depression is a common mental health *** current depression detection methods,specialized physicians often engage in conversations and physiological examinations based on standardized scales as auxiliary measures for depression ***-biological markers-typically classified as verbal or non-verbal and deemed crucial evaluation criteria for depression-have not been effectively *** physicians usually require extensive training and experience to capture changes in these *** in deep learning technology have provided technical support for capturing non-biological *** researchers have proposed automatic depression estimation(ADE)systems based on sounds and videos to assist physicians in capturing these features and conducting depression *** article summarizes commonly used public datasets and recent research on audio-and video-based ADE based on three perspectives:Datasets,deficiencies in existing research,and future development directions.

关键词： Depression recognition Deep learning Automatic depression estimation System Audio processing Image processing Feature fusion Future development

来源：

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

Recent geomagnetic storms observed by Macao Science Satellite-1

引用

Earth and Planetary Physics 2024年第4期8卷 565-569页

作者： qing Yan HongBo Yao Macao Institute of Space Technology and Application Macao University of Science and TechnologyMacao 999078China

Geomagnetic storms are rapid disturbances of the Earth’s *** are related to many geophysical phenomena and have large influences on human *** and studying geomagnetic storms is thus of great significance to both scientific research and geomagnetic hazards *** Macao Science Satellite-1(MSS-1)project includes two high-precision Chinese geomagnetic satellites successfully launched on May 21,*** main purpose of MSS-1 is to accurately measure the Earth’s magnetic ***,we analyze early MSS-1 geomagnetic field measurements and report observations of two recent geomagnetic storms that occurred on March 24,2024 and May 11,*** also calculate the related geoelectric fields as an initial step towards a quantitative assessment of geomagnetic hazards.

关键词： Macao Science Satellite-1 geomagnetic storms satellite magnetics electromagnetic induction geoelectric fields

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Comparative Analysis of ARIMA and LSTM Model-Based Anomaly Detection for Unannotated Structural Health Monitoring Data in an Immersed Tunnel

引用

Computer Modeling in Engineering & Sciences 2024年第5期139卷 1797-1827页

作者： qing Ai Hao Tian Hui Wang qing Lang xingchun Huang xinghong Jiang Qiang Jing School of Naval Architecture Ocean and Civil EngineeringShanghai Jiao Tong UniversityShanghai200240China Key Laboratory of Road and Bridge Detection and Maintenance Technology of Zhejiang Province Hangzhou311305China Zhejiang Scientific Research Institute of Transport Hangzhou310023China State Key Laboratory of Coal Mine Dynamics and Control Chongqing UniversityChongqing400044China Hong Kong-Zhuhai-Macao Bridge Authority Zhuhai519060China

Structural Health Monitoring(SHM)systems have become a crucial tool for the operational management of long *** immersed tunnels exposed to both traffic loads and the effects of the marine environment,efficiently identifying abnormal conditions from the extensive unannotated SHM data presents a significant *** study proposed amodel-based approach for anomaly detection and conducted validation and comparative analysis of two distinct temporal predictive models using SHM data from a real immersed ***,a dynamic predictive model-based anomaly detectionmethod is proposed,which utilizes a rolling time window for modeling to achieve dynamic *** the assumption of temporal data similarity,an interval prediction value deviation was employed to determine the abnormality of the ***,dynamic predictive models were constructed based on the Autoregressive Integrated Moving Average(ARIMA)and Long Short-Term Memory(LSTM)*** hyperparameters of these models were optimized and selected using monitoring data from the immersed tunnel,yielding viable static and dynamic predictive ***,the models were applied within the same segment of SHM data,to validate the effectiveness of the anomaly detection approach based on dynamic predictive modeling.A detailed comparative analysis discusses the discrepancies in temporal anomaly detection between the ARIMA-and LSTM-based *** results demonstrated that the dynamic predictive modelbased anomaly detection approach was effective for dealing with unannotated SHM *** a comparison between ARIMA and LSTM,it was found that ARIMA demonstrated higher modeling efficiency,rendering it suitable for short-term *** contrast,the LSTM model exhibited greater capacity to capture long-term performance trends and enhanced early warning capabilities,thereby resulting in superior overall performance.

关键词： Anomaly detection dynamic predictive model structural health monitoring immersed tunnel LSTM ARIMA

来源：

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

Combined effects of ultrasonic vibration and FeCoNiCrCu coating on interfacial microstructure and mechanical properties of Al/Mg bimetal by compound casting

引用

China Foundry 2024年第5期21卷 588-598页

作者： Yuan-cai Xu Wen-ming Jiang qing-qing Li Ling-hui Yu Xiao-peng Yu Zi-tian Fan State Key Laboratory of Materials Processing and Die&Mould Technology School of Materials Science and EngineeringHuazhong University of Science and TechnologyWuhan 430074China

In this work,a new treatment method combining ultrasonic vibration with FeCoNiCrCu high entropy alloy(HEA)coating was used to prepared Al/Mg bimetal through the lost foam compound *** effects of composite treatment involving ultrasonic vibration and HEA coating on interfacial microstructure and mechanical properties of Al/Mg bimetal were *** demonstrate that the interface thickness of the Al/Mg bimetal with composite treatment significantly decreases to only 26.99%of the thickness observed in the untreated Al/Mg *** HEA coating hinders the diffusion between Al and Mg,resulting the significant reduction in Al/Mg intermetallic compounds in the *** Al/Mg bimetal interface with composite treatment is composed of Al_(3)Mg_(2)and Mg_(2)Si/AlxFeCoNiCrCu+FeCoNiCrCu/δ-Mg+Al_(12)Mg_(17)eutectic *** interface resulting from the composite treatment has a lower hardness than that without *** acoustic cavitation and acoustic streaming effects generated by ultrasonic vibration promote the diffusion of Al elements within the HEA coating,resulting in a significant improvement in the metallurgical bonding quality on the Mg *** fracture position shifts from the Mg side of the Al/Mg bimetal only with HEA coating to the Al side with composite *** shear strength of the Al/Mg bimetal increases from 32.16 MPa without treatment to 63.44 MPa with ultrasonic vibration and HEA coating,increasing by 97.26%.

关键词： ultrasonic vibration FeCoNiCrCu HEA coating Al/Mg bimetal interfacial microstructure shear strength compound casting

来源：

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

Significantly Enhanced Energy Storage Performances of PEI-based Composites Utilizing Surface Functionalized ZrO_(2) Nanoparticles for High-Temperature Application

引用

Chinese Journal of Polymer Science 2024年第3期42卷 322-332,I0006页

作者： qing-qing Liu Qiu-Hao Lin Xiao-Dong Qi Nan Zhang Ting Huang Jing-Hui Yang Yong Wang School of Chemistry Southwest Jiaotong UniversityChengdu 610031China Key Laboratory of Advanced Technologies of Materials Ministry of Education of ChinaSouthwest Jiaotong UniversityChengdu 610031China

Polymer dielectrics with a high energy density and an available energy storage capacity have been playing an important role in advanced electronics and power systems. Nevertheless, the use of polymer dielectrics in harsh environments is limited by their low energy density at high temperatures. Herein, zirconium dioxide(ZrO_(2)) nanoparticles were decorated with amino group utilizing 4,4-methylenebis(phenyl isocyanate)(AMEO) and successfully incorporated into polyetherimide(PEI) matrix. The dielectric properties, breakdown strength, and energy storage performances of PEI/ZrO_(2)-AMEO nanocomposites were investigated from 25 ℃ to 150 ℃. It is found that the combination of moderate bandgap ZrO_(2) with modest dielectric constant and polar groups at interface with deep trap can offer an available strategy to simultaneously increase the dielectric constant and breakdown strength of polymer dielectrics. As a result, the composites containing ZrO_(2)-AMEO exhibit excellent energy storage performance at elevated temperatures. Specially, the PEI-based composites with 3 vol% ZrO_(2)-AMEO display a maximum discharged energy density(U_(d)) of 3.1 J/cm^(3) at 150 ℃, presenting 90% higher than that of neat PEI. This study may help to better develop the polymer-based dielectric composite applied at elevated temperatures.

关键词： Polyetherimide High temperature dielectric ZrO_(2) Interface

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

All types of base conversions allowed by base editors

引用

Science China(Life Sciences) 2024年第2期67卷 431-433页

作者： Shun-qing Liang Wen Xue RNA Therapeutics Institute UMass Chan Medical SchoolWorcester 01655USA Department of Molecular Cell and Cancer BiologyUMass Chan Medical SchoolWorcester 01655USA Department of Molecular Medicine UMass Chan Medical SchoolWorcester 01655USA Li Weibo Institute for Rare Diseases Research UMass Chan Medical SchoolWorcester 01655USA

Base editors(BEs) hold great promise as tools for introducing single-base-pair changes in both basic research and therapeutic applications(Rees and Liu,2018).Base editors are composed of a Cas9 nickase fused to a DNA-modifying enzyme,which chemically modifies nucleobases within a specific targeting window near the Cas9-binding site.

关键词： base bases allowed

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Lightweight Malicious Code Classification Method Based on Improved Squeeze Net

引用

Computers, Materials & Continua 2024年第1期78卷 551-567页

作者： Li Li Youran Kong qing Zhang School of Computer and Control Engineering Northeast Forestry UniversityHarbin150040China

With the growth of the Internet,more and more business is being done online,for example,online offices,online education and so *** this makes people’s lives more convenient,it also increases the risk of the network being attacked by malicious ***,it is important to identify malicious codes on computer systems ***,most of the existing malicious code detection methods have two problems:(1)The ability of the model to extract features is weak,resulting in poor model performance.(2)The large scale of model data leads to difficulties deploying on devices with limited ***,this paper proposes a lightweight malicious code identification model Lightweight Malicious Code Classification Method Based on Improved SqueezeNet(LCMISNet).In this paper,the MFire lightweight feature extraction module is constructed by proposing a feature slicing module and a multi-size depthwise separable convolution *** feature slicing module reduces the number of parameters by grouping *** multi-size depthwise separable convolution module reduces the number of parameters and enhances the feature extraction capability by replacing the standard convolution with depthwise separable convolution with different convolution kernel *** addition,this paper also proposes a feature splicing module to connect the MFire lightweight feature extraction module based on the feature reuse and constructs the lightweight model *** malicious code recognition accuracy of LCMISNet on the BIG 2015 dataset and the Malimg dataset reaches 98.90% and 99.58%,*** proves that LCMISNet has a powerful malicious code recognition *** addition,compared with other network models,LCMISNet has better performance,and a lower number of parameters and computations.

关键词： Lightweight neural network malicious code classification feature slicing feature splicing multi-size depthwise separable convolution

来源：

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

Super P and MoO_(2)/MoS_(2)co-doped gradient nanofiber membrane as multi-functional separator for lithium–sulfur batteries

引用

Rare Metals 2024年第9期43卷 4263-4273页

作者： xin Liang Dong-qing Zhao Qian-Qian Huang Sheng Liang Li-Li Wang Lei Hu Ling-Li Liu Kun-Hong Hu Chong-Hai Deng Sheng Cheng Er-Tao Zhu Hua-Xia Deng School of Energy Materials and Chemical Engineering LIB Technology Center of Anhui ProvinceHefei UniversityHefei 230601China Instrumental Analysis Centre Hefei University of TechnologyHefei 230009China Hefei Youngy Energy Materials Co. Ltd.Hefei 230000China Department of Modern Mechanics University of Science and Technology of ChinaHefei 230026China

Lithium-sulfur battery is one of the most promising battery systems for industrialization due to its high theoretical specific capacity and high energy ***,the"shuttle effect"has restrained the advancement of lithium-sulfur *** this work,a gradient-structured nanofiber membrane with pure gelatin on one side and Super P-MoO_(2)/MoS_(2)-gelatin on the other side was created using a multi-step electrostatic spinning technique,which was applied for multi-functional separator for lithium-sulfur *** pure gelatin layer facing the anode side primarily homogenizes the lithium flux,whereas the Super P-MoO_(2)/MoS_(2)-gelatin layer facing the cathode side primarily adsorbs polysulfides by physical and chemical adsorption and enhancing polysulfide conversion *** findings demonstrate that even after 150 cycles at 0.2C,the lithium-sulfur battery can still sustain a discharge-specific capacity of 572.3 mAh·g^(-1).When used with Li||Li symmetric batteries,it has a cycle life of more than 1200 *** commercialization of lithium-sulfur batteries is given a fresh idea by this straightforward preparation technique.

关键词： MoO_(2)/MoS_(2) Nanofiber Membrane Li-S battery

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

An Image Fingerprint and Attention Mechanism Based Load Estimation Algorithm for Electric Power System

引用

Computer Modeling in Engineering & Sciences 2024年第7期140卷 577-591页

作者： qing Zhu Linlin Gu Huijie Lin Electricity Technology Branch Nari Technology Co.Ltd.Nanjing211106China NARI-TECH Nanjing Control Systems Co. Ltd.Nanjing211106China

With the rapid development of electric power systems,load estimation plays an important role in system operation and ***,load estimation techniques contain traditional,time series,regression analysis-based,and machine learning-based *** the machine learning-based method can lead to better performance,in this paper,a deep learning-based load estimation algorithm using image fingerprint and attention mechanism is ***,an image fingerprint construction is proposed for training *** the data preprocessing,the training data matrix is constructed by the cyclic shift and cubic spline ***,the linear mapping and the gray-color transformation method are proposed to form the color image ***,a convolutional neural network(CNN)combined with an attentionmechanism is proposed for training performance *** last,an experiment is carried out to evaluate the estimation *** with the support vector machine method,CNN method and long short-term memory method,the proposed algorithm has the best load estimation performance.

关键词： Load estimation deep learning attention mechanism image fingerprint construction

来源：

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

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

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：