检索结果-南通市图书馆

Low-Brightness Object Recognition Based on Deep Learning

Computers, Materials & Continua 2024年第5期79卷 1757-1773页

作者： Shu-Yin Chiang Ting-Yu lin Department of Information and Telecommunications Engineering Ming Chuan UniversityTaoyuan City333Taiwan

This research focuses on addressing the challenges associated with image detection in low-light environments,particularly by applying artificial intelligence techniques to machine vision and object recognition *** primary goal is to tackle issues related to recognizing objects with low brightness *** this study,the Intel RealSense Lidar Camera L515 is used to simultaneously capture color information and 16-bit depth information *** detection scenarios are categorized into normal brightness and low brightness *** the system determines a normal brightness environment,normal brightness images are recognized using deep learning *** low-brightness situations,three methods are proposed for *** first method is the SegmentationwithDepth image(SD)methodwhich involves segmenting the depth image,creating amask from the segmented depth image,mapping the obtained mask onto the true color(RGB)image to obtain a backgroundreduced RGB image,and recognizing the segmented *** second method is theHDVmethod(hue,depth,value)which combines RGB images converted to HSV images(hue,saturation,value)with depth images D to form HDV images for *** third method is the HSD(hue,saturation,depth)method which similarly combines RGB images converted to HSV images with depth images D to form HSD images for *** experimental results,in normal brightness environments,the average recognition rate obtained using image recognition methods is 91%.For low-brightness environments,using the SD method with original images for training and segmented images for recognition achieves an average recognition rate of over 82%.TheHDVmethod achieves an average recognition rate of over 70%,while the HSD method achieves an average recognition rate of over 84%.The HSD method allows for a quick and convenient low-light object recognition *** research outcome can be applied to nighttime surveillance systems or nighttime road safety systems

关键词： Low-brightness depth image image segmentation image recognition HDV HSD

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

Cigarette Use and Secondhand Smoke Exposure Among Secondary School Students—China,2023

引用

China CDC weekly 2024年第22期6卷 509-515页

作者： Xinying Zeng Shiwei Liu lin Xiao Tobacco Control Office Chinese Center for Disease Control and PreventionBeijingChina

What is already known about this topic?In 2021,the prevalence of experimental and current cigarette use among secondary school students in China stood at 16.7%and 4.7%,***,39.9%of these students were exposed to secondhand smoke at *** is added by this report?In comparison to 2021,the prevalence of current cigarette use remained unchanged at 4.2%in 2023,whereas experimental use declined to 13.7%.Notably,rates were significantly higher among vocational senior high school(VSHS)students relative to their peers in senior high school(SHS)and junior high school(JHS).Furthermore,exposure to secondhand smoke in schools decreased to 35.4%in 2023 from previously recorded levels,with more pronounced reductions observed in JHS and SHS populations and no notable change among VSHS *** are the implications for public health practice?Targeted tobacco control policies are imperative for secondary school students,including the establishment of smoke-free school ***,it is crucial to pay close attention to the needs of VSHS students.

关键词： smoke unchanged senior

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

Neuronomodulation of Excitable Neurons

引用

Neuroscience Bulletin 2024年第1期40卷 103-112页

作者： Yizhang Chen lin Xiao Jian Qiu Institute of Neuroscience Second Military Medical UniversityShanghai 200433China Institute for Brain Research and Rehabilitation Key Laboratory of BrainCognition and Education Sciences of Ministry of EducationSouth China Normal UniversityGuangzhou 510631China Department of Chemical Physiology and Biochemistry Oregon Health and Science UniversityPortlandOR 97239USA

Neuronomodulation refers to the modulation of neural conduction and synaptic transmission(i.e.,the conduction process involved in synaptic transmission)of excitable neurons via changes in the membrane potential in response to chemical substances,from spillover neuro-transmitters to paracrine or endocrine hormones circulating in the *** can be direct or indirect,depending on the transduction pathways from the ligand binding site to the ion pore,either on the same molecule,*** ion channel,or through an intermediate step on different *** major players in direct neurono-modulation are ligand-gated or voltage-gated ion *** key process of direct neuronomodulation is the binding and chemoactivation of ligand-gated or voltage-gated ion channels,either orthosterically or allosterically,by various *** neuronomodulation involves metabotropic receptor-mediated slow potentials,where steroid hormones,cytokines,and chemokines can implement these *** neuronomodulation is of great significance for understanding the physiological mechanisms of brain function,and the occurrence and treatment of diseases.

关键词： Neuron Membrane potential Excitability Chemoactivation Neuronomodulation

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

An Efficient Local Radial Basis Function Method for Image Segmentation Based on the Chan-Vese Model

引用

Computer Modeling in Engineering & Sciences 2024年第4期139卷 1119-1134页

作者： Shupeng Qiu Chujin lin Wei Zhao School of Mathematics and Statistics Guangdong University of TechnologyGuangzhou510520China

In this paper,we consider the Chan–Vese(C-V)model for image segmentation and obtain its numerical solution accurately and *** this purpose,we present a local radial basis function method based on a Gaussian kernel(GA-LRBF)for spatial *** to the standard radial basis functionmethod,this approach consumes less CPU time and maintains good stability because it uses only a small subset of points in the whole computational ***,since the Gaussian function has the property of dimensional separation,the GA-LRBF method is suitable for dealing with isotropic ***,a numerical scheme that couples GA-LRBF with the fourth-order Runge–Kutta method is applied to the C-V model,and a comparison of some numerical results demonstrates that this scheme achieves much more reliable image segmentation.

关键词： Image segmentation Chan–Vese model local radial basis functionmethod Gaussian kernel Runge–Kuttamethod

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

ConvNeXt-UperNet-Based Deep Learning Model for Road Extraction from High-Resolution Remote Sensing Images

引用

Computers, Materials & Continua 2024年第8期80卷 1907-1925页

作者： Jing Wang Chen Zhang Tianwen lin Geographic Information and Tourism College Chuzhou UniversityChuzhou239000China Anhui Province Key Laboratory of Physical Geographic Environment Chuzhou UniversityChuzhou239000China

When existing deep learning models are used for road extraction tasks from high-resolution images,they are easily affected by noise factors such as tree and building occlusion and complex backgrounds,resulting in incomplete road extraction and low *** propose the introduction of spatial and channel attention modules to the convolutional neural network ***,ConvNeXt is used as the backbone network,which cooperates with the perceptual analysis network UPerNet,retains the detection head of the semantic segmentation,and builds a new model ConvNeXt-UPerNet to suppress noise *** on the open-source DeepGlobe and CHN6-CUG datasets and introducing the DiceLoss on the basis of CrossEntropyLoss solves the problem of positive and negative sample *** results show that the new network model can achieve the following performance on the DeepGlobe dataset:79.40%for precision(Pre),97.93% for accuracy(Acc),69.28% for intersection over union(IoU),and 83.56% for mean intersection over union(MIoU).On the CHN6-CUG dataset,the model achieves the respective values of 78.17%for Pre,97.63%for Acc,65.4% for IoU,and 81.46% for *** with other network models,the fused ConvNeXt-UPerNet model can extract road information better when faced with the influence of noise contained in high-resolution remote sensing *** also achieves multiscale image feature information with unified perception,ultimately improving the generalization ability of deep learning technology in extracting complex roads from high-resolution remote sensing images.

关键词： Deep learning semantic segmentation remote sensing imagery road extraction

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

Demixing microwave signals using system-on-chip photonic processor

引用

Light(Science & Applications) 2024年第3期13卷 399-401页

作者： Sheng Gao Chu Wu Xing lin Department of Electronic Engineering Tsinghua University100084 BeijingChina Beijing National Research Center for Information Science and Technology Tsinghua University100084 BeijingChina

The integrated photonic processor,co-packaged with electronic peripherals,is proposed for blind source separation of microwave signals,which separates signal-of-interest from dynamic interference with real-time adapta... 详细信息

关键词： processor microwave mixing

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

Electrodeposition of rare refractory metals in low-temperature ionic liquids

引用

Rare Metals 2024年第10期43卷 4921-4933页

作者： lin-lin Wang Han-Dong Jiao Rui Yuan Le-Yang Li Man-Peng lin Rui-Yang Sun Jiu-San Xiao Shu-Qiang Jiao Institute of Advanced Structure Technology Beijing Institute of Technology State Key Laboratory of Advanced Metallurgy University of Science and Technology Beijing

Rare refractory metals(RRMs) play a significant role in fundamental industries, including electronics,chemical industry, machinery, etc., and future advanced fields, such as aerospace and superconductivity. However,the traditional production processes of RRMs based on high-temperature thermal reduction cannot meet the requirements of low-energy consumption. This dilemma could be addressed efficiently by using a low-temperature electrodeposition strategy in ionic liquids(ILs). This review summarizes a panoramic view of the latest developments on the electrodeposition of RRMs in ILs after a brief review on the current industrial production methods of RRMs. Based on this, the electrochemical mechanism occurring at the cathode during the electrodeposition process of RRMs in different electrolytes and under different conditions is thoroughly discussed, because it is crucial for the successful production of pure RRMs. In addition, this review not only analyses the main challenges that hinder the industrial application of the electrodeposition of RRMs in ILs, but also proposes corresponding solutions. We hope this review can provide a valuable guidance for the fundamental research and industrial development of lowtemperature electrodeposition of RRMs.

关键词： Chemical industry

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

DMF-scMT-seq linking methylome and transcriptome within single cells with digital microfluidics

引用

Science China Chemistry 2024年第6期67卷 2070-2078页

作者： Xing Xu Xi Zeng Xin lin Shiyan lin Shanshan Liang Tian Tian Rui Su Jia Song Chaoyong Yang Collaborative Innovation Center of Chemistry for Energy Materials The MOE Key Laboratory of Spectrochemical Analysis and InstrumentationState Key Laboratory of Physical Chemistry of Solid SurfacesDepartment of Chemical BiologyCollege of Chemistry and Chemical EngineeringThe First Affiliated Hospital of Xiamen UniversityXiamen UniversityXiamen361005China Institute of Molecular Medicine Renji HospitalShanghai Jiao Tong University School of MedicineShanghai200127China Chemistry and Materials Science College Shanghai Normal UniversityShanghai200234China Chemistry and Biomedicine Innovation Center(ChemBIC) School of Chemistry and Chemical EngineeringNanjing UniversityNanjing210023China

Single-cell joint analysis of methylome and transcriptome reveals how the methylation regulates the transcriptional ***,traditional bench-top protocols for single-cell DNA methylation and RNA transcription co-detection are laborintensive,cost-ineffective and ***,we establish the DMF-sc MT-seq,a highly-efficient and cost-effective method to simultaneously analyze single-cell DNA methylation and transcriptional activity based on digital *** MT-seq automates the workflow of single-cell isolation,cellular hypotonic lysis,nucleic acid separation and methylome/transcriptome library construction in a contactless and addressable *** system ensures high accuracy(R>0.85),high gene detection ability(14,697 genes per cell at 4 million sequencing depth),and high CpG coverage(677,198 CpG sites per cell at 1million sequencing depth).By using DMF-sc MT-seq,the relationship of DNA methylation and RNA transcription under different genomic contexts is *** further apply DMF-sc MT-seq to study the dynamics of transcription regulation with methylation-inhibiting anti-tumor Decitabine,and identify the methylated promoter/gene body driven genes in response to Decitabine ***-sc MT-seq facilitates the construction of the correlation of DNA methylation and transcriptional activity at the single-cell level in a flexible,sensitive and accurate way,which is anticipated to be a powerful tool in studying single-cell biological systems.

关键词： single-cell analysis digital microfluidics methylome sequencing transcriptome sequencing

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

Machine learning model based on non-convex penalized huberized-SVM

引用

Journal of Electronic Science and Technology 2024年第1期22卷 81-94页

作者： Peng Wang Ji Guo lin-Feng Li School of Finance and Economics Xizang Minzu UniversityXianyang712082China Research Center for Quality Development of Xizang Special Industries Xianyang712082China School of Computer Science and Technology Xinjiang UniversityUrumqi830017China

The support vector machine(SVM)is a classical machine learning *** the hinge loss and least absolute shrinkage and selection operator(LASSO)penalty are usually used in traditional ***,the hinge loss is not differentiable,and the LASSO penalty does not have the Oracle *** this paper,the huberized loss is combined with non-convex penalties to obtain a model that has the advantages of both the computational simplicity and the Oracle property,contributing to higher accuracy than traditional *** is experimentally demonstrated that the two non-convex huberized-SVM methods,smoothly clipped absolute deviation huberized-SVM(SCAD-HSVM)and minimax concave penalty huberized-SVM(MCP-HSVM),outperform the traditional SVM method in terms of the prediction accuracy and classifier *** are also superior in terms of variable selection,especially when there is a high linear correlation between the *** they are applied to the prediction of listed companies,the variables that can affect and predict financial distress are accurately filtered *** all the indicators,the indicators per share have the greatest influence while those of solvency have the weakest *** companies can assess the financial situation with the indicators screened by our algorithm and make an early warning of their possible financial distress in advance with higher precision.

关键词： Huberized loss Machine learning Non-convex penalties Support vector machine(SVM)

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

Synergistic Effects of Bay of Bengal Tropical Cyclones and Tibetan Plateau Vortices on Water Vapor Transport over the Tibetan Plateau in Early Summer

引用

Journal of Meteorological Research 2024年第2期38卷 383-398页

作者： Jialu lin Ying LI Beiyao LIU Pengchao AN State Key Laboratory of Severe Weather Chinese Academy of Meteorological SciencesChina Meteorological AdministrationBeijing 100081 University of Chinese Academy of Sciences Beijing 100049 Department of Atmospheric and Oceanic Sciences and Institute of Atmospheric Sciences Fudan UniversityShanghai 200433

The Bay of Bengal(BoB)tropical cyclones(TCs)and the Tibetan Plateau vortices(TPVs)are two crucial weather systems influencing the Tibetan Plateau(TP).Their synergistic effects can lead to widespread heavy precipitation events on the *** this study,we employ the Hybrid Single-Particle Lagrangian Integrated Trajectory(HYSPLIT)model to track the trajectory of water vapor transport during three large-scale precipitation events on the TP under the combined influence of BoB TCs and *** results indicate that low-level water vapor from the BoB under the influence of BoB TCs was cyclonically entangled into the cyclonic circulation,lifted and transported northward by southwesterly flow to the southeastern part of the TP,which contributes to the moistening of the entire troposphere ***,convergence of the cyclonic circulation of the TPVs on the northern TP further transports water vapor collected in the southeastern TP northward,conducive to the maintenance and development of precipitation systems,thus inducing widespread heavy precipitation events over the TP.

关键词： Bay of Bengal(BoB) tropical cyclones(TCs) Tibetan Plateau vortices(TPVs) trajectory tracing water vapor transport

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

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：