检索结果-南通市图书馆

Text-Image Feature Fine-Grained Learning for Joint Multimodal Aspect-Based Sentiment Analysis

Computers, Materials & Continua 2025年第1期82卷 279-305页

作者： tianzhi zhang Gang Zhou Shuang zhang Shunhang Li Yepeng Sun Qiankun Pi Shuo Liu School of Data and Target Engineering Information Engineering UniversityZhengzhou450001China Information Engineering Department Liaoning Provincial College of CommunicationsShenyang110122China School of Computer and Artificial Intelligence Zhengzhou UniversityZhengzhou450000China

Joint Multimodal Aspect-based Sentiment Analysis(JMASA)is a significant task in the research of multimodal fine-grained sentiment analysis,which combines two subtasks:Multimodal Aspect Term Extraction(MATE)and Multimodal Aspect-oriented Sentiment Classification(MASC).Currently,most existing models for JMASA only perform text and image feature encoding from a basic level,but often neglect the in-depth analysis of unimodal intrinsic features,which may lead to the low accuracy of aspect term extraction and the poor ability of sentiment prediction due to the insufficient learning of intra-modal *** this problem,we propose a Text-Image Feature Fine-grained Learning(TIFFL)model for ***,we construct an enhanced adjacency matrix of word dependencies and adopt graph convolutional network to learn the syntactic structure features for text,which addresses the context interference problem of identifying different aspect ***,the adjective-noun pairs extracted from image are introduced to enable the semantic representation of visual features more intuitive,which addresses the ambiguous semantic extraction problem during image feature ***,the model performance of aspect term extraction and sentiment polarity prediction can be further optimized and *** on two Twitter benchmark datasets demonstrate that TIFFL achieves competitive results for JMASA,MATE and MASC,thus validating the effectiveness of our proposed methods.

关键词： Multimodal sentiment analysis aspect-based sentiment analysis feature fine-grained learning graph convolutional network adjective-noun pairs

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

Histopathologic and Immunohistochemical Analysis of 66 Cases of Gastrointestinal Stromal Tumor

引用

Journal of Biosciences and Medicines 2023年第6期11卷 140-147页

作者： tianzhi zhang Chao Liang Danting Su Department of Pathology The Seventh Affiliated Hospital of Sun Yat-sen University Shenzhen China

Background and Objective: To investigate the histopathological characteristics and immunohistochemistry of gastrointestinal stromal tumors (GIST). Immunohistochemistry (IHC) refers to the expression and meaning of CD117, DOG-1, CD34. Methods: Sixty-six gastrointestinal stromal tumor (GIST) samples with complete clinical data and definite clinicopathological diagnosis were collected from the Seventh Affiliated Hospital of Sun Yat-sen University from January 2019 to December 2022. Retrospective analysis was performed on the pathological data of 66 patients with GIST, and the histopathology and IHC were analyzed and summarized. Results: Among the 66 cases, 46, 14, 1, 5 were found in the stomach, small intestine, large intestine, and gastroenteral area. There were 45 cases (97%), 11 cases (79%), 1 case (100%), 5 cases (100%) in order of fusiform cell type. There were 1 case (3%), 2 cases (14%), 0 case, 0 case of upper dermatiform;Mixed type in 0 case, 1 case (7%), 0 case, 0 case;CD117 positive 66 cases (100%), DOG-1 positive 66 cases (100%), CD34 positive 61 cases (92%), CD117 and/or CD34 negative 5 cases (8%);CD34, CD117 and DOG-1 were negative simultaneously in 0 case. 19 cases (28%) were positive for SMA and 7 cases (11%) were positive for S-100. Conclusion: Fusiform cell type is the common type of GIST, followed by epithelioid type and mixed type, but the tumor sites are different, and the comparison cases are not completely the same. CD117, DOG-1 and CD34 are high surface in GIST, and the combination of SMA, S-100 and histomorphology can be used to diagnose most GIST.

关键词： Gastrointestinal Stromal Tumor Immunological Organization CD117 DOG-1 CD34

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

Luminescence of Unusual Bismuth in Barium Borates (BaB_8O_13:Bi)

引用

Journal of Materials Science & Technology 1999年第3期15卷 281-282页

作者： Qinghua ZENG tianzhi zhang Zhiwu PEI and Qiang SU(Laboratory of Rare Earth Chemistry and Physics, Changchun Institute of Applied Chemistry, Chinese Academy of Sciences, Changchun 130022, China) Laboratory of Rare Earth Chemistry and Physics Changchun Institute of Applied Chemistry Chinese Academy of Sciences Changchun 130022 China

The luminescence of unusual divalent bismuth (Bi2+) in BaB8O13 is reported. The emission band with maximum peak at 592 nm corresponds to the 2P3/2→2P1/2 transition of Bi2+ in the matrix and the excitation spectrum with two bands peaked at 470 and 580 nm respectively corresponds to two split crystal-field levels of 2P3/2 state. The small Stokes shift (~350 cm-1) reflects the rigid structure of the host for the Bi2+ ions

关键词： BaB8O13

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

Clinicopathologic Characteristics of Differentiated Thyroid Carcinoma in Children and Adolescents

引用

Advances in Bioscience and Biotechnology 2023年第4期14卷 143-150页

作者： tianzhi zhang Chao Liang Guangchang Shan Danting Su Department of Pathology The Seventh Affiliated Hospital of Sun Yat-sen University Shenzhen China

Objective: To investigate the clinicopathologic features of differentiated thyroid carcinoma in children and adolescents. Methods: The clinical data of 7 children and adolescents with differentiated thyroid carcinoma were retrospectively analyzed, and the clinicopathologic features of differentiated thyroid carcinoma were analyzed by gender, tumor size and BRAF mutation. Results: There were 7 cases of thyroid papillary carcinoma. The mean age of patients was (18.71 ± 2.75), and the mean tumor diameter was (2.4 ± 1.04) cm. Lymph node metastasis rate was 100% (7/7). In children and adolescents, the lesion volume was larger, membrane invasion and vascular cancer thrombus were more likely to occur, BRAF mutation was less common, and the difference was statistically significant. Conclusion: Children and adolescents with differentiated thyroid carcinoma are more aggressive and prone to membrane invasion and lymph node metastasis;BRAF mutation is less common than in adults.

关键词： Children and Adolescents Thyroid Papillary Carcinoma Clinicopathological Features BRAF Mutation

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

Tubular Carcinoma of the Breast: A Clinicopathological Analysis of Two Cases

引用

Advances in Bioscience and Biotechnology 2022年第11期13卷 499-506页

作者： tianzhi zhang Danting Su Chao Liang Jianxian Huang Department of Pathology The Seventh Affiliated Hospital of Sun Yat-sen University Shenzhen China

Tubular Carcinoma (TC) of the breast, also known as tubular carcinoma or well-differentiated adenocarcinoma, is defined as a special type of breast cancer consisting of well-differentiated tubular structures with excellent prognosis by WHO (2019) pathological and genetic classification of breast neoplasms. Two cases of breast tubular carcinoma admitted to our hospital were reported. The relevant literature was reviewed and the clinical features, histological morphology (microscopic features and differential diagnosis), molecular changes and clinical prognosis were summarized.

关键词： TC Clinical Pathology Differential Diagnosis Prognosis

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

泸州和安岳枳壳中的低极性化学成分

引用

应用与环境生物学报 2019年第2期25卷 432-437页

作者：罗禹张添植辜晓英税丕先西南医科大学药学院泸州646000 泸州宇龙枳壳枳实研究院泸州646000

为分析比较泸州和安岳两地产枳壳中的低极性成分特别是脂肪酸和挥发油的组成,分别采用有机溶剂提取法和水蒸气蒸馏法提取泸州和安岳枳壳中的低极性成分,运用气质联用技术进行成分分析,所得成分的质谱数据经数据库检索鉴定,并应用面积归... 详细信息

为分析比较泸州和安岳两地产枳壳中的低极性成分特别是脂肪酸和挥发油的组成,分别采用有机溶剂提取法和水蒸气蒸馏法提取泸州和安岳枳壳中的低极性成分,运用气质联用技术进行成分分析,所得成分的质谱数据经数据库检索鉴定,并应用面积归一化法计算各成分的相对含量.结果显示:(1)以石油醚为溶剂提取枳壳浸膏,泸州枳壳鉴定出61种化学成分,安岳枳壳鉴定出18种化学成分,成分以脂肪酸、烷烃为主,两种枳壳中含量最高的成分均为十八碳二烯酸;(2)以水蒸气蒸馏法提取枳壳挥发油,泸州枳壳鉴定出65种化学成分,安岳枳壳鉴定出81种化学成分,以小分子烯、醇、萜类物质为主,两种枳壳中含量最高的成分均为d-柠檬烯.本研究表明不同方法提取出的化学成分种类差异明显;泸州和安岳两地产两种枳壳的脂肪酸组成具有较大的差异;挥发性成分种类相似,其含量组成有一定差异;结果可为四川地区枳壳的开发利用提供数据基础.(表3参20)

关键词：枳壳低极性成分脂肪酸挥发油气相色谱-质谱联用

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

中国原生艺术界的新人——李昌胜

引用

上海艺术家 2015年第5期 42-43页

作者：张天志

李昌胜,艺术界一个很陌生的名字,然而就是这个默默无闻的＂小人物＂的作品却深深地打动了我,令我对他十分敬慕!认识李昌胜出于一种机缘。2014年5月初,我接受《大都市》杂志的专访。在与记者的闲聊中得知,她的一位朋友的弟弟（李昌胜）... 详细信息

李昌胜,艺术界一个很陌生的名字,然而就是这个默默无闻的＂小人物＂的作品却深深地打动了我,令我对他十分敬慕!认识李昌胜出于一种机缘。2014年5月初,我接受《大都市》杂志的专访。在与记者的闲聊中得知,她的一位朋友的弟弟（李昌胜）爱画画,作品有些叛经离道的感觉。

关键词：李昌超现实主义自闭症艺术天赋达利艺术语言河北石家庄市视觉冲击瑞士洛桑性格内向

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

基于文本和图像门控融合机制的多模态方面级情感分析

引用

计算机科学 2024年第9期51卷 242-249页

作者：张添植周刚刘洪波刘铄陈静战略支援部队信息工程大学郑州450001 数学工程与先进计算国家重点实验室郑州450001

多模态方面级情感分析是多模态情感分析领域的一项新兴任务,旨在对给定的方面实体在文本和图像中所体现的情感进行识别。尽管多模态方面级情感分析研究近年来取得了突破性的进展,但是现有的模型在多模态特征融合阶段大都仅采用简单的拼... 详细信息

多模态方面级情感分析是多模态情感分析领域的一项新兴任务,旨在对给定的方面实体在文本和图像中所体现的情感进行识别。尽管多模态方面级情感分析研究近年来取得了突破性的进展,但是现有的模型在多模态特征融合阶段大都仅采用简单的拼接方法,而没有考虑图像中是否存在与文本语义不相关的信息,这在一定程度上可能会为模型引入额外的噪声。为了解决上述问题,提出了一种基于文本和图像门控融合机制的多模态方面级情感分析模型(TIGFM)。该模型在文本和图像进行交互的同时引入了从数据集图像中提取的形容词-名词对(ANPs),并将其中形容词的加权作为图像辅助信息;此外,在特征融合阶段,通过构建一种动态控制图像和图像辅助信息输入的门控机制实现多模态特征融合。实验结果表明,TIGFM模型在两个基于Twitter的数据集上取得了具有竞争力的结果,进而验证了所提方法的有效性。

关键词：多模态方面级情感分析门控融合机制形容词-名词对图像辅助信息语义相关性

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

Method for Estimating the State of Health of Lithium-ion Batteries Based on Differential Thermal Voltammetry and Sparrow Search Algorithm-Elman Neural Network

引用

Energy Engineering 2025年第1期122卷 203-220页

作者： Yu zhang Daoyu zhang TiezhouWu School of Electrical and Electronic Engineering Hubei University of TechnologyWuhan430068China

Precisely estimating the state of health(SOH)of lithium-ion batteries is essential for battery management systems(BMS),as it plays a key role in ensuring the safe and reliable operation of battery ***,current SOH estimation methods often overlook the valuable temperature information that can effectively characterize battery aging during capacity ***,the Elman neural network,which is commonly employed for SOH estimation,exhibits several drawbacks,including slow training speed,a tendency to become trapped in local minima,and the initialization of weights and thresholds using pseudo-random numbers,leading to unstable model *** address these issues,this study addresses the challenge of precise and effective SOH detection by proposing a method for estimating the SOH of lithium-ion batteries based on differential thermal voltammetry(DTV)and an SSA-Elman neural ***,two health features(HFs)considering temperature factors and battery voltage are extracted fromthe differential thermal voltammetry curves and incremental capacity ***,the Sparrow Search Algorithm(SSA)is employed to optimize the initial weights and thresholds of the Elman neural network,forming the SSA-Elman neural network *** validate the performance,various neural networks,including the proposed SSA-Elman network,are tested using the Oxford battery aging *** experimental results demonstrate that the method developed in this study achieves superior accuracy and robustness,with a mean absolute error(MAE)of less than 0.9%and a rootmean square error(RMSE)below 1.4%.

关键词： Lithium-ion battery state of health differential thermal voltammetry Sparrow Search Algorithm

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

A Lightweight Multiscale Feature Fusion Network for Solar Cell Defect Detection

引用

Computers, Materials & Continua 2025年第1期82卷 521-542页

作者： Xiaoyun Chen Lanyao zhang Xiaoling Chen Yigang Cen Linna zhang Fugui zhang School of Mechanical Engineering Guizhou UniversityGuiyang550025China School of Computer Science and Technology Beijing Jiaotong UniversityBeijing100044China

Solar cell defect detection is crucial for quality inspection in photovoltaic power generation *** the production process,defect samples occur infrequently and exhibit random shapes and sizes,which makes it challenging to collect defective ***,the complex surface background of polysilicon cell wafers complicates the accurate identification and localization of defective *** paper proposes a novel Lightweight Multiscale Feature Fusion network(LMFF)to address these *** network comprises a feature extraction network,a multi-scale feature fusion module(MFF),and a segmentation ***,a feature extraction network is proposed to obtain multi-scale feature outputs,and a multi-scale feature fusion module(MFF)is used to fuse multi-scale feature information *** order to capture finer-grained multi-scale information from the fusion features,we propose a multi-scale attention module(MSA)in the segmentation network to enhance the network’s ability for small target ***,depthwise separable convolutions are introduced to construct depthwise separable residual blocks(DSR)to reduce the model’s parameter ***,to validate the proposed method’s defect segmentation and localization performance,we constructed three solar cell defect detection datasets:SolarCells,SolarCells-S,and *** and SolarCells-S are monocrystalline silicon datasets,and PVEL-S is a polycrystalline silicon *** results show that the IOU of our method on these three datasets can reach 68.5%,51.0%,and 92.7%,respectively,and the F1-Score can reach 81.3%,67.5%,and 96.2%,respectively,which surpasses other commonly usedmethods and verifies the effectiveness of our LMFF network.

关键词： Defect segmentation multi-scale feature fusion multi-scale attention depthwise separable residual block

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：