检索结果-内蒙古大学图书馆

Using analytic hierarchy process to evaluate deep learning for infrared target recognition

Multimedia Tools and Applications 2024年第38期83卷 86229-86245页

作者： Xu, Laixiang Cao, Bingxu Wei, Xinhong Li, Bei Su, Jingfeng Ning, Shiyuan Zhao, Junmin School of Computer and Data Science Henan University of Urban Construction Pingdingshan467036 China School of Information Engineering Luohe Vocational Technology College Henan University of Technology Luohe Institute of Technology Luohe462000 China School of Computer and Data Science Innovation Laboratory of Smart Traffic and Big Data Development of Hainan Province Pingdingshan467036 China School of Computer and Data Science Research Center of Smart City and Big Data Engineering of Henan Province Henan University of Urban Construction Pingdingshan467036 China Department of Software Information China Electronics Technology Group Corporation 36-th Research Institute Jiaxing314033 China School of Computer and Data Science Research Center of Smart City and Big Data Engineering of Henan Province Research Center of Intelligent Campus Application Engineering of Henan Province Innovation Laboratory of Smart Traffic and Big Data Development of Hainan Province Henan University of Urban Construction Pingdingshan467036 China

In order to promote the evaluation performance of deep learning infrared automatic target recognition (ATR) algorithms in the complex environment of air-to-air missile research, we proposed an analytic hierarchy process (AHP) evaluation system consisting of the target recognition ability, the generalization recognition ability, the anti-interference ability, the background suppression ability, and the cost metrics ability. According to detailed quantitative analysis and experimental results, we establish probability evaluation models and get their probability values. Compared with traditional evaluation systems, our proposed method implementation is showing high reliability. Similar superior performances are also achieved, such as quick, comprehensive, and scientific. Through the above research, the key technology of deep learning performance evaluation in automatic target recognition has been broken through, which provides some basis and guidance for the analysis of infrared imaging-guided weapon systems. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Infrared imaging

来源：评论

学校读者我要写书评

暂无评论

Android Application for Children to Learn Arabic Alphabets and Numbers

International Journal of Interactive Mobile Technologies

引用

International Journal of Interactive Mobile Technologies 2025年第5期19卷 115-127页

作者： Al Khaldy, Mohammad Ali Shaheen, Ameen Al-Shaikh, Ala’A Alzyadat, Wael Alhroob, Aysh Department of Business Intelligence and Data Analytics University of Petra Amman Jordan Faculty of Science and Information Technology Al-Zaytoonah University Amman Jordan Faculty of Information Technology Zarqa University Zarqa Jordan

Mobile learning has become a new trend in e-learning that uses portable media such as smartphones. This offers a new space for creating kid-friendly educational game applications. Therefore, this helps parents fulfill their responsibility to teach kids. This study aims to develop and integrate an educational application that contains multimedia elements that inspire children and evaluate their trustworthiness. The waterfall model was used to develop the application of this study. The application includes four sections: numbers, alphabets, animals, and fruits. A survey was conducted and distributed among four experts and 20 children to validate our application. A selective sampling technique was used to choose these responders. Thematic analysis was used to analyze the data collected. According to the results, the application is appropriate for beginners who want to learn the Arabic alphabet and numbers can easily inspire them with the multimedia elements used and can be implemented in the classroom to enhance the effectiveness of the educational process. Future research could examine the effectiveness of the application across different learning styles or age groups. © 2025 by the authors of this article.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Network Insights of Dementia Comorbidities Based on Genetic Background

Network Insights of Dementia Comorbidities Based on Genetic ...

引用

34th Medical Informatics Europe Conference, MIE 2024

作者： Hung, Fei-Hung Tung, Hsin Health Data Analytics and Statistics Center Office of Data Science Taipei Medical University Taipei Taiwan Department of Medical Education Taichung Veterans General Hospital Taichung Taiwan

ISBN: (纸本)9781643685335

Dementia is a global public health concern. This study focuses on the genetic factors underlying dementia. We analyzed electronic medical records (EMR) from Taichung Veterans General Hospital, Taiwan, to confirm differences between dementia and non-dementia patients. This work was supported by Taipei Medical University [TMU111-AE1-B45]. © 2024 The Authors.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

The Influence of Tartaric Acid in the Silver Nanoparticle Synthesis Using Response Surface Methodology

引用

Journal of Renewable Materials 2024年第2期12卷 245-258页

作者： Yatim Lailun Ni’mah Afaf Baktir Dewi Santosaningsih Suprapto Suprapto Chemistry Department Faculty of Science and Data AnalyticsInstitut Teknologi Sepuluh NopemberSurabayaIndonesia Chemistry Department Faculty of Science and TechnologyAirlangga UniversitySurabayaIndonesia Department Clinical Microbiology Faculty of MedicineBrawijaya UniversityMalangIndonesia

Silver nanoparticles(AgNPs)synthesized using tartaric acid as a capping agent have a great impact on the reaction kinetics and contribute significantly to the stability of *** protective layer formed by tartaric acid is an important factor that protects the silver surface and reduces potential cytotoxicity *** attributes are critical for assessing the compatibility of AgNPs with biological systems and making them suitable for drug delivery *** aim of this research is to conduct a comprehensive study of the effect of tartaric acid concentration,sonication time and temperature on the formation of silver *** Response Surface Methodology(RSM)with Face-Centered Central Composite Design(FCCD),the optimization process identifies the most favorable synthesis ***-Vis spectrum regression analysis shows that AgNPs stabilized with tartaric acid are more stable than AgNPs without tartaric *** highlights the increased stability that tartaric acid provides in AgNP *** size distribution analysis showed a multimodal distribution for AgNPs with tartaric acid and showed the smallest size peak with an average size of 20.53 *** second peak with increasing intensity shows a dominant average size of 108.8 nm accompanied by one standard deviation of 4.225 nm and a zeta potential of−11.08 *** contrast,AgNPs synthesized with polyvinylpyrrolidone(PVP)showed a unimodal particle distribution with an average particle size of 81.62 nm and a zeta potential of−2.96 *** more negative zeta potential of AgNP-tartaric acid indicates its increased *** of antibacterial activity showed that AgNPs stabilized with tartaric acid showed better performance against *** and *** bacteria compared with *** summary,this study highlights the potential of tartaric acid in AgNP synthesis and suggests an avenue for the development of stable AgNPs with versatile applications.

关键词： Tartaric acid silver nanoparticle polyvinyl pyrrolidone response surface methodology

来源：评论

学校读者我要写书评

暂无评论

G3DC:A Gene-Graph-Guided Selective Deep Clustering Method for Single Cell RNA-seq data

引用

big data Mining and analytics 2024年第3期7卷 809-827页

作者： Shuqing He Jicong Fan Tianwei Yu Department of Statistics University of MichiganAnn ArborMI 48109USA School of Data Science The Chinese University of Hong KongShenzhen(CUHK-Shenzhen)Shenzhen 518172China Shenzhen Research Institute of Big Data Shenzhen 518172China Warshel Institute for Computational Biology Shenzhen 518172China

Single-cell RNA sequencing(scRNA-seq)technology measures the expression of thousands of genes at the cellular *** single-cell transcriptome allows the identification of heterogeneous cell groups,cellular-level regulations,and the trajectory of cell *** important aspect in the analyses of scRNA-seq data is the clustering of cells,which is hampered by issues,such as high dimensionality,cell type imbalance,redundancy,and *** cells of each type are functionally consistent,incorporating biological relations among genes may improve the clustering *** light of this,we have developed a deep-embedded clustering method,*** method combines a graph regularization based on the pre-existing gene network and a feature selector based on the$l$2,1-norm regularization,along with a reconstruction loss,to generate a discriminatory and informative *** the gene interaction network bolsters the clustering performance and aids in selecting functionally coherent genes,consequently enriching the clustering *** experiments have shown that G3DC offers high clustering accuracy with regard to agreement with true cell types,outperforming other leading single-cell clustering *** addition,G3DC selects biologically relevant genes that contribute to the clustering,providing insight into biological functionality that differentiates cell groups.

关键词： gene graphs feature selection deep learning

来源：评论

学校读者我要写书评

暂无评论

Harnessing Medical big data: Integrating Computational Insights for Enhanced Patient Outcomes 24

Harnessing Medical Big Data: Integrating Computational Insig...

引用

7th International Conference on Digital Medicine and Image Processing, DMIP 2024

作者： Syed Masood, Jafar Ali Ibrahim Vinayagam, Jai Kumar Onteru, Ranjit Kumar Kopparapu, Umamaheswararao Parabathini, Bulah Pushpa Rani Department of IoT School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Vellore632014 India Centre for Big Data Analytics QIS College of Engineering and Technology Andhra Pradesh Ongole India

ISBN: (纸本)9798400709586

The rapid proliferation of medical big data has opened unprecedented opportunities for enhancing patient outcomes through advanced computational analysis. This paper explores the integration of big data analytics with clinical practices to deliver personalized medicine, optimize treatment protocols, and improve patient care. Our findings demonstrate that a synergistic approach between computational insights and clinical decision-making can significantly advance healthcare outcomes. This study provides a comprehensive framework for harnessing medical big data, addressing key challenges, and proposing solutions to integrate these insights into everyday clinical practice. Copyright © 2024 held by the owner/author(s). Publication rights licensed to ACM.

关键词： Personalized medicine

来源：评论

学校读者我要写书评

暂无评论

A TRUST-REGION METHOD FOR NONSMOOTH NONCONVEX OPTIMIZATION

引用

Journal of Computational Mathematics 2023年第4期41卷 683-716页

作者： Ziang Chen Andre Milzarek Zaiwen Wen Department of Mathematics Duke UniversityUSA School of Data Science(SDS) The Chinese University of Hong KongShenzhenShenzhen Research Institute for Big Data(SRIBD)China Beijing International Center for Mathematical Research Peking UniversityBeijing 100000China

We propose a trust-region type method for a class of nonsmooth nonconvex optimization problems where the objective function is a summation of a(probably nonconvex)smooth function and a(probably nonsmooth)convex *** model function of our trust-region subproblem is always quadratic and the linear term of the model is generated using abstract descent ***,the trust-region subproblems can be easily constructed as well as efficiently solved by cheap and standard *** the accuracy of the model function at the solution of the subproblem is not sufficient,we add a safeguard on the stepsizes for improving the *** a class of functions that can be“truncated”,an additional truncation step is defined and a stepsize modification strategy is *** overall scheme converges globally and we establish fast local convergence under suitable *** particular,using a connection with a smooth Riemannian trust-region method,we prove local quadratic convergence for partly smooth functions under a strict complementary *** numerical results on a family of Ei-optimization problems are reported and demonstrate the eficiency of our approach.

关键词： Trust-region method Nonsmooth composite programs Quadratic model function Global and local convergence

来源：评论

学校读者我要写书评

暂无评论

FAIRifying STEM data Ecosystem to Enhance data Reuse 53

FAIRifying STEM Data Ecosystem to Enhance Data Reuse

引用

53rd IEEE ASEE Frontiers in Education International Conference, FIE 2023

作者： Namgay, Phub Wangdi, Pema Thinley, Sangay Namgyel, Thinley Uppsala University Department of Informatics and Media Uppsala Sweden School of Data Science and Data Analytics Sherubtse College Royal University of Bhutan Bhutan

ISBN: (纸本)9798350336429

In the science, technology, engineering, and mathematics (STEM) community, academic and research workflows and work practices are increasingly mediated and informed by data. However, making digital materials and resources findable, accessible, interoperable, and reusable (FAIR) for teaching, learning, and research is an under-researched area. Thus, it is vital to examine the current data practices of STEM students and faculties and acquaint them with the FAIR data concept. FAIR data Principles is a set of guidelines that underscore metadata, vocabularies, licences, and standards to enhance data reuse. A study was conducted among students and faculties in the STEM community of the Royal University of Bhutan (RUB) to unpack their current data practices and explore areas for improvement using the FAIR data Principles. The STEM students and faculties of the RUB share and reuse digital materials and resources for teaching, learning, and research. Nevertheless, their data practice is not as widespread or desired in the literature on optimum data reuse. Moreover, the compliance of current data practices to the tenets of FAIR data Principles is not satisfactory. A pragmatic solution is complementing data practices with policies and infrastructural systems that underscore FAIR data Principles. A sensitisation programme such as seminars and hands-on exercises on data FAIRification is crucial to familiarise people with the essentialness of FAIR data, and doing so will provide a platform to develop their repertoire for FAIRifying data and encourage systematic sharing and reuse of data. An in-depth account of the FAIRifying STEM data ecosystem in the study contributes to the growing knowledge base on adopting FAIR data Principles in other areas of data-informed work and life. © 2023 IEEE.

关键词： Bhutan data Reuse FAIR data Principles FAIRifying data STEM data Ecosystem

来源：评论

学校读者我要写书评

暂无评论

Lifelong Graph Learning for Graph Summarization

Lifelong Graph Learning for Graph Summarization

引用

IEEE WIC ACM International Conference on Web Intelligence (WI)

作者： Jonatan Frank Marcel Hoffmann Nicolas Lell David Richerby Ansgar Scherp Data Science and Big Data Analytics Ulm University Germany University of Essex Colchester UK

ISBN: (数字)9798331504946

ISBN: (纸本)9798331504953

Summarizing web graphs is challenging due to the heterogeneity of the modeled information and its changes over time. We investigate the use of neural networks for lifelong graph summarization. After observing the web graph at a point in time, we train a network to summarize graph vertices. We apply this trained network to summarize the vertices of the changed graph at the next point in time. Subsequently, we continue training and evaluating the network to perform lifelong graph summarization. We use the GNNs Graph-MLP and GCN, as well as an MLP baseline, to summarize the temporal graphs. We compare 1-hop and 2-hop summaries. We investigate the impact of reusing parameters from a previous snapshot by measuring backward and forward transfer as well as forgetting rate. Our extensive experiments are on two series of ten weekly snapshots, from 2012 and 2022, of a web graph with over 100M edges. They show that all networks predominantly use 1-hop information to determine the summary, even when performing 2-hop summarization. Due to the heterogeneity of web graphs, in some snapshots, the 2-hop summary produces up to ten times as many vertex classes as the 1-hop summary. When using the network trained on the last snapshot from 2012 and applying it to the first snapshot of 2022, we observe a strong drop in accuracy. We attribute this drop over the ten-year time warp to the strongly increased heterogeneity of the web graph in 2022. The source code and additional resources are available at https://***/jofranky/Lifelong-Graph-Summarization-with-Neural-Networks.

关键词： Training Accuracy Current measurement Source coding Time measurement Resource description framework Graph neural networks Intelligent agents

来源：评论

学校读者我要写书评

暂无评论

Multi-View Structural Graph Summaries

Multi-View Structural Graph Summaries

引用

IEEE WIC ACM International Conference on Web Intelligence (WI)

作者： Jonatan Frank Andor Diera David Richerby Ansgar Scherp Data Science and Big Data Analytics Ulm University Germany University of Essex Colchester UK

ISBN: (数字)9798331504946

ISBN: (纸本)9798331504953

A structural graph summary is a small graph representation that preserves structural information necessary for a given task. The summary is used instead of the original graph to complete the task faster. We introduce multi-view structural graph summaries and propose an algorithm for merging two summaries. We conduct a theoretical analysis of our algorithm. We run experiments on three datasets, contributing two new ones. The datasets are of different domains (web graph, source code, and news) and sizes. The interpretation of multi-view depends on the domain: pay-level domains on the web, control vs. data flow of the code, and the output of different news broadcasters. We experiment with three graph summary models: attribute collection, class collection, and their combination. We observe that merging two structural summaries has an upper bound of quadratic complexity; but under reasonable assumptions, it has linear-time worst-case complexity. The running time of merging has a strong linear correlation with the number of edges in the two summaries. Therefore, the experiments support the assumption that the upper bound of quadratic complexity is not tight and that linear complexity is possible. Furthermore, our experiments show that always merging the two smallest summaries by the number of edges is the most efficient strategy for merging multiple structural summaries. The source code and additional resources are available at https://***/jofranky/Multi-View-Structural-Graph-Summaries.

关键词： Upper bound Correlation Codes Source coding Merging Knowledge graphs Resource description framework Complexity theory Intelligent agents

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：