检索结果-内蒙古大学图书馆

1st IEEE International Interdisciplinary Humanitarian Conference for Sustainability, IIHC 2022

作者： Sangeetha, M. Karthikeyini, C. Vasundhara, S. Saravanan, D. Arunkumar, G. School of Computing SRMIST Department of Data Science and Business Systems Kattankulathur C India Excel Engineering College Department of ECE Tamil Nadu Komarapalayam India G.Narayanamma Institute of Technology &science Department of Humanities & Mathematics JNTUH Hyderabad India IFET College of Engineering Department of CSE Tamil Nadu Villupuram India Madanapalle Institute of Technology & Science Department of CSE Andhra Pradesh Madanapalle India

ISBN: (纸本)9781665456876

Skin Cancer is one of the most common cancer forms in many countries, it is considered to be one of the dangerous types in the sense that it is lethal and its occurrence over time has been dramatically high. It is one of the deadliest cancers among all diseases and has a large rate of mortality. The efficiency of the earlier approaches to assess one of the most hazardous melanoma diagnosis in dermoscopic criteria are not up to the mark. Therefore, in this research, the work has been carried out in three stages in order to detect melanoma in an efficient manner. In the first stage, prior to the implementation of the image segmentation technique, noise elimination and pre-processing steps are carried out to remove the noise and to achieve better execution results. This segmentation model focuses on the separation of the interesting portions from the background and collects the necessary information from the neighboring pixels of the same category. Gaussian analytical patterns are used to handle the heterogeneous regions/sections of dermoscopy images whose mean and variance can be dynamic. In addition, the third stage of work is based on the texture classification, which is proposed as the CSTC-Mel Identification Model. © 2022 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Self-healing corrosion protective coatings based on micro/nanocarriers: A review

引用

Corrosion Communications 2021年第1期1卷 18-25页

作者： Tong Liu Lingwei Ma Xin Wang Jinke Wang Hongchang Qian Dawei Zhang Xiaogang Li National Materials Corrosion and Protection Data Center Institute for Advanced Materials and Technology University of Science and Technology Beijing BRI Southeast Asia Network for Corrosion and Protection (MOE) Shunde Graduate School of University of Science and Technology Beijing

Extrinsic self-healing corrosion protective coatings have attracted substantial interest because of their ability to prevent damage propagation by releasing corrosion inhibitors and polymerizable agents from micro/*** micro/nanoencapsulation technologies have been adopted to optimize the loading capacity and to control the releasing behavior of the healing agents for enhancing the self-healing functionality. This study aims to review recent advances in self-healing corrosion protective coatings based on micro/nanocarriers. This review also provides insights for the further development of extrinsic self-healing coatings by evaluating the advantages and limitations of different healing systems.

关键词： Corrosion protection Organic coating Self-healing material Micro/nanocarrier

来源：评论

学校读者我要写书评

暂无评论

IOMatch: Simplifying Open-Set Semi-Supervised Learning with Joint Inliers and Outliers Utilization

IOMatch: Simplifying Open-Set Semi-Supervised Learning with ...

引用

International Conference on Computer Vision (ICCV)

作者： Zekun Li Lei Qi Yinghuan Shi Yang Gao State Key Laboratory for Novel Software Technology and National Institute of Healthcare Data Science Nanjing University School of Computer Science and Engineering Southeast University

Semi-supervised learning (SSL) aims to leverage massive unlabeled data when labels are expensive to obtain. Unfortunately, in many real-world applications, the collected unlabeled data will inevitably contain unseen-class outliers not belonging to any of the labeled classes. To deal with the challenging open-set SSL task, the mainstream methods tend to first detect outliers and then filter them out. However, we observe a surprising fact that such approach could result in more severe performance degradation when labels are extremely scarce, as the unreliable outlier detector may wrongly exclude a considerable portion of valuable inliers. To tackle with this issue, we introduce a novel open-set SSL framework, IOMatch, which can jointly utilize inliers and outliers, even when it is difficult to distinguish exactly between them. Specifically, we propose to employ a multi-binary classifier in combination with the standard closed-set classifier for producing unified open-set classification targets, which regard all outliers as a single new class. By adopting these targets as open-set pseudo-labels, we optimize an open-set classifier with all unlabeled samples including both inliers and outliers. Extensive experiments have shown that IOMatch significantly outperforms the baseline methods across different benchmark datasets and different settings despite its remarkable simplicity. Our code and models are available at https://***/nukezil/IOMatch.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Disentangled Cascaded Graph Convolution Networks for Multi-Behavior Recommendation

引用

ACM Transactions on Recommender Systems 2024年第4期2卷 1-27页

作者： Zhiyong Cheng Jianhua Dong Fan Liu Lei Zhu Xun Yang Meng Wang School of Computer Science and Information Engineering Hefei University of Technology Hefei China Shandong Artificial Intelligence Institute Qilu University of Technology (Shandong Academy of Sciences) Jinan China School of Computing National University of Singapore Singapore Singapore School of Electronic and Information Engineering Tongji University Shanghai China School of Information Science and Technology University of Science and Technology of China Hefei China Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology Hefei China and Hefei Comprehensive National Science Center Hefei China

Multi-behavioral recommender systems have emerged as a solution to address data sparsity and cold-start issues by incorporating auxiliary behaviors alongside target behaviors. However, existing models struggle to accurately capture varying user preferences across different behaviors and fail to account for diverse item preferences within behaviors. Various user preference factors (such as price or quality) entangled in the behavior may lead to sub-optimization problems. Furthermore, these models overlook the personalized nature of user behavioral preferences by employing uniform transformation networks for all users and items. To tackle these challenges, we propose the Disentangled Cascaded Graph Convolutional Network (Disen-CGCN), a novel multi-behavior recommendation model. Disen-CGCN employs disentangled representation techniques to effectively separate factors within user and item representations, ensuring their independence. In addition, it incorporates a multi-behavioral meta-network, enabling personalized feature transformation across user and item behaviors. Furthermore, an attention mechanism captures user preferences for different item factors within each behavior. By leveraging attention weights, we aggregate user and item embeddings separately for each behavior, computing preference scores that predict overall user preferences for items. Our evaluation of benchmark datasets demonstrates the superiority of Disen-CGCN over state-of-the-art models, showcasing an average performance improvement of 7.07% and 9.00% on respective datasets. These results highlight Disen-CGCN’s ability to effectively leverage multi-behavioral data, leading to more accurate recommendations.

关键词： Multi-Behavior Recommendation disentangled representation learning graph convolutional network multi-behavior recommendation multi-task learning

来源：评论

学校读者我要写书评

暂无评论

Quadratic Finite Volume Element Schemes over Triangular Meshes for a Nonlinear Time-Fractional Rayleigh-Stokes Problem

引用

Computer Modeling in Engineering & sciences 2021年第5期127卷 487-514页

作者： Yanlong Zhang Yanhui Zhou Jiming Wu Graduate School of China Academy of Engineering Physics Beijing100088China School of Data and Computer Science Sun Yat-Sen UniversityGuangzhou510275China Institute of Applied Physics and Computational Mathematics Beijing100088China

In this article,we study a 2D nonlinear time-fractional Rayleigh-Stokes problem,which has an anomalous subdiffusion term,on triangular meshes by quadratic finite volume element ***-fractional derivative,defined by Caputo fractional derivative,is discretized through L2−1σformula,and a two step scheme is used to approximate the time first-order derivative at time tn−α/2,where the nonlinear term is approximated by using a matching linearized difference scheme.A family of quadratic finite volume element schemes with two parameters are proposed for the spatial discretization,where the range of values for two parameters areβ1∈(0,1/2),β2∈(0,2/3).For testing the precision of numerical algorithms,we calculate some numerical examples which have known exact solution or unknown exact solution by several kinds of quadratic finite volume element schemes,and contrast with the results of an existing quadratic finite element scheme by drawing diversified comparison plots and showing the detailed data of L2 error results and convergence *** results indicate that,L2 error estimate of one scheme with parameters β_(1)=(3−√3)/6,β2=(6+√3−√21+6√3)/9 is O(h^(3)+△t^(2)),and L^(2) error estimates of other schemes are O(h^(2)+△t^(2)),where h and △t denote the spatial and temporal discretization parameters,respectively.

关键词： Quadratic finite volume element schemes anomalous sub-diffusion term L2 error estimate quadratic finite element scheme

来源：评论

学校读者我要写书评

暂无评论

FedMHO: Heterogeneous One-Shot Federated Learning Towards Resource-Constrained Edge Devices

arXiv

引用

arXiv 2025年

作者： Yao, Dezhong Shi, Yuexin Liu, Tongtong Xu, Zhiqiang National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China Mohamed bin Zayed University of Artificial Intelligence United Arab Emirates

Federated Learning (FL) is increasingly adopted in edge computing scenarios, where a large number of heterogeneous clients operate under constrained or sufficient resources. The iterative training process in conventional FL introduces significant computation and communication overhead, which is unfriendly for resource-constrained edge devices. One-shot FL has emerged as a promising approach to mitigate communication overhead, and model-heterogeneous FL solves the problem of diverse computing resources across clients. However, existing methods face challenges in effectively managing model-heterogeneous one-shot FL, often leading to unsatisfactory global model performance or reliance on auxiliary datasets. To address these challenges, we propose a novel FL framework named FedMHO, which leverages deep classification models on resource-sufficient clients and lightweight generative models on resource-constrained devices. On the server side, FedMHO involves a two-stage process that includes data generation and knowledge fusion. Furthermore, we introduce FedMHO-MD and FedMHO-SD to mitigate the knowledge-forgetting problem during the knowledge fusion stage, and an unsupervised data optimization solution to improve the quality of synthetic samples. Comprehensive experiments demonstrate the effectiveness of our methods, as they outperform state-of-the-art baselines in various experimental setups. Our code is available at https://***/YXShi2000/FedMHO. © 2025, CC BY.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Structuring Clinical Notes of Italian ST-elevation Myocardial Infarction Patients 1

Structuring Clinical Notes of Italian ST-elevation Myocardia...

引用

1st Workshop on Patient-Oriented Language Processing, CL4Health 2024

作者： Torri, Vittorio Mazzucato, Sara Dalmiani, Stefano Paradossi, Umberto Passino, Claudio Moccia, Sara Micera, Silvestro Ieva, Francesca MOX - Modelling and Scientific Computing Lab Department of Mathematics Politecnico di Milano Italy Biorobotics Institute Department of Excellence in Robotics and AI Scuola Superiore Sant’Anna Italy Fondazione Toscana Gabriele Monasterio Italy Health Science Interdisciplinary Center Scuola Superiore Sant’Anna Italy Bertarelli Foundation Chair in Translational Neural Engineering Center for Neuroprosthetics Institute of Bioengineering Ecole Polytechnique Federale de Lausanne Switzerland HDS - Health Data Science Centre Human Technopole Italy

ISBN: (纸本)9782493814258

In recent years, it has become common for patients to get full access to their Electronic Health Records (EHRs), thanks to the advancements in the EHRs systems of many healthcare providers. While this access empowers patients and doctors with comprehensive and real-time health information, it also introduces new challenges, in particular due to the unstructured nature of much of the information within EHRs. To address this, we propose a pipeline to structure anamneses, providing patients with a clear and concise overview of their health data and its longitudinal evolution, also allowing clinicians to focus more on patient care during consultations. In this paper, we present preliminary results on extracting structured information from EHRs of patients diagnosed with ST-Elevation Myocardial Infarction from an Italian hospital. Our pipeline exploits text classification models to extract relevant clinical variables, comparing rule-based, recurrent neural network and BERT-based models. While various approaches utilized ontologies or knowledge graphs for Italian data, our work represents the first attempt to develop this type of pipeline. The results for the extraction of most variables are satisfactory (f1-score > 0.80), with the exception of the most rare values of certain variables, for which we propose future research directions to investigate. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Cerium oxide inclusion nucleation mechanism based on classical nucleation theory and two-step nucleation

引用

Journal of Rare Earths 2024年第4期42卷 793-802页

作者： Yutang Li Jun Wang Linzhu Wang Chaoyi Chen Shufeng Yang Junqi Li Xiang Li School of Materials and Metallurgy Guizhou UniversityGuiyang550025China State Key Laboratory of Public Big Data Guizhou UniversityGuiyang550025China School of Metallurgical and Ecological Engineering University of Science and Technology BeijingBeijing100083China Department of Materials&Metallurgy Engineering Guizhou Institute of TechnologyGuiyang550003China

It is challenging to assess the mechanism responsible for the nucleation of inclusions in metals at high *** present work therefore systematically investigates the nucleation of cerium oxide inclusions according to classical nucleation theory and a two-step nucleation *** nucleation rates and nucleation radii of these inclusions are obtained,and the results demonstrate a considerable difference between theoretical and experimental *** the basis of a two-step nucleation mechanism,(CeO_(2))_(n) and(Ce_(2)O_(3))_(n)(n=1-6)clusters were constructed and the thermodynamic properties of both these clusters and of cerium oxide nanoparticles were *** addition,the entropies and heat capacity changes of cerium oxides were determined using first principles calculations and are found to be consistent with literature *** present data indicate that the cerium oxide inclusion nucleation pathway can be summarized as[Ce]+[O]→(CeO_(2))n/(Ce_(2)O_(3))_(n)→(Ce_(2)O_(3))_(n)→(Ce_(2)O_(3))_(2)→core(Ce_(2)O_(3)crystal)-shell((Ce_(2)O_(3))_(2) cluster)nanoparticles→(Ce_(2)O_(3))bulk.

关键词： Cerium oxide inclusion Classical nucleation theory Two-step nucleation mechanism First principles Rare earths

来源：评论

学校读者我要写书评

暂无评论

Income Tax Fraud Deduction Using Machine Learning

Income Tax Fraud Deduction Using Machine Learning

引用

Advancement in Electronics & Communication Engineering (AECE), International Conference on

作者： Pradeep Sudhakaran Prudhvi Kolamudi Preetha M K Pragash Department of Computing Technologies SRM Institute of Science and Technology Kattankulathur Tamil Nadu India Career Development Centre SRM Institute of Science and Technology Potheri Kattankulathur Tamil Nadu India Department of Artificial Intelligence and Data Science Sri Manakula Vinayagar Engineering College Madagadipet Puducherry India

ISBN: (数字)9798350364729

ISBN: (纸本)9798350364736

Specifically, the program is based on boosting methods in the context of the used machine learning, to reveal potential cases of evasion of income tax. The procedure consists of obtaining and using datasets of income tax for the learning and training purpose. The first and crucial goal is to enhance the accuracy of predicting fraud cases through learning boosting algorithms and graphical representation of the most significant factors leading to fraud detection. Depending on accuracy and sensitivity as well as specificity and precision for that matter, the said assessment will be conducted. The first goal entails a mechanization of the process of identifying foraging activities, eliminating possible errors, and improving efficiency of and security in income tax assessments with particular emphasis in distinguishing between probable real and potentially fraudulent tax returns [10]. The boosting techniques alongside other futuristic ways of identifying the suspicious transactions can help the tax authorities to improve the risk management processes of their organization. In other words, this approach of fraud detection makes it possible to proceed to more efficient work in terms of both accuracy and the reliability of certain results. Also, the <|reserved_special_token_265|> channels of tax avoidance can be closed by concentrating efforts on cases of high risk as the authorities are more likely to lose a lot of revenues. Machine learning technologies can easily address these requirements, giving the necessary flexibility and precision to prevent and identify fraudulent activities and strategies. These strategies are critical in protecting the Tax system a longer term game which can effectively counter financial fraudsters. The goal of the project are to gather information on the corporate taxation; to apply boosting algorithms for fraudulent activity detection, and to evaluate the efficiency of boosting algorithms. The main focus is primarily aimed at the increased app

关键词： Training Accuracy Machine learning algorithms Sensitivity Finance Boosting Prediction algorithms Fraud Stakeholders Security

来源：评论

学校读者我要写书评

暂无评论

An overview of diffusion models for generative artificial intelligence

arXiv

引用

arXiv 2024年

作者： Gallon, Davide Jentzen, Arnulf von Wurstemberger, Philippe Applied Mathematics: Institute for Analysis and Numerics University of Münster Germany School of Data Science Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Shenzhen [CUHK-Shenzhen China Risklab Department of Mathematics ETH Zurich Switzerland

This article provides a mathematically rigorous introduction to denoising diffusion probabilistic models (DDPMs), sometimes also referred to as diffusion probabilistic models or diffusion models, for generative artificial intelligence. We provide a detailed basic mathematical framework for DDPMs and explain the main ideas behind training and generation procedures. In this overview article we also review selected extensions and improvements of the basic framework from the literature such as improved DDPMs, denoising diffusion implicit models, classifier-free diffusion guidance models, and latent diffusion models. Copyright © 2024, The Authors. All rights reserved.

关键词： Generative adversarial networks

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：