检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Su, Jinyan Zhao, Changhong Wang, Di Mohamed bin Zayed University of Artificial Intelligence United Arab Emirates Department of Information Engineering The Chinese University of Hong Kong Hong Kong Provable Responsible AI and Data Analytics Lab India Computational Bioscience Research Center India Division of CEMSE King Abdullah University of Science and Technology Saudi Arabia

In this paper, we revisit the problem of Differentially Private Stochastic Convex Optimization (DP-SCO) in Euclidean and general dp spaces. Specifically, we focus on three settings that are still far from well understood: (1) DP-SCO over a constrained and bounded (convex) set in Euclidean space;(2) unconstrained DP-SCO in dp space;(3) DP-SCO with heavy-tailed data over a constrained and bounded set in dp space. For problem (1), for both convex and strongly convex loss functions, we propose methods whose outputs could achieve (expected) excess population risks that are only dependent on the Gaussian width of the constraint set, rather than the dimension of the space. Moreover, we also show the bound for strongly convex functions is optimal up to a logarithmic factor. For problems (2) and (3), we propose several novel algorithms and provide the first theoretical results for both cases when 1 © 2023, CC BY.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

Deep and handcrafted feature supported diabetic retinopathy detection: A study

Deep and handcrafted feature supported diabetic retinopathy ...

引用

2022 International Conference on Machine Learning and data engineering, ICMLDE 2022

作者： Kadry, Seifedine Crespo, Rubén González Herrera-Viedma, Enrique Krishnamoorthy, Sujatha Rajinikanth, Venkatesan Faculty of Applied Computing and Technology Noroff University College Kristiansand94612 Norway Computer Science Department School of Engineering and Technology Universidad Internacional de la Rioja Andalusia26006 Spain Research Institute in Data Science and Computational Intelligence University of Granada Granada Spain Zhejiang Bioinformatics International Science and Technology Cooperation Center Wenzhou-Kean University Zhejiang Province China Wenzhou Municipal Key Lab of Applied Biomedical and Biopharmaceutical Informatics Wenzhou-Kean University Zhejiang Province China Department of Electronics and Instrumentation Engineering St. Joseph's College of Engineering OMR Tamil Nadu Chennai600119 India

The eye is the prime sensory organ in physiology, and the abnormality in the eye severely influences the vision system. Therefore, eye irregularity is commonly assessed using imaging schemes, and Fundus Retinal Image (FRI) supported eye screening is one of the ophthalmological practices. This work proposed a Deep-Learning Procedure (DLP) to recognize Diabetic Retinopathy (DR) in FI. The proposed work presents the experimental work with different DLP methods found in the literature. This work is executed with two modes;(i) DR detection using conventional deep-features and (ii) DR discovery using deep ensemble features. To demonstrate this work, 1800 fundus images (900 regular and 900 DR class) are considered for the assessment, and the advantage of proposed plan is confirmed using various performance metrics. The experimental outcome of this study confirms that the AlexNet-based detection provides a better detection (>96%), and the deep ensemble features of AlexNet, VGG16, and ResNet18 provide a detection accuracy of >98% on the chosen FRI database. © 2022 Elsevier B.V.. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Automatic detection of lung nodule in CT scan slices using CNN segmentation schemes: A study

Automatic detection of lung nodule in CT scan slices using C...

引用

2022 International Conference on Machine Learning and data engineering, ICMLDE 2022

作者： Kadry, Seifedine Herrera-Viedma, Enrique Crespo, Rubén González Krishnamoorthy, Sujatha Rajinikanth, Venkatesan Faculty of Applied Computing and Technology Noroff University College Kristiansand94612 Norway Research Institute in Data Science and Computational Intelligence University of Granada Andalusian Granada Spain Computer Science Department School of Engineering and Technology Universidad Internacional de la Rioja 26006 Spain Zhejiang Bioinformatics International Science and Technology Cooperation Center Wenzhou-Kean University Zhejiang Province China Wenzhou Municipal Key Lab of Applied Biomedical and Biopharmaceutical Informatics Wenzhou-Kean University Zhejiang Province China Department of Electronics and Instrumentation Engineering St. Joseph's College of Engineering OMR Tamil Nadu Chennai600119 India

The lung is one of the prime respiratory organs in human physiology, and its abnormality will severely disrupt the respiratory system. Lung Nodule (LN) is one of the abnormalities, and early screening and treatment are necessary to reduce its harshness. The proposed work aims to implement the Convolutional-Neural-Network (CNN) segmentation methodology to extract the LN in various lung CT slices, such as axial, coronal, and sagittal planes. This work consists of the following phases;(i) Image collection and pre-processing, (ii) Ground-truth generation, (iii) CNN-supported segmentation, and (iv) Performance evaluation and validation. In this work, the merit of pre-trained CNN segmentation schemes is verified using (i) One-fold training and (ii) Two-fold training methods. The test images for this study are collected from The Cancer Imaging Archive (TCIA) database. The experimental investigation is executed using Python®, and the outcome of this study confirms that the VGG-SegNet helps to get better values of Jaccard (>88%), Dice (>93%), and Accuracy (>96%) compared to other CNN methods. © 2023 The Authors. Published by Elsevier B.V.

关键词： Computerized tomography

来源：评论

学校读者我要写书评

暂无评论

An improved RNN modeling algorithm for flotation process of copper-silver ore

An improved RNN modeling algorithm for flotation process of ...

引用

Chinese Control and Decision Conference, CCDC

作者： Kang Wang Liwei Pang Xiaoli Li Xin Zhao Faculty of Information Technology Beijing University of Technology Beijing Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing Engineering Research Center of Digital Community of Ministry of Education Beijing China Railway 19th Bureau Group Mining Investment Co. Beijing

ISBN: (纸本)9781665478977

Concentrate grade is an important evaluation index in the flotation process, which reflects the rich degree of specific recovery components in the concentrate. In this paper, the copper and silver ore grades in LinXi mining Co., Ltd are taken as the research object. Given the difficulty in identifying the flotation process through mechanism modeling, the recurrent neural network model of the flotation process is established by using the idea of data-driven. Considering that the learning parameters are randomly selected, an improved RNN model is proposed by introducing the index function which optimizes the model parameters to obtain better modeling performance. The simulation results show that the improved recurrent neural network model can effectively identify the flotation process compared with the traditional RNN model and ARMAX model. Key Words: Flotation process, Recurrent neural network, Concentrate grade, data driven, Model optimization

关键词： Silver Recurrent neural networks Simulation Ores Process control Production Predictive models

来源：评论

学校读者我要写书评

暂无评论

Estimating geographic variation of infection fatality ratios during epidemics

引用

Infectious Disease Modelling 2024年第2期9卷 634-643页

作者： Joshua Ladau Eoin L.Brodie Nicola Falco Ishan Bansal Elijah B.Hoffman Marcin P.Joachimiak Ana M.Mora Angelica M.Walker Haruko M.Wainwright Yulun Wu Mirko Pavicic Daniel Jacobson Matthias Hess James B.Brown Katrina Abuabara Departments of Computational Precision Health and Dermatology University of CaliforniaSan FranciscoCA94115USA Arva Intelligence Inc.Salt Lake CityUT84101USA Computational Biosciences Group Lawrence Berkeley National LaboratoryBerkeleyCA94720USA Earth and Environmental Sciences Area Lawrence Berkeley National LaboratoryBerkeleyCA94720USA Graduate Group in Biostatistics University of CaliforniaBerkeleyCA94720USA Biosystems Data Science Environmental Genomics and Systems BiologyLawrence Berkeley National LaboratoryBerkeleyCA94720USA Center for Environmental Research and Community Health(CERCH) School of Public HealthUniversity of CaliforniaBerkeleyCA94720USA Bredesen Center for Interdisciplinary Research and Graduate Education University of TennesseeKnoxvilleTN37996USA Department of Nuclear Science and Engineering Massachusetts Institute of TechnologyBostonMA02139USA Biosciences Oak Ridge National LaboratoryOak RidgeTN37830USA University of California DavisCA95616USA Statistics Department University of CaliforniaBerkeleyCA94720USA Division of Epidemiology and Biostatistics University of California Berkeley School of Public Health2121 Berkeley WayBerkeleyCA94720USA

Objectives We aim to estimate geographic variability in total numbers of infections and infection fatality ratios(IFR;the number of deaths caused by an infection per 1,000 infected people)when the availability and quality of data on disease burden are limited during an *** We develop a noncentral hypergeometric framework that accounts for differential probabilities of positive tests and reflects the fact that symptomatic people are more likely to seek *** demonstrate the robustness,accuracy,and precision of this framework,and apply it to the United States(U.S.)COVID-19 pandemic to estimate county-level SARS-CoV-2 *** The estimators for the numbers of infections and IFRs showed high accuracy and precision;for instance,when applied to simulated validation data sets,across counties,Pearson correlation coefficients between estimator means and true values were 0.996 and 0.928,respectively,and they showed strong robustness to model *** the county-level estimators to the real,unsimulated COVID-19 data spanning April 1,2020 to September 30,2020 from across the U.S.,we found that IFRs varied from 0 to 44.69,with a standard deviation of 3.55 and a median of *** The proposed estimation framework can be used to identify geographic variation in IFRs across settings.

关键词： Infection fatality ratio Infection fatality rate Noncentral hypergeometric distribution COVID-19 SARS-CoV-2

来源：评论

学校读者我要写书评

暂无评论

Classification of Breast Thermal Images into Healthy/Cancer Group Using Pre-Trained Deep Learning Schemes

引用

Procedia Computer Science 2023年 218卷 24-34页

作者： Seifedine Kadry Rubén González Crespo Enrique Herrera-Viedma Sujatha Krishnamoorthy Venkatesan Rajinikanth Faculty of Applied Computing and Technology Noroff University College Kristiansand 94612 Norway Computer Science Department School of Engineering and Technology Universidad Internacional de La Rioja 26006 Andalusian Spain Research Institute in Data Science and Computational Intelligence University of Granada Granada Spain Zhejiang Bioinformatics International Science and Technology Cooperation Center Wenzhou-Kean University Zhejiang Province China Wenzhou Municipal Key Lab of Applied Biomedical and Biopharmaceutical Informatics Wenzhou-Kean University Zhejiang Province China Department of Computer Science and Engineering Saveetha School of Engineering SIMATS Chennai 602105 Tamil Nadu India

In the women's community, Breast Cancer (BC) is a severe disease. The World Health Organization reported in 2020 that 2.26 million deaths occur due to BC. BC is curable if detected early. Since thermal imaging is non-invasive and supports disease detection, it is commonly used in clinics. Compared to other methods, it keeps BC early and accurate. The proposed work aims to evaluate the performance of the Pretrained Deep-Learning Methods (PDLM) in detecting BC using the thermal images collected from the benchmark dataset. It includes the following stages: primary image processing, deep feature mining, handcrafted feature mining, feature optimization using Firefly-Algorithm (FA), classification and validation. Visual Lab thermal images were used in the study. The investigational outcome of this study authenticates that the VGG16, along with the DT, provides better detection accuracy (95.5%) compared to other classifiers used in this study. To justify the significance of the implemented technique, the proposed work not only improved accuracy, but also improved precision, sensitivity, specificity, and F1-Scores.

关键词： Breast cancer Thermal imaging Firefly algorithm Feature optimization Classification

来源：评论

学校读者我要写书评

暂无评论

Automatic detection of lung nodule in CT scan slices using CNN segmentation schemes: A study

引用

Procedia Computer Science 2023年 218卷 2786-2794页

作者： Seifedine Kadry Enrique Herrera-Viedma Rubén González Crespo Sujatha Krishnamoorthy Venkatesan Rajinikanth Faculty of Applied Computing and Technology Noroff University College Kristiansand 94612 Norway Research Institute in Data Science and Computational Intelligence University of Granada Granada Andalusian Spain Computer Science Department School of Engineering and Technology Universidad Internacional de La Rioja 26006 Spain Zhejiang Bioinformatics International Science and Technology Cooperation Center Wenzhou-Kean University Zhejiang Province China Wenzhou Municipal Key Lab of Applied Biomedical and Biopharmaceutical Informatics Wenzhou-Kean University Zhejiang Province China Department of Electronics and Instrumentation Engineering St. Joseph's College of Engineering OMR Chennai 600119 Tamil Nadu India

The lung is one of the prime respiratory organs in human physiology, and its abnormality will severely disrupt the respiratory system. Lung Nodule (LN) is one of the abnormalities, and early screening and treatment are necessary to reduce its harshness. The proposed work aims to implement the Convolutional-Neural-Network (CNN) segmentation methodology to extract the LN in various lung CT slices, such as axial, coronal, and sagittal planes. This work consists of the following phases; (i) Image collection and pre-processing, (ii) Ground-truth generation, (iii) CNN-supported segmentation, and (iv) Performance evaluation and validation. In this work, the merit of pre-trained CNN segmentation schemes is verified using (i) One-fold training and (ii) Two-fold training methods. The test images for this study are collected from The Cancer Imaging Archive (TCIA) database. The experimental investigation is executed using Python®, and the outcome of this study confirms that the VGG-SegNet helps to get better values of Jaccard (>88%), Dice (>93%), and Accuracy (>96%) compared to other CNN methods.

关键词： Lung nodule CT scan CNN segmentation VGG-SegNet Accuracy Detection

来源：评论

学校读者我要写书评

暂无评论

Deep and handcrafted feature supported diabetic retinopathy detection: A study

引用

Procedia Computer Science 2023年 218卷 2675-2683页

作者： Seifedine Kadry Rubén González Crespo Enrique Herrera-Viedma Sujatha Krishnamoorthy Venkatesan Rajinikanth Faculty of Applied Computing and Technology Noroff University College Kristiansand 94612 Norway Computer Science Department School of Engineering and Technology Universidad Internacional de La Rioja 26006 Andalusian Spain Research Institute in Data Science and Computational Intelligence University of Granada Granada Spain Zhejiang Bioinformatics International Science and Technology Cooperation Center Wenzhou-Kean University Zhejiang Province China Wenzhou Municipal Key Lab of Applied Biomedical and Biopharmaceutical Informatics Wenzhou-Kean University Zhejiang Province China Department of Electronics and Instrumentation Engineering St. Joseph's College of Engineering OMR Chennai 600119 Tamil Nadu India

The eye is the prime sensory organ in physiology, and the abnormality in the eye severely influences the vision system. Therefore, eye irregularity is commonly assessed using imaging schemes, and Fundus Retinal Image (FRI) supported eye screening is one of the ophthalmological practices. This work proposed a Deep-Learning Procedure (DLP) to recognize Diabetic Retinopathy (DR) in FI. The proposed work presents the experimental work with different DLP methods found in the literature. This work is executed with two modes; (i) DR detection using conventional deep-features and (ii) DR discovery using deep ensemble features. To demonstrate this work, 1800 fundus images (900 regular and 900 DR class) are considered for the assessment, and the advantage of proposed plan is confirmed using various performance metrics. The experimental outcome of this study confirms that the AlexNet-based detection provides a better detection (>96%), and the deep ensemble features of AlexNet, VGG16, and ResNet18 provide a detection accuracy of >98% on the chosen FRI database.

关键词： Eye abnormality Diabetic retinopathy Fundus imaging Deep-Learning Classification

来源：评论

学校读者我要写书评

暂无评论

Adaptive fast-reaching nonsingular terminal sliding mode tracking control for quadrotor UAVs subject to model uncertainties and external disturbances

引用

Ain Shams engineering Journal 2023年第8期14卷

作者： Mobayen, Saleh El-Sousy, Fayez F.M. Alattas, Khalid A Mofid, Omid Fekih, Afef Rojsiraphisal, Thaned Graduate School of Intelligent Data Science National Yunlin University of Science and Technology 123 University Road Section 3 Douliou Yunlin640301 Taiwan Department of Electrical Engineering Prince Sattam Bin Abdulaziz University Al Kharj Saudi Arabia Department of Computer Science and Artificial Intelligence College of Computer Science and Engineering University of Jeddah Jeddah Saudi Arabia Department of Electrical and Computer Engineering University of Louisiana at Lafayette Lafayette United States Advanced Research Center for Computational Simulation Department of Mathematics Faculty of Science Chiang Mai University Chiang Mai50200 Thailand Data Science Research Center Department of Mathematics Faculty of Science Chiang Mai University Chiang Mai50200 Thailand

This paper proposes an adaptive fast-reaching nonsingular terminal sliding mode control approach for the position and attitude tracking control of a quadrotor UAV subject to model uncertainty and external disturbances. To this end, a fast-reaching nonsingular terminal sliding surface is defined with the aim of fast convergence of the tracking error. The fast reachability of the nonsingular terminal sliding surface is proven using the Lyapunov stability theory. Since, in practice, the upper bounds of model uncertainties and external disturbances are unknown, an adaptive control scheme is considered to approximate them. The fast-reaching nonsingular terminal sliding mode control approach was augmented with the adaptive scheme to ensure both, the fast convergence of the switching surfaces and the rejection of model uncertainties and external disturbances. The effectiveness of the proposed adaptive fast-reaching nonsingular terminal sliding mode control approach is assessed using simulations of a quadrotor system implemented in MATLAB/Simulink software. The obtained results are further compared to those of an existing approach in terms of tracking performance, robustness, and integrator of absolute-value of error criteria. © 2022 THE AUTHORS

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Rudin Extension Theorems on Product Spaces, Turning Bands, and Random Fields on Balls cross Time

arXiv

引用

arXiv 2022年

作者： Porcu, Emilio Feng, Samuel F. Emery, Xavier Peron, Ana Paula Department of Mathematics Research And Data Intelligence Support Center R-DISC Khalifa University Abu Dhabi United Arab Emirates School of Computer Science and Statistics Trinity College Dublin Ireland Millennium Nucleus Center for the Discovery of Structures in Complex Data Chile Deparment of Mining Engineering University of Chile Chile Advanced Mining Technology Center University of Chile Chile Department of Mathematics Institute of Mathematical and Computer Sciences University of São Paulo Brazil

Characteristic functions that are radially symmetric have a dual interpretation, as they can be used as the isotropic correlation functions of spatial random fields. Extensions of isotropic correlation functions from balls into d-dimensional Euclidean spaces, Rd, have been understood after Rudin. Yet, extension theorems on product spaces are elusive, and a counterexample provided by Rudin on rectangles suggest that the problem is quite challenging. This paper provides extension theorem for multiradial characteristic functions that are defined in balls embedded in Rd cross, either Rd′ or the unit sphere Sd′ embedded in Rd′+1, for any two positive integers d and d′. We then examine Turning Bands operators that provide bijections between the class of multiradial correlation functions in given product spaces, and multiradial correlations in product spaces having different dimensions. The combination of extension theorems with Turning Bands provides a connection with random fields that are defined in balls cross linear or circular time. © 2022, CC BY.

关键词：

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：