检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Jürgens, Mira Mortier, Thomas Hüllermeier, Eyke Bengs, Viktor Waegeman, Willem Department of Data Analysis and Mathematical Modeling Ghent University Belgium Department of Environment Ghent University Belgium Department of Informatics Munich Center for Machine Learning LMU Munich Germany

The accurate representation of epistemic uncertainty is a challenging yet essential task in machine learning. A widely used representation corresponds to convex sets of probabilistic predictors, also known as credal sets. One popular way of constructing these credal sets is via ensembling or specialized supervised learning methods, where the epistemic uncertainty can be quantified through measures such as the set size or the disagreement among members. In principle, these sets should contain the true data-generating distribution. As a necessary condition for this validity, we adopt the strongest notion of calibration as a proxy. Concretely, we propose a novel statistical test to determine whether there is a convex combination of the set’s predictions that is calibrated in distribution. In contrast to previous methods, our framework allows the convex combination to be instance dependent, recognizing that different ensemble members may be better calibrated in different regions of the input space. Moreover, we learn this combination via proper scoring rules, which inherently optimize for calibration. Building on differentiable, kernel-based estimators of calibration errors, we introduce a nonparametric testing procedure and demonstrate the benefits of capturing instance-level variability on of synthetic and real-world experiments. © 2025, CC BY.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Conformal Prediction in Hierarchical Classification

arXiv

引用

arXiv 2025年

作者： Mortier, Thomas Javanmardi, Alireza Sale, Yusuf Hüllermeier, Eyke Waegeman, Willem Department of Environment Ghent University Ghent Belgium Department of Data Analysis and Mathematical Modelling Ghent University Ghent Belgium Institute of Informatics LMU Munich Munich Germany Munich Center for Machine Learning Munich Germany

Conformal prediction has emerged as a widely used framework for constructing valid prediction sets in classification and regression tasks. In this work, we extend the split conformal prediction framework to hierarchical classification, where prediction sets are commonly restricted to internal nodes of a predefined hierarchy, and propose two computationally efficient inference algorithms. The first algorithm returns internal nodes as prediction sets, while the second relaxes this restriction, using the notion of representation complexity, yielding a more general and combinatorial inference problem, but smaller set sizes. Empirical evaluations on several benchmark datasets demonstrate the effectiveness of the proposed algorithms in achieving nominal coverage. © 2025, CC BY.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

RVPD: An Automated System for Calculating the Tortuosity and Bifurcation Angles of Retinal Vessels to Predict Diseases

RVPD: An Automated System for Calculating the Tortuosity and...

引用

IEEE International Symposium on Biomedical Imaging

作者： Guangzhengao Yang Xingyu Luo Jie Zhao Fangfang Fan Haoshen Li Bin Dong Li Zhang Yan Zhang Center for Data Science Peking University China Department of Cardiology Peking University First Hospital China National Engineering Laboratory for Big Data Analysis and Applications Peking University China Peking University Changsha Institute for Computing and Digital Economy China Beijing International Center for Mathematical Research Peking University China Center for Machine Learning Research Peking University China National Biomedical Imaging Center Peking University China

ISBN: (数字)9798331520526

ISBN: (纸本)9798331520533

Hypertension and diabetes are known to potentially cause morphological changes in the retinal capillary system, yet quantifying these changes presents significant challenges. This research addresses this issue by designing and developing an automated system capable of analyzing retinal images to detect and measure these changes. Our system automatically segments vessels and the optic disc, calculates tortuosity and bifurcation angles, and performs disease prediction based on these measurements along with clinical features. For tortuosity calculation, we adopted a novel curve fitting method, which provides more stable convergence compared to traditional discrete numerical methods. The system integrates clinical data and conducts prediction experiments on hypertensive and diabetic patients with varying sample sizes. Our results demonstrate the system's strong performance and scalability: in the hypertension group, the AUC reached a maximum of 0.814 ± 0.023, with an ACC of 0.735 ± 0.033, while in the diabetes group, the AUC reached a maximum of 0.710 ± 0.043, with an ACC of 0.641 ± 0.052. These findings suggest that our automated system could serve as a valuable tool for early detection and risk assessment of hypertension and diabetes, potentially improving patient outcomes through timely intervention.

关键词： Hypertension Image segmentation Scalability Bifurcation Optical variables measurement Optical imaging Retinal vessels Diabetes Risk management Diseases

来源：评论

学校读者我要写书评

暂无评论

Harmonizing Social and Production Indicators in the Way to Technological Sovereignty 15

Harmonizing Social and Production Indicators in the Way to T...

引用

15th International Conference Management of Large-Scale System Development, MLSD 2022

作者： Goroshko, Igor V. Smirnov, Mikhail V. Financial University Data Analysis and Machine Learning Department Moscow Russia

Achieving national technological sovereignty is a complex problem that combines the tasks of social and industrial development. The article contains the results of a study on elaborating mechanisms for harmonizing the... 详细信息

ISBN: (数字)9781665497015

ISBN: (纸本)9781665497015

关键词： Economic and social effects

来源：评论

学校读者我要写书评

暂无评论

The method of residual‑based bootstrap averaging of the forecast ensemble

引用

Financial Innovation 2023年第1期9卷 991-1002页

作者： Vera Ivanyuk Department of Data Analysis and Machine Learning Financial University49 Leningradsky ProspektMoscowRussia 125993

This paper presents an optimization approach—residual-based bootstrap averaging(RBBA)—for different types of forecast *** traditional residual-mean-square-error-based ensemble forecast averaging approaches,the RBBA method attempts to find optimal forecast weights in an ensemble and allows for their combi-nation into the most effective additive *** the RBBA method,all the different types of forecasts obtain the optimal weights for ensemble residuals that are statisti-cally optimal in terms of the fitness function of the *** studies have been conducted to demonstrate why and how the RBBA method *** experi-mental results based on the real-world time series of contemporary stock exchanges show that the RBBA method can produce ensemble forecasts with good generalization ability.

关键词： Forecast ensembles Time series Artificial neural networks

来源：评论

学校读者我要写书评

暂无评论

Application of factor analysis and neural networks for prediction in taxi service 14

Application of factor analysis and neural networks for predi...

引用

14th International Conference Management of Large-Scale System Development, MLSD 2021

作者： Andriyanov, Nikita Financial University Government of the Russian Federation Data Analysis and Machine Learning Department Moscow Russia

ISBN: (纸本)9781665412308

In this work, a study of multidimensional data on the operation of a taxi ordering service was carried out in order to predict the cost of an application. It is shown that it is possible to single out the main components, on the basis of which a sufficiently accurate prediction with respect to the initial data set is possible. © 2021 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Methodology for Training data Science Skills Based on Competitions on the Kaggle Platform

Methodology for Training Data Science Skills Based on Compet...

引用

2023 Seminar on Information Computing and Processing, ICP 2023

作者： Kalazhokov, Zaur Kh. Makoveichuk, Yan T. Financial University under the Government of the Russian Department of Data Analysis and Machine Learning Moscow Russia

ISBN: (纸本)9798350369830

The article describes the experience of teaching students of Big data analytics-related fields the basics of data science. The teaching methodology used at the Financial University under the Government of the Russian Federation is given, which consists in involvement of students of the group to competitions on Google Kaggle platform. In this methodology, the positive factors influencing the rapid acquisition of initial data science skills are: competitive effect;availability of prepared datasets and problem formulations from the real business sector in various directions;possibility of instant verification of the found solution;practical unlimited number of solutions. These factors contribute to the rapid understanding by students of the need to understand the essence of the problem for the best results, obligatory familiarization with the data, data cleaning and formatting, exploratory data analysis, forming a model with some basic level and its improvement, as well as interpretation. © 2023 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

IRIS: A Bayesian Approach for Image Reconstruction in Radio Interferometry with expressive Score-Based priors

arXiv

引用

arXiv 2025年

作者： Dia, Noé Yantovski-Barth, M.J. Adam, Alexandre Bowles, Micah Perreault-Levasseur, Laurence Hezaveh, Yashar Scaife, Anna Université de Montréal Montréal Canada Mila - Quebec Artificial Intelligence Institute Montréal Canada Ciela - Montreal Institute for Astrophysical Data Analysis and Machine Learning Montréal Canada Department of Astrophysics University of Oxford Oxford United Kingdom Flatiron Institute Center for Computational Astrophysics New York United States Perimeter Institute Waterloo Canada Trottier Space Institute McGill University Montréal Canada University of Manchester Manchester United Kingdom The Alan Turing Institute United Kingdom

Inferring sky surface brightness distributions from noisy interferometric data in a principled statistical framework has been a key challenge in radio astronomy. In this work, we introduce Imaging for Radio Interferometry with Score-based models (IRIS). We use score-based models trained on optical images of galaxies as an expressive prior in combination with a Gaussian likelihood in the uv-space to infer images of protoplanetary disks from visibility data of the DSHARP survey conducted by ALMA. We demonstrate the advantages of this framework compared with traditional radio interferometry imaging algorithms, showing that it produces plausible posterior samples despite the use of a misspecified galaxy prior. Through coverage testing on simulations, we empirically evaluate the accuracy of this approach to generate calibrated posterior samples. Our code is open source and freely available at https://***/EnceladeCandy/IRIS. © 2025, CC BY.

关键词： Gaussian distribution

来源：评论

学校读者我要写书评

暂无评论

analysis of the Restrictive Measures Impact on the Disease Spread 7

Analysis of the Restrictive Measures Impact on the Disease S...

引用

7th IEEE International Conference on Information Technology and Nanotechnology, ITNT 2021

作者： Andriyanov, Nikita Korovin, Dmitry Financial University under the Government of the Russian Federation Data Analysis and Machine Learning Department Moscow Russia

ISBN: (纸本)9781665432177

The study focuses on the statistical analysis of information about diseases spreading. To obtain data, specialized application programming interfaces (APIs) in the Python language are used. data from Johns Hopkins University Center for Systems Science and Engineering (JHU CSSE) and data from the Oxford dataset OxCGRT were considered as data sources. On the basis of the data obtained, such indicators as detected cases, the proportion of deaths and the proportion of recovery are investigated. The analysis is for countries around the world. At the same time, data for TOP-9 countries are visualized. In addition, the work is devoted to the study of the impact of measures taken by the Government to contain the spread of the infection. data for the Russian Federation, France and the USA are being processed. Finally, a simulation model of migration and spread of the disease with open and closed borders between cities is considered. The analysis showed that the countermeasures taken, although they are tough and restrictive, have an effective effect on reducing the rate of spread of the infection. © 2021 IEEE.

关键词： Time series analysis

来源：评论

学校读者我要写书评

暂无评论

Using Control Charts with Variable Control Limits in Statistical Process Control 5

Using Control Charts with Variable Control Limits in Statist...

引用

5th International Conference on Control Systems, Mathematical Modeling, Automation and Energy Efficiency, SUMMA 2023

作者： Zhuravlyova, Marina Financial University under the Government of the Russian Federation Department of Data Analysis and Machine Learning Moscow Russia

ISBN: (纸本)9798350309126

The procedure of building control charts with variable control limits based on nonparametric bootstrap percentile method is proposed. It makes possible to construct control chart of any statistic with unknown continuous distribution and involves a large number of calculations. The order of building one of the scalar statistics to be monitored for the group of mutually dependent quality characteristics is considered. Formulas for obtaining variable control limits based on percentile method are shown. The issue of identifying the structure of relationships between quality characteristics is raised. Proposed control chart, Hotelling T2 and Shewhart usual control charts and their modifications for variable control limits have been constructed using actual data of two characteristics of the rolled steel manufacturing process. It is concluded that the development of the proposed approach can be useful in statistical process control. © 2023 IEEE.

关键词： Control charts

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：