检索结果-内蒙古大学图书馆

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

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

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

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

Determining the Genre of Music from a Melody Using machine learning and Parallel data Processing

Determining the Genre of Music from a Melody Using Machine L...

引用

2023 Seminar on Information Computing and Processing, ICP 2023

作者： Solodennikov, Danila A. Makoveichuk, Krystina A. Financial University under the Government of the Russian Federation Department of Data Analysis and Machine Learning Moscow Russia

ISBN: (纸本)9798350369830

This article describes the author's methodology for determining the genre of music from a melody using machine learning and parallel data processing. For determination is used dataset formed by the author, on the basis of which the model is trained and the genre is predicted on the test data. Yandex technologies, parallel programming, and Python data processing models are used in the work. There are also examples of training and test samples, model operation, data cleaning and dataset analysis methods. The work built neural network to identify genres and output results. The results vary from 35% to 50% and it should be noted that the dataset is rather small, so with bigger dataset we can await much higher result. © 2023 IEEE.

关键词： machine learning

来源：评论

学校读者我要写书评

暂无评论

Using Generative Models to Improve Fire Detection Efficiency 10

Using Generative Models to Improve Fire Detection Efficiency

引用

10th International Conference on Information Technology and Nanotechnology, ITNT 2024

作者： Andriyanov, Nikita Kim, Alexandr Fao, Xenin Data Analysis And Machine Learning Department Financial University Under The Government Of The Russian Federation Moscow Russia Data Science Department Huazhong University Of Science And Technology Huazhong China

ISBN: (纸本)9798350372939

The paper discusses generative artificial intelligence technologies used to improve the efficiency of fire detection in satellite images. Different detector architectures are proposed and compared in terms of accuracy. It is found that the use of generative models to expand the training sample is on average 1-2% more effective than the use of standard augmentations. The combined method of expanding the training image base can improve the accuracy by 4-5%. In addition, the right approach in generative prompts can also improve the accuracy metrics of the models. © 2024 IEEE.

关键词： Generative adversarial networks

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

A machine learning Approach to Exploring Ecological Determinacy of Socially Significant Diseases in Moscow 16

A Machine Learning Approach to Exploring Ecological Determin...

引用

16th International Conference Management of Large-Scale System Development, MLSD 2023

作者： Marunko, Anna Zolotova, Tatiana Financial University under the Government of the Russian Federation Faculty of Information Technology and Big Data Analysis Moscow Russia Financial University under the Government of the Russian Federation Department of Data Analysis and Machine Learning Moscow Russia

ISBN: (纸本)9798350337907

A study of the relationship between some selected environmental indicators and the presence of socially significant diseases in the population of Moscow was carried out. A statistically significant correlation was confirmed. machine learning models were built during the regression analysis. A web interface was developed to automate the processes of predicting the population's morbidity. © 2023 IEEE.

关键词： Ecology

来源：评论

学校读者我要写书评

暂无评论

Estimating Object Coordinates Using Convolutional Neural Networks and Intel Real Sense D415/D455 Depth Maps 8

Estimating Object Coordinates Using Convolutional Neural Net...

引用

8th International Conference on Information Technology and Nanotechnology, ITNT 2022

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

ISBN: (数字)9781665485715

ISBN: (纸本)9781665485715

The paper considers the problem of estimating the coordinates of objects detected from a video sequence of images from an Intel Real Sense cameras. An object detection system was developed by using the YOLOv5 convolutional neural network. An algorithm for estimating detected objects coordinates in three-dimensional space was implemented based on the joint processing of information from depth maps and the pixel coordinates of objects in the image. The conducted comparative analysis with the method of instrumental measurements showed a low root mean square error of the proposed algorithm. In addition, comparative studies have been conducted for the Intel Real Sense D415 series and D455 series cameras. © 2022 IEEE.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Pitfalls of Epistemic Uncertainty Quantification through Loss Minimisation 36

Pitfalls of Epistemic Uncertainty Quantification through Los...

引用

36th Conference on Neural Information Processing Systems, NeurIPS 2022

作者： Bengs, Viktor Hüllermeier, Eyke Waegeman, Willem Germany Munich Center for Machine Learning Germany Department of Data Analysis and Mathematical Modeling Ghent University Belgium

ISBN: (纸本)9781713871088

Uncertainty quantification has received increasing attention in machine learning in the recent past. In particular, a distinction between aleatoric and epistemic uncertainty has been found useful in this regard. The latter refers to the learner's (lack of) knowledge and appears to be especially difficult to measure and quantify. In this paper, we analyse a recent proposal based on the idea of a second-order learner, which yields predictions in the form of distributions over probability distributions. While standard (first-order) learners can be trained to predict accurate probabilities, namely by minimising suitable loss functions on sample data, we show that loss minimisation does not work for second-order predictors: The loss functions proposed for inducing such predictors do not incentivise the learner to represent its epistemic uncertainty in a faithful way. © 2022 Neural information processing systems foundation. All rights reserved.

关键词： Probability distributions

来源：评论

学校读者我要写书评

暂无评论

Econometric Modeling of the Company's Intellectual Capital in the Context of Digitalization 16

Econometric Modeling of the Company's Intellectual Capital i...

引用

16th International Conference Management of Large-Scale System Development, MLSD 2023

作者： Grineva, Natalia Mikhailova, Svetlana Kontsevaya, Natalia Financial University under the Government of the Russian Federation Department of Data Analysis and Machine Learning Moscow Russia Financial University under the Government of the Russian Federation Department of Mathematics Moscow Russia

ISBN: (纸本)9798350337907

An approach to assessing the value of intellectual capital has been developed. Models demonstrating the impact of intellectual capital and its components on the financial performance of companies implementing a digital transformation strategy have been constructed. The influence of R&D investments on company performance has been evaluated, and strategic modeling of enterprise revenue growth rates has been conducted. © 2023 IEEE.

关键词： Knowledge management

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：