检索结果-内蒙古大学图书馆

Information Technology and Nanotechnology (ITNT), International Conference on

作者： Nikita Andriyanov Alexandr Kim Xenin Fao 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: (数字)9798350372939

ISBN: (纸本)9798350372946

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.

关键词： Training Measurement YOLO Accuracy Image databases Detectors Satellite images

来源：评论

学校读者我要写书评

暂无评论

Sharpening the dark matter signature in gravitational waveforms. II. Numerical simulations

引用

Physical Review D 2025年第6期111卷 063071-063071页

作者： Bradley J. Kavanagh Theophanes K. Karydas Gianfranco Bertone Pierfrancesco Di Cintio Mario Pasquato Instituto de Física de Cantabria (IFCA UC-CSIC) Avenue de Los Castros s 39005 Santander Spain Gravitation Astroparticle Physics Amsterdam (GRAPPA) Institute for Theoretical Physics Amsterdam and Delta Institute for Theoretical Physics University of Amsterdam Science Park 904 1098 XH Amsterdam The Netherlands Consiglio Nazionale delle Ricerche Istituto dei Sistemi Complessi (CNR-ISC) via Madonna del Piano 17 50022 Sesto Fiorentino (FI) Italy INAF-Osservatorio Astronomico di Arcetri Largo Enrico Fermi 5 50125 Firenze Italy INFN-Sezione di Firenze Via Giovanni Sansone 1 50022 Sesto Fiorentino Italy Département de Physique Université de Montréal 1375 Avenue Thérèse-Lavoie-Roux Montréal Canada Mila—Quebec Artificial Intelligence Institute 6666 Rue Saint-Urbain Montréal Canada Ciela—Montréal Institute for Astrophysical Data Analysis and Machine Learning Montréal Canada Dipartimento di Fisica e Astronomia Università di Padova Vicolo dell’Osservatorio 5 Padova Italy Istituto Nazionale di Fisica Nucleare Padova Via Marzolo 8 Padova Italy

Future gravitational wave observatories can probe dark matter by detecting the dephasing in the waveform of binary black hole mergers induced by dark matter overdensities. Such a detection hinges on the accurate modeling of the dynamical friction, induced by dark matter on the secondary compact object in intermediate and extreme mass ratio inspirals. In this paper, we introduce nbodyimri, a new publicly available code designed for simulating binary systems within cold dark matter spikes. Leveraging higher particle counts and finer time steps, we validate the applicability of the standard dynamical friction formalism and provide an accurate determination of the maximum impact parameter of particles which can effectively scatter with a compact object, across various mass ratios. We also show that in addition to feedback due to dynamical friction, the dark matter also evolves through a stirring effect driven by the time-dependent potential of the binary. We introduce a simple semianalytical scheme to account for this effect and demonstrate that including stirring tends to slow the rate of dark matter depletion and therefore enhances the impact of dark matter on the dynamics of the binary.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Applying convolutional neural networks for stock market trends identification

arXiv

引用

arXiv 2021年

作者： Zolotareva, Ekaterina Data Analysis and Machine Learning Department Financial University under the Government of the Russian Federation 38 Shcherbakovskaya St. Moscow105187 Russia

In this paper we apply a specific type ANNs - convolutional neural networks (CNNs) - to the problem of finding start and endpoints of trends, which are the optimal points for entering and leaving the market. We aim to explore long-term trends, which last several months, not days. The key distinction of our model is that its labels are fully based on expert opinion data. Despite the various models based solely on stock price data, some market experts still argue that traders are able to see hidden opportunities. The labelling was done via the GUI interface, which means that the experts worked directly with images, not numerical data. This fact makes CNN the natural choice of algorithm. The proposed framework requires the sequential interaction of three CNN submodels, which identify the presence of a changepoint in a window, locate it and finally recognize the type of new tendency - upward, downward or flat. These submodels have certain pitfalls, therefore the calibration of their hyperparameters is the main direction of further research. The research addresses such issues as imbalanced datasets and contradicting labels, as well as the need for specific quality metrics to keep up with practical applicability. This paper is the full text of the research, presented at the 20th International Conference on Artificial Intelligence and Soft Computing Web System (ICAISC 2021). © 2021, CC BY-NC-ND.

关键词： Image recognition

来源：评论

学校读者我要写书评

暂无评论

A novel brain-computer interface based on the rapid serial visual presentation paradigm

A novel brain-computer interface based on the rapid serial v...

引用

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

作者： Laura Acqualagna Matthias Sebastian Treder Martijn Schreuder Benjamin Blankertz Università degli Studi di Genova Genova Italy Machine Learning Laboratory Berlin Institute of Technology Germany Berlin Institute of Technology Machine Learning Laboratory Germany Fraunhofer FIRST Intelligent Data Analysis group Berlin Germany

Most present-day visual brain computer interfaces (BCIs) suffer from the fact that they rely on eye movements, are slow-paced, or feature a small vocabulary. As a potential remedy, we explored a novel BCI paradigm consisting of a central rapid serial visual presentation (RSVP) of the stimuli. It has a large vocabulary and realizes a BCI system based on covert non-spatial selective visual attention. In an offline study, eight participants were presented sequences of rapid bursts of symbols. Two different speeds and two different color conditions were investigated. Robust early visual and P300 components were elicited time-locked to the presentation of the target. Offline classification revealed a mean accuracy of up to 90% for selecting the correct symbol out of 30 possibilities. The results suggest that RSVP-BCI is a promising new paradigm, also for patients with oculomotor impairments.

关键词： Image color analysis Visualization Accuracy Electrodes Vocabulary Electric potential Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Forecasting Financial Time Series Based on the Ensemble Method 15

Forecasting Financial Time Series Based on the Ensemble Meth...

引用

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

作者： Ivanyuk, Vera Tsvirkun, Anatoly Soloviev, Vladimir Feklin, Vadim Sunchalina, Anna Kravchenko, Oleg Financial University under the Government of the Russian Federation Department of Data Analysis and Machine Learning Moscow Russia Bauman Moscow State Technical University Department of Higher Mathematics Moscow Russia Laboratory of Management of the Development of Large-scale Systems V.A. Trapeznikov Institute of Control Sciences of Ras Moscow Russia

The study considers methods for forecasting financial time series. We construct an ensemble forecast based on the linear forecast, ETS forecast, and neural forecast methods. Thereupon, we evaluate the quality of the f... 详细信息

ISBN: (数字)9781665497015

ISBN: (纸本)9781665497015

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

Uncertainty Estimation and Propagation in Accelerated MRI Reconstruction

arXiv

引用

arXiv 2023年

作者： Fischer, Paul Küstner, Thomas Baumgartner, Christian F. Cluster of Excellence – Machine Learning for Science University of Tübingen Germany Medical Image and Data Analysis Lab University Hospital of Tübingen Germany

MRI reconstruction techniques based on deep learning have led to unprecedented reconstruction quality especially in highly accelerated settings. However, deep learning techniques are also known to fail unexpectedly and hallucinate structures. This is particularly problematic if reconstructions are directly used for downstream tasks such as real-time treatment guidance or automated extraction of clinical paramters (e.g. via segmentation). Well-calibrated uncertainty quantification will be a key ingredient for safe use of this technology in clinical practice. In this paper we propose a novel probabilistic reconstruction technique (PHiRec) building on the idea of conditional hierarchical variational autoencoders. We demonstrate that our proposed method produces high-quality reconstructions as well as uncertainty quantification that is substantially better calibrated than several strong baselines. We furthermore demonstrate how uncertainties arising in the MR reconstruction can be propagated to a downstream segmentation task, and show that PHiRec also allows well-calibrated estimation of segmentation uncertainties that originated in the MR reconstruction process. Copyright © 2023, The Authors. All rights reserved.

关键词： Uncertainty analysis

来源：评论

学校读者我要写书评

暂无评论

learning invariances with Stationary Subspace analysis

Learning invariances with Stationary Subspace Analysis

引用

International Conference on Computer Vision Workshops (ICCV Workshops)

作者： Frank C. Meinecke Paul von Bünau Motoaki Kawanabe Klaus-R. Müller Machine Learning Group Department Computer Science Technical University Berlin Berlin Germany Intelligent Data Analysis Group Fraunhofer FIRST (IDA) Berlin Germany

Recently, a novel subspace decomposition method, termed `Stationary Subspace analysis' (SSA), has been proposed by Bu¿nau et al.. SSA aims to find a linear projection to a lower dimensional subspace such that the distribution of the projected data does not change over successive epochs or sub-datasets. We show that by modifying the loss function and the optimization procedure we can obtain an algorithm that is both faster and more accurate. We discuss the problem of indeterminacies and provide a lower bound on the number of epochs that is needed. Finally, we show in an experiment with simulated image patches, that SSA can be used favourably in invariance learning.

关键词： Space stations Cost function Conferences machine learning Computer science learning systems data analysis Brain modeling Feature extraction Brain computer interfaces

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 22

Pitfalls of epistemic uncertainty quantification through los...

引用

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Viktor Bengs Eyke Hüllermeier Willem Waegeman Institute of Informatics University of Munich (LMU) Institute of Informatics University of Munich (LMU) and Munich Center for Machine Learning Department of Data Analysis and Mathematical Modeling Ghent University

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.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Object Segmentation Tracking from Generic Video Cues

Object Segmentation Tracking from Generic Video Cues

引用

International Conference on Pattern Recognition

作者： Amirhossein Kardoost Sabine Müller Joachim Weickert Margret Keuper Data and Web Science Group University of Mannheim Mannheim Germany Fraunhofer Center Machine Learning Germany Mathematical Image Analysis Group Saarland University Saarbrücken Germany

We propose a light-weight variational framework for online tracking of object segmentations in videos based on optical flow and image boundaries. While high-end computer vision methods on this task rely on sequence specific training of dedicated CNN architectures, we show the potential of a variational model, based on generic video information from motion and color. Such cues are usually required for tasks such as robot navigation or grasp estimation. We leverage them directly for video object segmentation and thus provide accurate segmentations at potentially very low extra cost. Our simple method can provide competitive results compared to the costly CNN-based methods with parameter tuning. Furthermore, we show that our approach can be combined with state-of-the-art CNN-based segmentations in order to improve over their respective results. We evaluate our method on the datasets DAVIS16,17 and SegTrack v2.

关键词： Training Navigation Annotations Video sequences Estimation Object segmentation Task analysis

来源：评论

学校读者我要写书评

暂无评论

Information Security Control Engineering for an Industrial Company with “1C” Software

Information Security Control Engineering for an Industrial C...

引用

Electrical, Computer and Energy Technologies (ICECET), International Conference on

作者： Alexey Yu. Zalozhnev Dmitry V. Chistov Active Systems Laboratory V.A. Trapeznikov Institute of Control Sciences Russian Academy of Sciences Moscow Russia Department of Data Analysis and Machine Learning Financial University Moscow Russia

The issues related to information security control engineering for an industrial company with “1C” software are considered in this paper. The article discusses the types of threats to the company's information resources, including collective knowledge stored on electronic media. The paper contains standards and other documents governing the development and operation of an industrial company's information security. A brief description of the 1C software platform and 1C ERP is given. To prevent unauthorized access to the IT infrastructure and misappropriation of information important to the client, a set of needed organizational and technical measures with the use of 1C software products is considered. Some practical conclusions are also given.

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：