检索结果-内蒙古大学图书馆

Remote Research System of Archaeological Sites Using Deep Learning

PATTERN RECOGNITION AND IMAGE ANALYSIS 2024年第3期34卷 574-582页

作者： Vokhmintcev, A. V. Melnikov, A. V. Romanov, M. A. Shitselov, A. V. Chelyabinsk State Univ Chelyabinsk 454001 Russia Yugra State Univ Khanty Mansiysk 628012 Russia Yugra Res Inst Informat Technol Khanty Mansiysk 628012 Russia

This work is devoted to the problem of detecting and studying archaeological sites based on methods of machine learning, mapping, and geophysics. The article discusses the methodology for mapping and surveying archaeological objects in the form of 2D and 3D models, and proposes machine learning methods based on convolutional neural networks for the detection and classification of archaeological objects.

关键词： residual neural networks data classification data segmentation archaeological site

来源：评论

学校读者我要写书评

暂无评论

Time series data analysis using Artificial Immune System

引用

INTELLIGENT DECISION TECHNOLOGIES-NETHERLANDS 2018年第2期12卷 119-135页

作者： Ahmad, Waseem Narayanan, Ajit Toi Ohomai Inst Technol Tauranga New Zealand AUT Univ Auckland New Zealand

Extracting knowledge from temporal data has become an important topic of research for data mining researchers due to its wide range of applications in real world problems, such as finding patterns in weather data for forecasting, stock market data for prediction and industrial production indices forecasting. In this paper, a novel time series data analysis approach inspired by the processes of natural immune system is proposed. The approach is layered where, firstly, segmentation is used to subdivide the complete time series data into sub-sequences and, secondly, an Artificial Immune System (AIS) algorithm is used to analyse and cluster segmented data. Finally, this clustering information is used to build a model for forecasting and prediction. The effectiveness of the proposed approach is demonstrated by testing it on various non-linear cyclic time series data and results are compared against linear regression and multi-layer perceptrons.

关键词： Temporal data mining Artificial Immune System data segmentation clustering B-cells antibodies

来源：评论

学校读者我要写书评

暂无评论

θ, β But not α-band EEG connectivity has implications for dual task performance in Parkinson's disease

引用

PARKINSONISM & RELATED DISORDERS 2010年第6期16卷 393-397页

作者： Palmer, Samantha J. Lee, Pamela Wen-Hsin Wang, Z. Jane Au, Wing-Lok McKeown, Martin J. Univ British Columbia Pacific Parkinsons Res Ctr Vancouver BC V6T 2B5 Canada Univ British Columbia Dept Elect & Comp Engn Vancouver BC V6T 2B5 Canada Natl Inst Neurosci Dept Neurol Parkinsons Dis & Movement Disorders Ctr Singapore Singapore Univ British Columbia Dept Med Neurol Vancouver BC V6T 2B5 Canada Univ British Columbia Brain Res Ctr Vancouver BC V6T 2B5 Canada

People with Parkinson's disease (PD) have difficulty performing dual tasks or simultaneous movements, even if the same movements can be easily performed individually. This has particular significance clinically, as for example falling injuries may occur if care is not taken to perform tasks one at a time. We investigated whether this difficultyx results from impaired dopamine-modulated connectivity. We recorded the EEG in PD subjects off and on L-dopa medication performing simultaneous and unimanual tracking tasks. To deal with the inherent non-stationarity of the EEG during motor tasks, we segmented the data into task-related sections based on transient synchronisation between independent components of the data, before assessing the mutual information (MI) between each EEG channel pair. In both tasks, PD subjects off-medication demonstrated enhanced fronto-central and decreased occipital synchronisation within theta and alpha bands, and widespread increased beta-band synchronisation, compared to controls. Synchronisation changes in theta and beta bands were partially normalised by L-dopa, but L-dopa had relatively little effect on alpha band synchronisation. When comparing simultaneous movements to unimanual tracking, PD subjects off-medication demonstrated synchronisation changes within theta and beta bands, however alpha connectivity was largely unchanged. These results suggest that downstream influences of impaired basal ganglia function on cortico-cortical connectivity may result in difficulties with dual task performance in PD. (C) 2010 Elsevier Ltd. All rights reserved.

关键词： L-dopa Mutual information Parkinson disease EEG data segmentation Independent Component Analysis (ICA)

来源：评论

学校读者我要写书评

暂无评论

Fast local reconstruction methods for nonuniform sampling in shift-invariant spaces

引用

SIAM JOURNAL ON MATRIX ANALYSIS AND APPLICATIONS 2003年第4期24卷 899-913页

作者： Gröchenig, K Schwab, H Univ Connecticut Dept Math Storrs CT 06269 USA Univ Vienna Dept Math NUHAG A-1090 Vienna Austria

We present a new method for the fast reconstruction of a function f from its samples f(x(j)) under the assumption that f belongs to a shift-invariant space V (phi). If the generator phi has compact support, then the reconstruction is local, quite in contrast to methods based on band-limited functions. Using frame theoretic arguments, we show that the matrix of the corresponding linear system of equations is a positive-definite banded matrix. This special structure makes possible the fast local reconstruction algorithm in O(S(2)J) operations, where J is the number of samples and S is the support length of the generator phi. Further optimization can be achieved by means of data segmentation. Ample numerical simulation is provided.

关键词： shift-invariant space nonuniform sampling banded matrix localization data segmentation denoising

来源：评论

学校读者我要写书评

暂无评论

Segmenting Input data to Improve the Quality of Identification of Information Security Events

引用

AUTOMATIC CONTROL AND COMPUTER SCIENCES 2024年第8期58卷 1192-1203页

作者： Sukhoparov, M. E. Lebedev, I. S. Tikhonov, D. D. Russian State Hydrometeorol Univ St Petersburg 192007 Russia Russian Acad Sci St Petersburg Fed Res Ctr St Petersburg 199178 Russia

The processing of information sequences using segmentation of input data, aimed at improving the quality indicators of destructive impact detection using machine learning models is proposed. The basis of the proposed solution is the division of data into segments with different properties of the objects of observation. A method is described that uses a multilevel data processing architecture, where the processes of training, analysis of the achieved values of quality indicators, and assignment of the best models for quality indicators to individual data segments are implemented at various levels. The proposed method allows us to improve the quality indicators of the detection of destructive information impacts through segmentation and assignment of models that have the best indicators in individual segments.

关键词： information security machine learning data sets data sampling data segmentation processing models

来源：评论

学校读者我要写书评

暂无评论

CT evaluation prior to transapical aortic valve replacement: semi-automatic versus manual image segmentation

引用

INTERNATIONAL JOURNAL OF CARDIOVASCULAR IMAGING 2015年第6期31卷 1233-1242页

作者： Foldyna, Borek Jungert, Camelia Luecke, Christian von Aspern, Konstantin Boehmer-Lasthaus, Sonja Rueth, Eva Maria Grothoff, Matthias Nitzsche, Stefan Gutberlet, Matthias Mohr, Friedrich Wilhelm Lehmkuhl, Lukas Univ Leipzig Ctr Heart Dept Intervent & Diagnost Radiol D-04289 Leipzig Germany Univ Leipzig Ctr Heart Dept Cardiac Surg D-04289 Leipzig Germany Siemens Healthcare Imaging & Therapy Erlangen Germany

To compare the performance of semi-automatic versus manual segmentation for ECG-triggered cardiovascular computed tomography (CT) examinations prior to transcatheter aortic valve replacement (TAVR), with focus on the speed and precision of experienced versus inexperienced observers. The preoperative ECG-triggered CT data of 30 consecutive patients who were scheduled for TAVR were included. All datasets were separately evaluated by two radiologists with 1 and 5 years of experience (novice and expert, respectively) in cardiovascular CT using an evaluation software program with or without a semi-automatic TAVR workflow. The time expended for data loading and all segmentation steps required for the implantation planning were assessed. Inter-software as well as inter-observer reliability analysis was performed. The CT datasets were successfully evaluated, with mean duration between 520.4 +/- A 117.6 s and 693.2 +/- A 159.5 s. The three most time-consuming steps were the 3D volume rendering, the measurement of aorta diameter and the sizing of the aortic annulus. Using semi-automatic segmentation, a novice could evaluate CT data approximately 12.3 % faster than with manual segmentation, and an expert could evaluate CT data approximately 10.3 % faster [mean differences of 85.4 +/- A 83.8 s (p < 0.001) and 59.8 +/- A 101 s (p < 0.001), respectively]. The inter-software reliability for a novice was slightly lower than for an expert;however, the reliability for a novice and expert was excellent (ICC 0.92, 95 % CI 0.75-0.97/ICC 0.96, 95 % CI 0.91-0.98). Automatic aortic annulus detection failed in two patients (6.7 %). The study revealed excellent inter-software and inter-observer reliability, with a mean ICC of 0.95. TAVR evaluation can be accomplished significantly faster with semi-automatic rather than with manual segmentation, with comparable exactness, showing a benefit for experienced and inexperienced observers.

关键词： Transapical valve replacement Aortic valve Computed tomography data segmentation data evaluation Experienced versus inexperienced users Efficiency

来源：评论

学校读者我要写书评

暂无评论

Multiple change point detection under serial dependence: Wild contrast maximisation and gappy Schwarz algorithm

引用

JOURNAL OF TIME SERIES ANALYSIS 2024年第3期45卷 479-494页

作者： Cho, Haeran Fryzlewicz, Piotr Univ Bristol Sch Math Fry Bldg Bristol BS8 1UG England London Sch Econ Dept Stat London England

We propose a methodology for detecting multiple change points in the mean of an otherwise stationary, autocorrelated, linear time series. It combines solution path generation based on the wild contrast maximisation principle, and an information criterion-based model selection strategy termed gappy Schwarz algorithm. The former is well-suited to separating shifts in the mean from fluctuations due to serial correlations, while the latter simultaneously estimates the dependence structure and the number of change points without performing the difficult task of estimating the level of the noise as quantified e.g. by the long-run variance. We provide modular investigation into their theoretical properties and show that the combined methodology, named ***, achieves consistency in estimating both the total number and the locations of the change points. The good performance of *** is demonstrated via extensive simulation studies, and we further illustrate its usefulness by applying the methodology to London air quality data.

关键词： data segmentation wild binary segmentation information criterion autoregressive time series

来源：评论

学校读者我要写书评

暂无评论

Automated System Identification in Mineral Processing Industries: A Case Study using the Zinc Flotation Cell

引用

IFAC-PapersOnLine 2018年第18期51卷 132-137页

作者： Shardt, Yuri A.W. Brooks, Kevin Technical University of Ilmenau Ilmenau Canada BluESP 53 Platina St Randburg South Africa

In many industries, including the mineral processing industry, process modelling can be improved by mining the data historian. However, the data in the historian is often contaminated with missing values, unknown operating conditions, and other imperfections. Furthermore, manual segmentation of the data is difficult due to the large number of data points and variables. Thus, there is a need to develop and implement methods that can automatically segment the data set into viable components for identification purposes. One approach uses Laguerre models to segment the data set. However, when used in a multivariate situation, such as in the zinc flotation cell, various issues, such as collinearity, arise. Therefore, the data segmentation algorithm needs to take this into consideration when examining a data set. Using the zinc flotation cell, it is shown that for the multivariate case preselecting the data variables to consider improves the data segmentation. © 2018

关键词： Cells Automation Cytology data mining Flotation History Identification (control systems) Mineral industry Religious buildings Zinc Automated systems data segmentation Flotation cell Manual segmentation Mineral processing industry Number of datum Operating condition Process modelling

来源：评论

学校读者我要写书评

暂无评论

Improving the Quality of the Identification of the Information Security State Based on Sample segmentation

引用

AUTOMATIC CONTROL AND COMPUTER SCIENCES 2023年第8期57卷 1071-1075页

作者： Sukhoparov, M. E. Lebedev, I. S. Russian State Hydrometeorol Univ St Petersburg 192007 Russia Russian Acad Sci St Petersburg Fed Res Ctr St Petersburg 199178 Russia

Increasing the quality indicators for identifying the information security (IS) state of individual segments of cyber-physical systems is related to processing large information arrays. A method for improving quality indicators when solving problems of identifying the IS state is proposed. Its implementation is based on the formation of individual sample segments. Analysis of the properties of these segments makes it possible to select and assign algorithms that have the best quality indicators in the current segment. segmentation of a data sample is considered. Using real dataset data as an example, experimental values of the quality indicator for the proposed method are given for various classifiers on individual segments and the entire sample.

关键词： information security machine learning data set data segmentation data sampling

来源：评论

学校读者我要写书评

暂无评论

On automated cloud bursting and hybrid cloud setups using Apache Mesos

引用

CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE 2020年第17期32卷

作者： Haugerud, Harek Xue, Noha Yazidi, Anis Oslo Metropolitan Univ Dept Comp Sci Oslo Norway Oslo Metropolitan Univ POB 4 N-0130 Oslo Norway

Hybrid cloud technology is becoming increasingly popular as it merges private and public clouds to bring the best of two worlds together. However, due to the heterogeneous cloud installation, facilitating a hybrid cloud setup is not simple. Despite some commercial solutions being available to build a hybrid cloud, an open-source implementation is still unavailable. In this paper, we try to bridge the gap by providing an open-source implementation using the power of Apache Mesos. We build a hybrid cloud on top of multiple cloud platforms, private and public. Through comprehensive experimental results, we show that our solution is able to ensure resource bursting by leveraging the power of the public cloud.

关键词： Apache Mesos cloud bursting data segmentation fault tolerance open-source hybrid cloud

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：