检索结果-内蒙古大学图书馆

International Conference on Communications (COMM)

作者： Raluca Oncioiu Emil Simion Faculty of Automatic Control and Computer Science University Politehnica of Bucharest

ISBN: (纸本)9781538623510;9781538623503

Denial-of-service (DOS) attacks are the most frequent attacks in Cloud. Usually this type of attack consists in sending a large number of requests that will overwhelm the functioning of Cloud. DOS attack implies IP spoofing because each request needs to be different. So the server will consume its resources and it will not be able to reply to a legitimate connection request. SYN floods are the second most common type of DOS attack for Cloud in the last 3 years. SYN floods exploit the flaws in TCP three-way handshake procedures. The attacker sends multiple SYN requests from a spoofed IP address. The server will allocate all the resources needed without receiving any ACK from the attacker. We propose an approach of solving this type of attack for Big Data in Cloud while respecting the Service Level Agreement (SLA) and show that the improvement is considerable.

关键词： Cloud computing Servers IP networks Big Data Protocols Operating systems Monitoring

来源：评论

学校读者我要写书评

暂无评论

On asymptotic properties of discrete Volterra equations of convolution type

On asymptotic properties of discrete Volterra equations of c...

引用

International Conference on Methods and Models in Automation and Robotics (MMAR)

作者： Pham The Anh Artur Babiarz Adam Czornik Michał Niezabitowski Stefan Siegmund Department of Mathematics Le Quy Don Technical University Ha noi Vietnam Faculty of Automatic Control Electronics and Computer Science Silesian University of Technology Gliwice Poland Faculty of Mathematics Technische Universität Dresden Dresden Germany

This paper discusses dynamic properties of discrete Volterra equations of convolution type. The asymptotic separation of solutions is studied. More precisely, a polynomial lower bound for the norm of differences between two different solutions of discrete Volterra equations of convolution type is presented. We apply this result to the theory of fractional difference equations.

关键词： Mathematical model Convolution Difference equations Stability analysis Asymptotic stability computer science

来源：评论

学校读者我要写书评

暂无评论

Local search algorithms for memetic algorithms: understanding behaviors using biological intelligence

Local search algorithms for memetic algorithms: understandin...

引用

International Conference on System Theory, control, and Computing (ICSTCC)

作者： Beatrice Luca Mitica Craus Department of Computer Science Faculty of Automatic Control and Computer Engineering Iasi Romania

Memetic Algorithms (MAs) are a class of stochastic global search heuristics in which Evolutionary Algorithms (EAs) - based approaches are combined usually with heuristic local searches. This hybridization is meant to reach solutions that would otherwise be unreachable by evolution or a local method alone. In this work, we propose three Local Search (LS) algorithms for hybridization with an existing Evolutionary Algorithm with Pareto ranking in order to define biological intelligence using the concepts of useful and utility and therefore to zoom on the basin of attraction of promising realistic solutions. Our experimental results with these memetic algorithms in the game of Checkers show how we can learn the organization of behaviors into paths of behaviors of different lengths and frequencies and then reveal the true nature of these behaviors.

关键词： Correlation Sociology Memetics Optimization Ice

来源：评论

学校读者我要写书评

暂无评论

Automated Prediction of Student Participation in Collaborative Dialogs Using Time Series Analyses 3rd

Automated Prediction of Student Participation in Collaborati...

引用

3rd International Conference on Smart Learning Ecosystems and Regional Development, SLERD 2018

作者： Pasov, Iulia Dascalu, Mihai Nistor, Nicolae Trausan-Matu, Stefan Faculty of Automatic Control and Computer Science University "Politehnica" Bucharest 313 Splaiul Independenţei Bucharest60042 Romania Faculty of Psychology and Educational Sciences Ludwig-Maximilians-Universität Leopoldstr. 13 Munich80802 Germany Academy of Romanian Scientists Splaiul Independentei 54 Bucharest050094 Romania Richard W. Riley College of Education and Leadership Walden University 100 Washington Avenue South Suite 900 MinneapolisMN55401 United States

ISBN: (纸本)9783319920214

The massive student participation in computer Supported Collaborative Learning (CSCL) sessions from online classrooms requires intense tutor engagement to track and evaluate individual student participation. In this study, we investigate how the time evolution of messages predicts students’ participation using two models - a linear regression and a Random Forest model. A corpus of 10 chats involving 47 students was scored by 4 human experts and used to evaluate our models. Our analysis shows that students’ pauses length between consecutive messages within a discussion is the strongest participation predictor accounting for R2 =. 796 variance in the human estimations while using a Random Forest model. Our results provide an extended basis for the automated assessment of student participation in collaborative online discussions. © Springer International Publishing AG, part of Springer Nature 2019.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Hand gesture classification with use of convolutional neural networks 32

Hand gesture classification with use of convolutional neural...

引用

32nd Annual European Simulation and Modelling Conference, ESM 2018

作者： Grzejszczak, Tomasz Roth, Robert Moller, Reinhard Silesian University of Technology Faculty of Automatic Control Electronics and Computer Science 16 Akademicka Street Gliwice44-100 Poland Department of Automation/Computer Science Univeristy of Wuppertal Rainer-Guenter-Str. 21 Wuppertal42119 Germany

ISBN: (纸本)9789492859051

The preliminary research on stationary sign language hand gesture recognition with use of convolutional neural networks is presented. Three tests are presented that differ in number of gesture types, that is, by classes amount. The main question is, whether it is possible to use convolutional neural networks and deep learning approach in stationary gesture recognition, when there is small number of training data, what is the influence of similar gestures on classification process and is it necessary to use controlled background. Test results are provided in form of confusion matrices. Finally, the direction of future work and further research is discussed. © 2018 PDF-CONFERENCE. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Mathematical Modelling and Effect Size Analysis in Support of Searching for the Proteomic Signature of Radiotherapy Toxicity

Mathematical Modelling and Effect Size Analysis in Support o...

引用

IEEE Symposium on Bioinformatics and Bioengineering (BIBE)

作者： Kinga Leszczorz Omid Azimzadeh Soile Tapio Michael Atkinson Joanna Polanska Silesian University of Technology Gliwice Poland Helmholtz Zentrum München Institute of Radiation Biology München Germany Faculty of Automatic Control Electronics and Computer Science Silesian University of Technology Gliwice Poland

Development of new technologies has resulted in the significant expansion of biological research, among which studies in the area of genomics, transcriptomics, proteomics, and metabolomics are the leading ones. In the majority of omics studies, the goal is to identify reliable molecular biomarkers and pathways associated with the examined process. In almost all cases, a list of differentially expressed genes or proteins is constructed, which is not easy to obtain for some experimental designs. In our work, we mainly focus on the experiments with small sample size. The goal was to determine the robust proteomic signature of radiation exposure in the mouse model. Our selection algorithm combines mathematical modelling of signal and its fold change distributions with the comprehensive effect size analysis. Thanks to the data-driven automated thresholding of the protein absolute or relative (fold change) expressions, and Cohens effect size based filters, the obtained proteomic signature demonstrated a higher level of consistency and functional coherency. The additional, intuitively expected, signalling pathways were identified when compared to the standard statistical approach.

关键词： Proteins Lung Proteomics Mice Peptides Testing Statistical analysis

来源：评论

学校读者我要写书评

暂无评论

Microgrid control simulation and testing

UPB Scientific Bulletin, Series C: Electrical Engineering an...

引用

UPB Scientific Bulletin, Series C: Electrical Engineering and computer science 2018年第2期80卷 57-68页

作者： Puianu, Mihaela Flangea, Ramona-Oana Arghira, Nicoleta Iliescu, Sergiu Stelian Faculty of Automatic Control and Computer Science University POLITEHNICA of Bucharest Romania Dept. of Automatic Control and Industrial Informatics University POLITEHNICA of Bucharest Romania

Microgrid control becomes more and more developed with the application of this concept on a larger scale. This paper defines the modern microgrid concept and evaluates the possible architectures and control hierarchy. A small scale microgrid architecture is proposed. The components of the system are a wind turbine, a photovoltaic panel and a household. The model was implemented in Matlab/Simulink and a decision table control was proposed. The proposed decisions and actions are defined for both on and off grid operation, in order to benefit most of the local resources. The results of this study are promising in terms of microgrid off grid operation for single dwellings, considering that the house is grid supplied for a period of only 4 hours of the day. © 2018 Politechnica University of Bucharest. All rights reserved.

关键词： Decision tables

来源：评论

学校读者我要写书评

暂无评论

Flooded Area Segmentation from UAV Images Based on Generative Adversarial Networks

Flooded Area Segmentation from UAV Images Based on Generativ...

引用

International Conference on control, Automation, Robotics and Vision (ICARCV)

作者： Dan Popescu Loretta Ichim Florin Stoican Faculty of Automatic Control and Computer Science University Politehnica of Bucharest Romania Faculty of Automatic Control and Computers University Politehnica of Bucharest Bucharest

The detection, localization and evaluation of small flooded areas can contribute to decrease the economical damages of such disasters. The cheapest and most accurate method is to segment the aerial images taken from UAV. In this paper, we propose a new method for detection of regions of interest, like flooding in rural areas, using Generative Adversarial Networks (GAN) and Graphics Processing Units (GPU). The classical GPU is used to create, by parallel calculation of textural features, extracted from the co-occurrence matrix, the supervised mask of flood segmentation in the images from the learning set. Based on these images and their associated real masks, the weights of the generator and discriminator are established. A set of 40 images were used for the learning phase and another set of 60 images were used for method validation. The results demonstrate that the proposed method provide a high accuracy and robustness, comparing with other papers for flooding evaluation. Even if it is a relative long time to learn the GAN, in the operational phase the time for image segmentation process is very short.

关键词： Image segmentation Gallium nitride Floods Instruction sets Graphics processing units Generative adversarial networks Generators

来源：评论

学校读者我要写书评

暂无评论

Fog-Based Solution for Real-Time Monitoring and Data Processing in Manufacturing

Fog-Based Solution for Real-Time Monitoring and Data Process...

引用

International Conference on System Theory, control, and Computing (ICSTCC)

作者： Stefan Mocanu Giorgiana Geampalia Oana Chenaru Radu Dobrescu Faculty of Automatic Control and Computer Science Politehnica University Bucharest Romania

Today's industry is facing an increased need for implementing intelligent manufacturing solutions, capable of integrating existing machinery with new technologies. Current solutions do not provide support for analyzing vast amounts of data. Also, implementation of cloud architectures proved inappropriate for real-time or near real-time processing and control because of the network latency. Under these considerations, the new paradigm of fog computing provides promising characteristics enabling greater scalability, fast reaction time and increasing security through a local private processing cloud structure. This paper evaluates the integration capabilities between existing technologies with new devices for seamless integration of the fog computing paradigm and provides an architecture solution for this upgrade.

关键词： Cloud computing Real-time systems computer architecture Manufacturing processes Process control Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

CNN based on LBP for Evaluating Natural Disasters

CNN based on LBP for Evaluating Natural Disasters

引用

International Conference on control, Automation, Robotics and Vision (ICARCV)

作者： Andrada Livia Cirneanu Dan Popescu Loretta Ichim Faculty of Automatic Control and Computer Science University Politehnica of Bucharest Romania Faculty of Automatic Control and Computers University Politehnica of Bucharest Bucharest

This paper presents a novel evaluation method of areas affected by natural disasters with the purpose of managing these crisis situations. Since it is necessary to have a real overview of a specific area in the shortest time, our methodology proposes a neural network with backpropagation approach for flood detection from UAV images. For this, the Local Binary Pattern (LBP) texture operator is used for areas classification. The LBP operator labels each pixel of the analyzed image by comparing it with its neighbors, which ends with the computation of a binary number that it is converted to decimal format named LBP code. Thus, based on the generated LBP codes, a histogram type feature is computed and used in both training and testing phases of the proposed neural network. Over 50 images obtained with the aid of UAV technology were tested with the proposed neural network and good results in terms of accuracy for flood areas detection were obtained.

关键词： Training Biological neural networks Histograms Backpropagation Testing Training data

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：