检索结果-内蒙古大学图书馆

International Conference on Management of Large-Scale System Development (MLSD)

作者： Oleg S. Amosov Svetlana G. Amosova Laboratory of Intellectual Control Systems and Modelling V.A. Trapeznikov Institute of Control Sciences of RAS Moscow Russia Laboratory of Cyber-physical Systems V.A. Trapeznikov Institute of Control Sciences of RAS Moscow Russia

ISBN: (数字)9781728110943

ISBN: (纸本)9781728110950

The problem of evaluating the emergent properties of a system and detecting and recognizing the occurrence of anomalies in the behavior of a dynamic system is formulated. To solve these problems, fuzzy cognitive modeling and a set of deep neural networks are proposed. An example of recognizing an anomaly in the behavior of processes in the airfield infrastructure is being considered.

关键词： Training Atmospheric modeling Computational modeling Neural networks Streaming media Airports Dynamical systems

来源：评论

学校读者我要写书评

暂无评论

Detection and Recognition of Manufacturing Defects of Rivet Joints by their Video Images Using Deep Neural Networks

Detection and Recognition of Manufacturing Defects of Rivet ...

引用

2019 International Multi-Conference on Industrial Engineering and Modern Technologies, FarEastCon 2019

作者： Amosov, O.S. Amosova, S.G. Iochkov, I.O. Laboratory of Intellectual Control Systems and Modelling V.A. Trapeznikov Institute of Control Sciences of Russian Academy of Sciences Moscow Russia Electronics KnASU Department of Industria Komsomolsk-on-Amur Russia

The issue of detecting and recognizing manufacturing defects in riveted joints using video content is presented. For the detection and classification of defects in riveted joints of aircraft, a computational method us... 详细信息

ISBN: (纸本)9781728100616

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

The use of deep neural networks to recognize network traffic abnormalities in enterprise information and telecommunication systems 12

The use of deep neural networks to recognize network traffic...

引用

12th International Conference "Management of Large-Scale System Development", MLSD 2019

作者： Amosov, O.S. Amosova, S.G. Ivanov, Y.S. Zhiganov, S.V. V.A. Trapeznikov Institute of Control Sciences Russian Academy of Sciences Laboratory of Intellectual Control Systems and Modelling Moscow Russia Komsomolsk-on-Amur State University Department of Industrial Electronics Komsomolsk-on-Amur Russia

ISBN: (纸本)9781728117300

It is proposed to recognize the network traffic abnormalities by using different deep neural network architectures. The experiment in detecting DoS attacks was conducted. The influences of neural networks layers combinations on the accuracy characteristics are revealed. New is the strengthening of the classification, through the reinforcement of an input vector to its cluster evaluation. © 2019 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Selecting Architecture and Parameters of Deep Neural Networks for Computer Attack Classification

Selecting Architecture and Parameters of Deep Neural Network...

引用

International Multi-Conference on Industrial Engineering and Modern Technologies (FarEastCon)

作者： O.S. Amosov S.G. Amosova D.S. Magola Laboratory of Intellectual Control Systems and Modelling V.A. Trapeznikov Institute of Control Sciences of Russian Academy of Sciences Moscow Russia Laboratory of Cyber-physical Systems V.A. Trapeznikov Institute of Control Sciences of Russian Academy of Sciences Moscow Russia Komsomolsk-on-Amur state university Komsomolsk-on-Amur Russia

ISBN: (数字)9781728169514

ISBN: (纸本)9781728169521

The article states a problem of a multiclass network classification of computer attacks. To solve it, the authors consider an option of applying deep neural networks. For this research, the authors selected the architecture of a deep neural network based on the strategy combining a set of convolution and recurrent LSTM layers. The research suggests optimizing the neural network parameters on the basis of a genetic algorithm. The authors present the simulation results that show an opportunity to solve the task of network classification in real time.

关键词： Convolution Neural networks Training Tensors Computer architecture Transforms Industrial engineering

来源：评论

学校读者我要写书评

暂无评论

Recognition of Abnormal Traffic Using Deep Neural Networks and Fuzzy Logic

Recognition of Abnormal Traffic Using Deep Neural Networks a...

引用

2019 International Multi-Conference on Industrial Engineering and Modern Technologies, FarEastCon 2019

作者： Amosov, O.S. Ivanov, Y.S. Amosova, S.G. V.A. Trapeznikov Institute of Control Sciences of Russian Academy of Sciences Moscow Laboratory of Intellectual Control Systems and Modelling Russia KnASU Department of Industrial Electronics Komsomolsk-on-Amur Russia V.A. Trapeznikov Institute of Control Sciences of Russian Academy of Sciences Laboratory of Cyber-physical Systems Moscow Russia

ISBN: (纸本)9781728100616

Recognition of the abnormal traffic using the deep learning is proposed. The dual deep neural network architecture for detecting the DOS attacks based on a combination of convolutional layers is proposed. The new thing is the classification strengthening realized by the reinforcement of the input vector with its cluster evaluation. The software was implemented, the testing bench was assembled and a semi-natural experiment was conducted on the basis of the local computer network of the University. As a result of the tests, 87% accuracy of attack recognition was achieved. © 2019 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Computational method basing on deep neural networks to detect and classify defects, appearing in rivet assemblies of aircraft 12

Computational method basing on deep neural networks to detec...

引用

12th International Conference "Management of Large-Scale System Development", MLSD 2019

作者： Amosov, O.S. Amosova, S.G. Pashchenko, F.E. Iochkov, I.O. V.A. Trapeznikov Institute of Control Sciences Russian Academy of Sciences Laboratory of Intellectual Control Systems and Modelling Moscow Russia V.A. Trapeznikov Institute of Control Sciences Russian Academy of Sciences Laboratory of Cyber-physical Systems Moscow Russia Komsomolsk-on-Amur State University Department of Postgraduate Studies Komsomolsk-on-Amur Russia

ISBN: (纸本)9781728117300

A causal analysis of the occurrence of defects in holes and sockets, mortgages and closing heads of rivets when producing rivet joints of aircraft equipment was conducted. The statement of the problem of defects detection and classification is given. The computational method of defects detection and classification in rivet joints of aircraft equipment by using deep neural networks is developed. The example of modeling is given. © 2019 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Face Video Tracking Using Deep Neural Networks

Face Video Tracking Using Deep Neural Networks

引用

International Multi-Conference on Industrial Engineering and Modern Technologies (FarEastCon)

作者： O.S. Amosov S.G. Amosova Y.S. Ivanov S.V. Zhiganov Laboratory of Intellectual Control Systems and Modelling V.A. Trapeznikov Institute of Control Sciences of Russian Academy of Sciences Moscow Russia Laboratory of Cyber-physical Systems V.A. Trapeznikov Institute of Control Sciences of Russian Academy of Sciences Moscow Russia Komsomolsk-on-Amur state university Komsomolsk-on-Amur Russia IT control Komsomolsk-on-Amur state university Komsomolsk-on-Amur Russia

ISBN: (数字)9781728169514

ISBN: (纸本)9781728169521

The computational method of the face recognition in a continuous video stream using deep neural networks is offered, that is effective in terms of accuracy and high-speed performance. Adapted architectures of deep neural networks are proposed: the modified MobileNet v2 neural network and the original dual network for identifying a person by face image. The original databases for neural networks are developed. Natural experiments are made, and the characteristics of accuracy and speed of problem solutions were evaluated. To solve the problems video tracking of persons in real time the software modules of the intelligent access control system in Python are developed.

关键词： Streaming media Face recognition Artificial neural networks Image recognition Training Video tracking Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Optimal Estimation Using Deep Neural Networks Applied to Navigation and Motion control

引用

Journal of Physics: Conference Series 2021年第1期1864卷

作者： O.S. Amosov S.G. Amosova Doctor of Technical Sciences Professor Principal Researcher Laboratory of Intellectual Control Systems and Modelling V.A. Trapeznikov Institute of Control Sciences of RAS Moscow Russia Candidate of Technical Sciences Senior Researcher Laboratory of Cyber-physical Systems V.A. Trapeznikov Institute of Control Sciences of RAS Moscow Russia

The critical analysis is given concerning the current state of using deep neural networks with convolutional and recurrent layers, a recurrent network of Long Short-Term Memory, Gated Recurrent Units for estimation tasks in relation to navigation and motion control. A comparison of neural network and traditional methods is given for understanding and explaining their functioning. The differences, advantages and disadvantages of deep neural networks in relation to solving estimation problems are revealed. The possibility of machine training with reinforcement is analyzed for estimation tasks in navigation and motion control in real time. The prospects of using neural networks in the processing of navigation data, as well as for the tasks of adaptive estimation and trajectory tracking, are formulated.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Recognition of Abnormal Traffic Using Deep Neural Networks and Fuzzy Logic

Recognition of Abnormal Traffic Using Deep Neural Networks a...

引用

International Multi-Conference on Industrial Engineering and Modern Technologies (FarEastCon)

作者： O.S. Amosov Y.S. Ivanov S. G. Amosova Laboratory of Intellectual Control Systems and Modelling V.A. Trapeznikov Institute of Control Sciences of Russian Academy of Sciences Moscow Russia Department of Industrial Electronics KnASU Komsomolsk-on-Amur Russia Laboratory of Cyber-physical Systems V.A. Trapeznikov Institute of Control Sciences of Russian Academy of Sciences Moscow Russia

关键词： Training Telecommunication traffic Neural networks Correlation Fuzzy logic Industrial engineering IP networks

来源：评论

学校读者我要写书评

暂无评论

Detection and Recognition of Manufacturing Defects of Rivet Joints by their Video Images Using Deep Neural Networks

Detection and Recognition of Manufacturing Defects of Rivet ...

引用

International Multi-Conference on Industrial Engineering and Modern Technologies (FarEastCon)

作者： O.S. Amosov S.G. Amosova I.O. Iochkov V.A. Trapeznikov Institute of Control Sciences of Russian Academy of Sciences Laboratory of Intellectual Control Systems and Modelling Moscow Russia V.A. Trapeznikov Institute of Control Sciences of Russian Academy of Sciences Laboratory of Cyber-physical Systems Moscow Russia Department of Industria Electronics KnASU Komsomolsk-on-Amur Russia

关键词： Neural networks Head Inspection Aircraft Aircraft manufacture Training Three-dimensional displays

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：