检索结果-内蒙古大学图书馆

IEEE International Symposium on Industrial Electronics (ISIE)

作者： Frank Wasinski Werner Bonath Ubbo Ricklefs Josef Börcsök Michael Schwarz Eike Hahn Dept. of Electrical Engineering and Information Technology THM University of Applied Sciences Giessen Germany ICAS Institute for Computer Architecture and System Programming University of Kassel Kassel Germany

Optical speed sensors based on the spatial frequency filter method are a proven technology that offer high measurement accuracy over a wide speed range. Newly developed variants also enable measurements at very low speeds and increase the robustness of the method [1]. This makes the sensor very suitable for use in the area of functional safety. A measurement chain up to safety integrity level 3 (SIL3) should be feasible via a combination with a safety system on a chip (SoC) for evaluating the measurement data and an extension of the sensor module to include safety-related elements [2], [3]. By integrating the sensor at IC level, a compact overall solution is to be made possible. After the first successful tests with the safety SoC, further examinations of the measuring method with regard to functional safety are now necessary.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Training Policy for Privacy-Preserving Logistic Regression in Federated Learning Environments

Training Policy for Privacy-Preserving Logistic Regression i...

引用

Federated Learning Technologies and Applications (FLTA), International Conference on

作者： Jorge M. Cortés-Mendoza Andrei Tchernykh Horacio González-Vélez Cloud Competency Centre National College of Ireland Dublin Ireland Computer Science Department CICESE Research Center Ensenada Mexico Institute for System Programming RAS Moscow Russia

ISBN: (数字)9798350354812

ISBN: (纸本)9798350354829

Logistic Regression (LR) is a widely used statistical model for classification problems. However, its training and evaluation in a shared environment increase the possibility of information leaking. A federated LR reduces security issues by using only locally available data for training. In a Federated Learning (FL) environment, LR receives the coefficients of local models to create the federated LR model, which is then distributed to update the local models. The exchange process does not leak confidential information when LR coefficients are encrypted. Homomorphic Encryption (HE) allows the merging of local LR models with privacy preservation (HE-LR). This work presents a novel training policy to reduce the training time with only slightly decreased quality in an FL environment with HE. We analyze the accuracy and time of FL policies with HE-LR that progressively reduce the amount of training data and exchange the LR coefficients in a privacy-preserving manner. The results show that the proposed policy can speed up the training time between 12% and 69%, compared to the traditional FL approach, with an average decrease in accuracy of 1.79% and 1.95%.

关键词： Training Measurement Logistic regression Privacy Accuracy Federated learning Merging Training data Cryptography Homomorphic encryption

来源：评论

学校读者我要写书评

暂无评论

Classification of Static Analyzer Warnings using Machine Learning Methods

Classification of Static Analyzer Warnings using Machine Lea...

引用

Ivannikov Memorial Workshop (IVMEM)

作者： U. V. Tsiazhkorob V. N. Ignatyev Ivannikov Institute for System Programming of the Russian Academy of Sciences (ISP RAS) Moscow Russian Federation Moscow Institute of Physics and Technology Moscow Russian Federation Lomonosov Moscow State University Moscow Russian Federation

ISBN: (数字)9798331504663

ISBN: (纸本)9798331504670

The paper is devoted to the approach for static analyzer’s warnings classification using machine learning methods. Static analysis plays a crucial role in software development by identifying potential errors and vulnerabilities in source code. However, the huge amount of warnings generated by static analyzers often overwhelms developers, making it challenging to prioritize and address them effectively. This paper proposes a novel approach to automatically classify static analyzer warnings using machine learning techniques. It showed the result up to 92% accuracy on real-world projects. Our method uses a set of code metrics collected during the analysis process to generate features for training the classifier. In the paper it is explored various strategies for feature selection and model training, considering different types of warnings and analyzers. The effectiveness of the proposed approach in warning classification was experimentally demonstrated. The developed method will be used to automatically review the results generated by the industrial static analyzer.

关键词： Training Measurement Reviews Source coding Conferences Computer bugs Static analysis

来源：评论

学校读者我要写书评

暂无评论

Scalable supervised machine learning apparatus for computationally constrained devices 13

Scalable supervised machine learning apparatus for computati...

引用

13th International Conference on Software Technologies, ICSOFT 2018

作者： López, Jorge Laputenko, Andrey Kushik, Natalia Yevtushenko, Nina Torgaev, Stanislav N. SAMOVAR CNRS Télécom SudParis Université Paris-Saclay 9 rue Charles Fourier Évry91000 France Department of Information Technologies Tomsk State University 36 Lenin street Tomsk634050 Russia Ivannikov Institute for System Programming of the Russian Academy of Sciences 25 Alexander Solzhenitsyn street Moscow109004 Russia

ISBN: (纸本)9789897583209

Computationally constrained devices are devices with typically low resources / computational power built for specific tasks. At the same time, recent advances in machine learning, e.g., deep learning or hierarchical or cascade compositions of machines, that allow to accurately predict / classify some values of interest such as quality, trust, etc., require high computational power. Often, such complicated machine learning configurations are possible due to advances in processing units, e.g., Graphical Processing Units (GPUs). Computationally constrained devices can also benefit from such advances and an immediate question arises: how? This paper is devoted to reply the stated question. Our approach proposes to use scalable representations of 'trained' models through the synthesis of logic circuits. Furthermore, we showcase how a cascade machine learning composition can be achieved by using 'traditional' digital electronic devices. To validate our approach, we present a set of preliminary experimental studies that show how different circuit apparatus clearly outperform (in terms of processing speed and resource consumption) current machine learning software implementations. Copyright © 2018 by SCITEPRESS - Science and Technology Publications, Lda. All rights reserved

关键词： Timing circuits

来源：评论

学校读者我要写书评

暂无评论

Comparative analysis of non/ductedpropeller under the influence of vertical wall

Comparative analysis of non/ductedpropeller under the influe...

引用

Ivannikov ISPRAS Open Conference (ISPRAS)

作者： Mengfei Wang QingXu Qin Zhang Andrey Epikhin Bingchen Liang College of Engineering Ocean University of China Qingdao China Ivannikov Institute for System Programming of the RAS Moscow Russia Shandong Provincial Key Laboratory of Ocean Engineering Qingdao China

A numerical and experimental study has been conducted to explore the influence of vertical wall on the wake of the non/ducted propeller. The numerical simulation is achieved using a structured and transient sliding mesh approach. The control equations are closed by the Delayed Detached Eddy Simulation (DDES), and the computational results are compared with the available experimental data. By dividing the ducted propeller flow wake vortex shape into different behavior regions, the temporal vortex evolution near the wake of the propellers under the influence of different vertical walls are emphatically analysed. The results show that the jet flow wake reaches the wall, forming a conical low-speed area at the centre of the wall. The fluid circulates from the outer side to the inner side of the cone, forming a vortex whose size first increases and then decreases with the distance between the propellers and the wall. In addition, the change of propellers wake velocity profile is given. The wake velocity of propeller and ducted propeller decreases exponentially and linearly along the flow direction, respectively.

关键词： Fluids Propellers Shape Computational modeling Numerical simulation Mathematical models Data models

来源：评论

学校读者我要写书评

暂无评论

Sinkhorn Transformations for Single-Query Postprocessing in Text-Video Retrieval

arXiv

引用

arXiv 2023年

作者： Yakovlev, Konstantin Polyakov, Gregory Alimova, Ilseyar Podolskiy, Alexander Bout, Andrey Nikolenko, Sergey Piontkovskaya, Irina Huawei Noah’s Ark Lab Moscow Russia Ivannikov Institute for System Programming of the RAS Moscow Russia St. Petersburg Department the Steklov Institute of Mathematics St. Petersburg Russia

A recent trend in multimodal retrieval is related to postprocessing test set results via the dual-softmax loss (DSL). While this approach can bring significant improvements, it usually presumes that an entire matrix of test samples is available as DSL input. This work introduces a new postprocessing approach based on Sinkhorn transformations that outperforms DSL. Further, we propose a new postprocessing setting that does not require access to multiple test queries. We show that our approach can significantly improve the results of state of the art models such as CLIP4Clip, BLIP, X-CLIP, and DRL, thus achieving a new state-of-the-art on several standard text-video retrieval datasets both with access to the entire test set and in the single-query setting. Copyright © 2023, The Authors. All rights reserved.

关键词： Information retrieval

来源：评论

学校读者我要写书评

暂无评论

A Practical Approach for Reliability Prediction of Safety Critical Software Using Multi-Model Ensemble Techniques

A Practical Approach for Reliability Prediction of Safety Cr...

引用

International Conference on system Reliability and Science (ICSRS)

作者： Aymen Ouertani Ossmane Krini Habil. Josef Börcsök Institute of functional safety & cyber security Baden-Wuerttemberg Cooperative State University Lörrach Germany Computer Architecture und System Programming University of Kassel Kassel Germany

This paper introduces a novel and comprehensive approach for estimating the reliability of safety critical software components in autonomous vehicle motion systems. The proposed approach in this paper presents a combination software reliability model (CSRM) that integrates multiple non-homogeneous Poisson process (NHPP) software reliability growth models (SRGMs) to achieve a reasonable compromise between accuracy, the trade-off between the goodness of fit and the simplicity, and stability. By using machine learning techniques, the CSRM effectively combines the strengths of individual SRGMs while mitigating their weaknesses through suitable evaluation and calibration techniques. The developed CSRM has been successfully applied and validated to facilitate a smoother and more efficient evaluation of reliability targets for software components in autonomous robotic wheelchair (ARW). Based on the validation results, the new CSRM has significantly enhanced the efficiency of the process for evaluating whether the defined reliability goals were being achieved. Furthermore, has facilitated a more accurate assessment of the need for further test executions and better planning of the required verification and validation session. This new approach provides valuable insights into the reliability of the developed software, particularly for software developers lacking extensive experience in identifying and applying appropriate SGRM.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Homomorphic Comparison Methods: Technologies, Challenges, and Opportunities

Homomorphic Comparison Methods: Technologies, Challenges, an...

引用

Engineering and Telecommunication (En&T), International Conference

作者： Mikhail Babenko Andrei Tchernykh Elena Golimblevskaia Luis Bernardo Pulido-Gaytan Arutyun Avetisyan Ivannikov Institute for System Programming Moscow Russia South Ural State University Chelyabinsk Russia North-Caucasus Federal University Stavropol Russia CICESE Research Center Ensenada Mexico

ISBN: (纸本)9781728188300

The use of cloud computing imposes a number of restrictions related to the security and confidentiality of stored and processed data. One of the mechanisms that allows expanding the scope of public cloud services for processing personal and medical data is homomorphic encryption. Homomorphic encryption allows performing arithmetic addition and multiplication operations on encrypted data. To expand the scope of homomorphic encryption, efficient algorithms are needed to implement the operation of comparing encrypted numbers. In this paper we investigate existing algorithms of encrypted numbers comparison for homomorphic encryption schemes operating both with integers and with fixed-precision numbers. We have shown that for homomorphic integer ciphers, there are efficient algorithms for comparing encrypted numbers based on Lagrange interpolation of a function of two variables. We have shown that fixed-precision comparison of encrypted numbers is an open problem.

关键词： Deep learning Interpolation Cloud computing Ciphers Neural networks Iterative algorithms Encryption

来源：评论

学校读者我要写书评

暂无评论

Secure Verifiable Secret Short Sharing Scheme for Multi-Cloud Storage

Secure Verifiable Secret Short Sharing Scheme for Multi-Clou...

引用

International Conference on High Performance Computing and Simulation

作者： Maxim Deryabin Nikolay Chervyakov Andrei Tchernykh Mikhail Babenko Nikolay Kucherov Vanessa Miranda-Lopez Arutyun Avetisyan North-Caucasus Federal University CICESE Research Center Ensenada Mexico South Ural State University CICESE Research Center Institute for System Programming of the Russian Academy of Sciences

ISBN: (纸本)9781538678800

In this paper, we propose a new approach to the construction of computationally secure secret sharing scheme based on the simultaneous use of the Residue Number system (RNS), as the symmetric encryption, and the perfect Asmuth-Bloom secret sharing scheme. We combine the useful features of Redundant RNS to design space efficient secret sharing scheme with enough level of security and to control of data integrity. This combination provides verifiability and achieves a high speed of data processing.

关键词： Threshold secret sharing scheme Computationally secure secret sharing Verifiable scheme Residue Number system Cloud data storage Distributed storage Multi-clouds

来源：评论

学校读者我要写书评

暂无评论

Docmarking: Real-Time Screen-Cam Robust Document Image Watermarking

Docmarking: Real-Time Screen-Cam Robust Document Image Water...

引用

Ivannikov ISPRAS Open Conference (ISPRAS)

作者： Aleksey Yakushev Yury Markin Dmitry Obydenkov Alexander Frolov Stas Fomin Manuk Akopyan Alexander Kozachok Arthur Gaynov Ivannikov Institute for System Programming of the RAS Moscow Russia Russian Federation Security Guard Service Federal Academy Oryol Russia Ministry of Defence of the Russian Federation Moscow Russia

This paper focuses on investigation of confidential documents leaks in the form of screen photographs. Proposed approach does not try to prevent leak in the first place but rather aims to determine source of the leak. Method works by applying on the screen a unique identifying watermark as semi-transparent image that is almost imperceptible for human eyes. Watermark image is static and stays on the screen all the time thus watermark present on every captured photograph of the screen. The key components of the approach are three neural networks. The first network generates an image with embedded message in a way that this image is almost invisible when displayed on the screen. The other two neural networks are used to retrieve embedded message with high accuracy. Developed method was comprehensively tested on different screen and cameras. Test results showed high efficiency of the proposed approach.

关键词： Neural networks Watermarking Cameras Real-time systems

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：