检索结果-内蒙古大学图书馆

11th International Conference on Advanced Computer Information Technologies, ACIT 2021

作者： Nykolaychuk, Yaroslav Grynchychyn, Taras Pitukh, Ihor Petrashchuk, Yaroslav Nykolaychuk, Lyubov Hryha, Volodymyr West Ukrainian National University Department of Specialized Computer Systems Ternopil Ukraine Nadvirna Vocational College by National Transport University Department of Programming and Information Technologies Nadvirna Ukraine Gorgany Nature Reserve Nadvirna Ukraine Ivano-Frankivsk National Technical University of Oil and Gas Department of Social Communication and Law Ivano-Frankivsk Ukraine Vasyl Stefanyk Precarpathian National University Department of Computer Engineering and Electronics Ivano-Frankivsk Ukraine

Experience in designing and building cyber physical interactive distributed monitoring systems for industrial facilities and reserve landscapes is analyzed. Advantages of the existing interactive and dialogue computerized systems, replicated by many companies, are systematized and their functional limitations are determined. The legal and system requirements for the implementation of this class of information system components, which can be applied in strict Nature Reserve, are clarified. It is proposed to expand the functionality and increase the reliability of the ring-star system for background monitoring of nature reserves based on binary-manipulated optical signals. A sensor system for measuring the height of snow cover along the monitoring route is developed using a relay sensor network and quadcopters. © 2021 IEEE.

关键词： Cyber Physical System

来源：评论

学校读者我要写书评

暂无评论

Data poisoning: issues, challenges, and needs

Data poisoning: issues, challenges, and needs

引用

7th IET Smart Cities Symposium (SCS 2023)

作者： Mohammad Aljanabi Alaa Hamza Omran Maad M Mijwil Mostafa Abotaleb El-Sayed M. El-kenawy Sahar Yousif Mohammed Abdelhameed Ibrahim Department of computer College of Education Aliarqai university Baghdad Iraq University of information technology and communications Baghdad Iraq Computer Techniques Engineering Department Baghdad College of Economic Sciences University Baghdad Iraq Department of System Programming South Ural State University Chelyabinsk Russia Department of Communications and Electronics Delta Higher Institute of Engineering and Technology Egypt Computer Science Department Computer Science & Information Technology College Anbar University Anbar Iraq Computer Engineering and Control Systems Department Faculty of Engineering Mansoura University Mansoura Egypt

Data poisoning attacks, where adversaries manipulate training data to degrade model performance, are an emerging threat as machine learning becomes widely deployed in sensitive applications. This paper provides a comprehensive overview of data poisoning including attack techniques, adversary incentives, impacts on security and reliability, detection methods, defenses, and key research gaps. We examine label flipping, instance injection, backdoors, and other attack categories that enable malicious outcomes ranging from IP theft to accidents in autonomous systems. Promising detection approaches include statistical tests, robust learning, and forensics. However, significant challenges remain in translating academic defenses like adversarial training and sanitization into practical tools ready for operational use. With safety and trustworthiness at stake, more research on benchmarking evaluations, adaptive attacks, fundamental tradeoffs, and real-world deployment of defenses is urgently needed. Understanding vulnerabilities and developing resilient machine learning pipelines will only grow in importance as data integrity is fundamental to developing safe artificial intelligence.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Speaker's Emotions Recognition Module Based on the GoogleLeNet Neural Network

Speaker's Emotions Recognition Module Based on the GoogleLeN...

引用

2022 International Conference on Smart Information systems and Technologies, SIST 2022

作者： Tereikovskyi, Ihor Tereikovska, Liudmyla Kryvoruchko, Olena Tereikovskyi, Oleh Tyshchenko, Dmytro Franchuk, Tamara National Technical University Of Ukraine Igor Sikorsky Kyiv Polytechnic Institute Dept. Of System Programming And Specialized Computer Systems Kyiv Ukraine Kyiv National University Of Construction And Architecture Dept. Of Information Technology For Design And Applied Mathematics Kyiv Ukraine Kyiv National University Of Trade And Economics Dept. Of Software Engineering And Cyber Security Kyiv Ukraine National Technical University Of Ukraine Igor Sikorsky Kyiv Polytechnic Institute Dept. Of Department Of Computer Engineering Kyiv Ukraine

ISBN: (数字)9781665467902

ISBN: (纸本)9781665467902

The article is devoted to the development of means for recognition of the emotions of the speaker, based on the neural network analysis of fixed fragments of the voice signal. The possibility of improving recognition tools through the use of a convolutional neural network of the GoogLeNet type is shown. The expediency of training the network on the examples of the TESS database is determined. A procedure for representing a voice signal in the form of a square grayscale image has been developed. Based on the use of the specified database, the modification of the GoogLeNet network was carried out. The architecture and software implementation of the recognition module have been developed. With the help of computer experiments, it has been established that after 150 epochs of training on a fairly limited training sample, the modified GoogLeNet makes it possible to achieve an accuracy of recognition of the speaker's emotions of approximately 0.97 on test examples. The obtained accuracy is comparable to the accuracy of the best modern systems of this purpose and confirms the promise of using neural network models like GoogLeNet for emotion recognition based on voice signal analysis. The need for further research aimed at reducing the resource intensity of the neural network model is shown. © 2022 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Issues of modelling of the intellectual capital reproduction and increment processes 16

Issues of modelling of the intellectual capital reproduction...

引用

16th International Conference on Intellectual Capital, Knowledge Management and Organisational Learning, ICICKM 2019

作者： Volkov, Denis Mamedova, Natalia Department of Information Systems Management and Programming Plekhanov Russian University of Economics Moscow Russia

ISBN: (纸本)9781912764501

The paper contains threshold results and demonstrates a perspective for ongoing research in the field of digitalization of the economy. The relationship between the knowledge economy and intangible and material production is presented. The value of knowledge as a factor of production and goods, as well as a production asset and a production resource is determined. Evolutionary changes in the paradigm of knowledge management in connection with the transition to a new economic formation – the digital economy are outlined. The results of research of the concept and structure of intellectual capital on the basis of a systematic approach are summarized. The problems of both theoretical and applied nature that prevent more effective implementation of the results of the research in the practice of organizations in all spheres of the economy are systematized. The problems are presented in the context of considering the role and place of knowledge in the formation and increment of intellectual capital. The greatest development was the question associated with the development of a model describing the process of increment of intellectual capital through the change of parameters included in the model of describing the increment of knowledge acquired (produced) by the subject of the economy. The perspective direction of research of mutual influence (correlation) of parameters of increment of knowledge and reflecting influence of these parameters on volume and rates of increment of intellectual capital is specified. The methods of mathematical modeling are indicated as tools for the research. This will not only describe the process of increment/change in the volume of intellectual capital using a finite number of parameters, but also explore the possibility of manipulating parameters. The results of the study stated the establishment of mutual correlation with changes in the parameters of the studied processes at various scales. It will allow to form the forecast of behavior of

关键词： Knowledge management

来源：评论

学校读者我要写书评

暂无评论

Improving Predictions of Long Sequences by Hyperparameter Tuning

Improving Predictions of Long Sequences by Hyperparameter Tu...

引用

Computer Science (COMSCI), International Scientific Conference on

作者： Kiril Andreev Koparanov Krasin Krasimirov Georgiev Vasil Aleksandrov Shterev Daniela Veleva Minkovska Department of Programming and Computer Technologies Faculty of Computer Systems and Technologies Technical University of Sofia 8 Kliment Ohridski blvd Sofia Bulgaria Department of Air Transport Faculty of Transport Technical University of Sofia 8 Kliment Ohridski blvd Sofia Bulgaria Department of Communication Networks Faculty of Telecommunications Technical University of Sofia 8 Kliment Ohridski blvd Sofia Bulgaria

ISBN: (数字)9781665497770

ISBN: (纸本)9781665497787

The problem of forecasting long sequences is important in many different domains. Proper selection of the hyperparameters when a machine learning approach is applied could make the difference between adequate and inadequate model. Several algorithms for automatic hyperparameters tuning were evaluated and compared with baseline selection. As a result, recommendations have been made. Some of the intuitive assumptions for the baseline model proved to be wrong.

关键词： Industries Machine learning algorithms Computational modeling Time series analysis Diversity reception Machine learning Prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

Design of a model for disinfection robot system

Design of a model for disinfection robot system

引用

2020 International Conference on Information Science and Communications Technologies, ICISCT 2020

作者： Nosirov, Khabibullo Begmatov, Shohruh Arabboev, Mukhriddin Medetova, Kunduz Tashkent University of Information Technologies Named after Muhammad Al-Khwarizmi Department of Television and Radio Broadcasting Systems Tashkent Uzbekistan Tashkent University of Information Technologies Named after Muhammad Al-Kwarizmi Department of Hardware and Software of Control Systems in Telecommunications Tashkent Uzbekistan Tashkent University of Information Technologies Named after Muhammad Al-Khwarizmi Department of Systems and Applied Programming Tashkent Uzbekistan

ISBN: (纸本)9781728199696

Following for hygiene and sanitation requirements have always been the most significant factor to stay healthy in human life. Proper cleaning and sanitation measures are one of the important ways to fight against various viruses. In recent years, the use of modern technology in sanitation has helped to fight against infectious diseases. One such modern technology is disinfection robot. Disinfection robots are increasingly used in all around the world. Use of these disinfection robots reduce the risk of infection, cost of traditional cleaning and disinfection, and most importantly acquires confidence and security of individuals. In this paper, we design a model for robot-disinfector. This robot is inspired on/from a technique, which consists of disinfecting places autonomously in order to save human life from infections. The main advantages of the designed robot are the novelty, multi-functionality, and the availability at an affordable cost. © 2020 IEEE.

关键词： Robots

来源：评论

学校读者我要写书评

暂无评论

Line Search Strategy for Navigating through Barren Plateaus in Quantum Circuit Training

arXiv

引用

arXiv 2024年

作者： Nádori, Jakab Morse, Gregory Majnay-Takács, Zita Zimborás, Zoltán Rakyta, Péter Department of Physics of Complex Systems Eötvös Loránd University Pázmány Péter sétány 1/a Budapest1117 Hungary Department of Programming Languages and Compilers Eötvös Loránd University Pázmány Péter sétány 1/a Budapest1117 Hungary Wigner Research Center for Physics P.O. Box 49 Budapest1525 Hungary Algorithmiq Ltd. Kanavakatu 3C Helsinki00160 Finland

Variational quantum algorithms are viewed as promising candidates for demonstrating quantum advantage on near-term devices. These approaches typically involve the training of parameterized quantum circuits through a classical optimization loop. However, they often encounter challenges attributed to the exponentially diminishing gradient components, known as the barren plateau (BP) problem. This work introduces a novel optimization approach designed to alleviate the adverse effects of BPs during circuit training. In contrast to conventional gradient descent methods with a small learning parameter, our approach relies on making a finite number of hops along the search direction. The optimization search direction, together with the range of the search, is determined by the distant features of the cost-function landscape. This enables the optimization path to navigate around barren plateaus without the need for external control mechanisms. We have successfully applied our optimization strategy to quantum circuits comprising 16 qubits and 15000 entangling gates, demonstrating robust resistance against BPs. Additionally, we have extended our optimization strategy by incorporating an evolutionary selection framework, enhancing its ability to avoid local minima in the landscape. The modified algorithm has been successfully utilized in quantum gate synthesis applications, showcasing a significantly improved efficiency in generating highly compressed quantum circuits compared to traditional gradient-based optimization approaches. © 2024, CC BY.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

Forecasting nonlinear nonstationary processes in machine learning task 3

Forecasting nonlinear nonstationary processes in machine lea...

引用

3rd IEEE International Conference on Data Stream Mining and Processing, DSMP 2020

作者： Bidyuk, Peter Gozhyj, Aleksandr Kalinina, Irina Vysotska, Victoria Vasilev, Mikhail Malets, Romanna Department of Mathematical Methods of System Analysis National Technical University of Ukraine Igor Sikorsky Kyiv Polytechnic Institute Kyiv Ukraine Petro Mohyla Black Sea National University Department of Intelligent Information Systems Nikolaev Ukraine National University Lvivska Politechnika Department of Information Systems and Networks Lviv Ukraine Ivan Franko Lviv National University Programming Department Lviv Ukraine

ISBN: (纸本)9781728132143

The article discusses the features of the solving the forecasting problems using machine learning techniques. The issues of accounting and correctly processing non-linear non-stationary processes in the problems of modeling and forecasting time series in various areas are considered. The analysis of stages and methods for solving machine learning problems. As an example, consider the problem of predicting currency pairs based on historical data. A comparative analysis of the normalization methods in data clustering is given. For the six currency pairs a short-term forecast is proposed. © 2020 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis Technology of English Newspapers Quotes Based on Neural Network as Public Opinion Influences Identification Tool

Sentiment Analysis Technology of English Newspapers Quotes B...

引用

International Computer Sciences and Information Technologies (CSIT)

作者： Serhii Voloshyn Victoria Vysotska Oksana Markiv Ivan Dyyak Ihor Budz Vadim Schuchmann Information Systems and Networks Department Lviv Polytechnic National University Lviv Ukraine Lviv Polytechnic National University Lviv Ukraine Osnabrück University Osnabrück Germany Applied Mathematics Department Ivan Franko National University of Lviv Lviv Ukraine Computational Mathematics and Programming Department Lviv Polytechnic National University Lviv Ukraine Software Engineering Department West Ukrainian National University Ternopil Ukraine

ISBN: (纸本)9798350334326

This article dwells upon research concerning human language processing techniques, namely emotion analysis, conducted to identify emotions of author quotations in English newspaper articles. The publication describes general information about human language processing, brief description of analogues based on machine learning and neural network to analyse emotions in text. The main goal is to develop intelligent system for sentiment analysis of English language quotations and keywords identification that influences public opinion. The article describes sequence of program actions and tools that have been used. Then, statistics of tasks performed by neural networks with various functions of activators have been described. In the publication, product demo version has been described, and primary usage scenario has been depicted. In the end, research results have been summarised.

关键词： Training Sentiment analysis Vocabulary Dictionaries Mood Neural networks Text categorization

来源：评论

学校读者我要写书评

暂无评论

Automated Computation of Therapies Using Failure Mode and Effects Analysis in the Medical Domain

arXiv

引用

arXiv 2024年

作者： Luttermann, Malte Baake, Edgar Bouchagiar, Juljan Gebel, Benjamin Grüning, Philipp Manikwadura, Dilini Schollemann, Franziska Teifke, Elisa Rostalski, Philipp Möller, Ralf Institute of Information Systems University of Lübeck Germany Institute of Telematics University of Lübeck Germany Institute for Software Engineering and Programming Languages University of Lübeck Germany Department of Infectious Diseases and Microbiology University Hospital Schleswig-Holstein Campus Lübeck Germany Institute for Neuro- and Bioinformatics University of Lübeck Germany Institute for Molecular Medicine University of Lübeck Germany Institute for Electrical Engineering in Medicine University of Lübeck Germany franziska.schollemann Department of Anesthesiology and Intensive Care University Hospital Schleswig-Holstein Campus Lübeck Germany

Failure mode and effects analysis (FMEA) is a systematic approach to identify and analyse potential failures and their effects in a system or process. The FMEA approach, however, requires domain experts to manually analyse the FMEA model to derive risk-reducing actions that should be applied. In this paper, we provide a formal framework to allow for automatic planning and acting in FMEA models. More specifically, we cast the FMEA model into a Markov decision process which can then be solved by existing solvers. We show that the FMEA approach can not only be used to support medical experts during the modelling process but also to automatically derive optimal therapies for the treatment of patients. © 2024, CC BY.

关键词： Patient treatment

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：