检索结果-内蒙古大学图书馆

2024 IEEE 22nd World Symposium on applied Machine Intelligence and informatics, SAMI 2024

作者： Kovacs, Andras Szenasi, Sandor Lovas, Robert Obuda University Doctoral School of Applied Informatics and Applied Mathematics Budapest Hungary Obuda University John von Neumann Faculty of Informatics Budapest Hungary

ISBN: (纸本)9798350317206

Nowadays more and more servers are put to use due to the explosive improvement of information technology all around the world. Smart solutions, big data storages and cloud technologies brings with it the ever increasing energy consumption. It is often heard on the news that the energy consumption of some newly built server farm is getting to the level of a smaller city. The question of the near future is the efficient use of energy and avoiding wasteful usage of it. In the context of softwares this can be achieved by running the softwares in optimized hardware environments, using the capacity of the serves to the maximum, allocating more procedures to them until the point where it does not affect performance. In this study we will build a training pattern from hundreds of program codes, vectorizing them based on their main characteristics. Under a dynamic stress test their ideal resource consumption will be determined, then a deep neural network will be trained to determine the minimal resource allocations needed ( memory size, cpu cores) to achieve optimal runtime for a program code that is unknown to it. Based on this it would be possible to develop an optimal distributing algorithm that would place the services on a whole server farm in a way to achieve the desired quality of service using the least amount of hardware. © 2024 IEEE.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Using AI to Improve Accessibility and Inclusivity in Higher Education for Students with Disabilities 21

Using AI to Improve Accessibility and Inclusivity in Higher ...

引用

21st International Conference on Information Technology Based Higher Education and Training, ITHET 2024

作者： Mitre, Xhulio Zeneli, Muhamet University of Tirana Faculty of Economics Department of Statistics and Applied Informatics Tirana Albania

ISBN: (纸本)9798331516635

Around 1.3 billion, or more than 15% of the global population, suffer from a significant form of disability, with students and researchers in this category being underrepresented in higher education. This paper examines the use of Interactive Artificial Intelligence solutions to improve the inclusivity and accessibility of students with disabilities in higher education. The paper addresses the failure of traditional education methods to accommodate the diverse needs of people with disabilities. Through an exploratory literature review, several AI-driven solutions, like assistive technologies, adaptive-learning systems, and generative AI chatbots and virtual assistants, have been reviewed to understand how AI could be leveraged to create an inclusive learning environment. Key results show AI-driven solutions' potential to transform the learning process of people with disabilities by creating personalized learning paths, increasing access to educational resources, and supporting real-time communication. Additionally, the research highlights ethical concerns about the integration of AI in education, emphasizing the need for the participation of disabled individuals in the developmentprocess. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Visual Space-Time Complexity Analysis of Big Signal Data

Visual Space-Time Complexity Analysis of Big Signal Data

引用

2024 IEEE International Symposium on Electromagnetic Compatibility, Signal and Power Integrity, EMC+SIPI 2024

作者： Nemec, Jan Kovar, Stanislav Valouch, Jan Adamek, Milan Tomas Bata University in Zlin Faculty of Applied Informatics Zlin Czech Republic

ISBN: (纸本)9798350360394

This paper will focus on introducing visual analysis for big signal data suitable for preliminary conclusions and information presented to others. The analysis is to determine uniqueness, focusing on spatial-temporal complexity by the nature of the test data. Alongside introducing the analysis and optimization for programming purposes, the real data will be presented and used to display possible usage of this analysis and to determine the uniqueness of electromagnetic background for the possible use in true random number generators. The data consists of measurements in frequency band increments in many locations using widely available consumer-grade equipment. Visual analyses are especially valuable in situations like search for entropy sources because there is no immediate need for a concrete number or boolean statement of the uniqueness;moreover, presenting work is the daily job of a researcher, and the ability to visualize findings in a simple figure is easier to digest by the wider population. © 2024 IEEE.

关键词： Random number generation

来源：评论

学校读者我要写书评

暂无评论

Emotion Classification in Private Social Media Using Machine Learning Methods: Case Study of My Tel-U App 9

Emotion Classification in Private Social Media Using Machine...

引用

9th IEEE International Conference for Convergence in Technology, I2CT 2024

作者： Haq, Hanifan Nurul Akbar Gozali, Alfian Adiwijaya Telkom University Faculty of Informatics Bandung Indonesia Telkom University Faculty of Applied Science Bandung Indonesia

ISBN: (纸本)9798350394474

Emotion, intricately woven through the brain's structures, involves complex neural processes in the brain stem, amygdala, insula, and anterior cingulate cortex. This intentional and affective state finds expression through diverse channels, with social media emerging as a prominent platform. Since its 2021 launch, My Tel-U has seen significant post activity, providing a valuable dataset for research. This study delves into emotion classification using machine learning within the My TelU dataset and assesses model performance. The study's findings have several critical implications. Firstly, the choice of text encoding method plays a significant role in emotion classification model performance, with the TF-IDF method emerging as the optimal choice. Secondly, Support Vector Machine (SVM) and Random Forest exhibit remarkable accuracy-to-execution time ratios, making them suitable for emotion classification tasks. Thirdly, addressing dataset imbalance through methods like SMOTE significantly enhances model performance, highlighting the importance of imbalanced handling. Lastly, private social media datasets, such as My Tel-U, demand specialized handling and models due to unique user communication styles, resulting in higher emotion classification accuracy. Future endeavors may explore hybrid models that combine the strengths of diverse machine learning techniques, such as merging Support Vector Machine's precision with Random Forest's ensemble efficiency. Additionally, the potential of deep learning models like recurrent neural networks (RNNs) and convolutional neural networks (CNNs) promises enhanced emotion classification accuracy. The path to unraveling the complexities of human emotions is just beginning, and this study marks a significant step towards realizing its potential. © 2024 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Beyond Integration: Advancing Electricity Metering with Secure and Transparent Blockchain-IoT Solutions 47

Beyond Integration: Advancing Electricity Metering with Secu...

引用

47th International Conference on Telecommunications and Signal Processing, TSP 2024

作者： Koštál, Kristian Bahar, Muhammad Nasim Numyalai, Sultan Ries, Michal Institute of Computer Engineering and Applied Informatics Slovak University of Technology in Bratislava Faculty of Informatics and Information Technologies Bratislava Slovakia

ISBN: (纸本)9798350365597

As the demand for reliable and accurate electricity metering escalates in the digital era, traditional systems increasingly need to improve due to their centralized nature, prone to inaccuracies, privacy breaches, and cybersecurity threats. This paper proposes a novel solution that harnesses the transformative power of Blockchain and Internet of Things (IoT) technologies to address these critical challenges. By integrating the immutable ledger capabilities of blockchain with the real-time data acquisition prowess of IoT, we introduce a decentralized system that ensures the secure and transparent measurement and billing of electricity for domestic consumers. Adopting Hyperledger Fabric within our framework offers a robust, scalable architecture that supports secure transactions and enhances trust through digital identities for all participants. This system mitigates the vulnerabilities associated with centralized authorities and efficiently monitors and manages energy consumption with unprecedented precision. Through this approach, we aim to revolutionize the electricity metering infrastructure, providing a blueprint for future advancements in the energy sector. © 2024 IEEE.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

Prefix-free graphs and suffix array construction in sublinear space 23

Prefix-free graphs and suffix array construction in sublinea...

引用

23rd Conference Information Technologies - Applications and Theory, ITAT 2023

作者： Baláž, Andrej Petescia, Alessia Department of Applied Informatics Faculty of Mathematics Physics and Informatics Comenius University Bratislava Slovakia

A recent paradigm shift in bioinformatics from a single reference genome to a pangenome brought with it several graph structures. These graph structures must implement operations, such as efficient construction from multiple genomes and read mapping. Read mapping is a well-studied problem in sequential data, and, together with data structures such as suffix array and Burrows-Wheeler transform, allows for efficient computation. Attempts to achieve comparatively high performance on graphs bring many complications since the common data structures on strings are not easily obtainable for graphs. In this work, we introduce prefix-free graphs, a novel pangenomic data structure;we show how to construct them and how to use them to obtain well-known data structures from stringology in sublinear space, allowing for many efficient operations on pangenomes. © 2023 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0). CEUR Workshop Proceedings (***)

关键词： Data structures

来源：评论

学校读者我要写书评

暂无评论

How Aphasia Influences Written and Spoken Texts 14

How Aphasia Influences Written and Spoken Texts

引用

14th International Conference on Measurement, MEASUREMENT 2023

作者： Petril'ak, Daniel Markosova, Maria Physics and Informatics Comenius University Faculty of Mathematics Department of Applied Informatics Bratislava Slovakia

ISBN: (纸本)9788097262976

Aphasia is disorder of the brain influencing language processing which occurs after the brain damage (such as stroke or brain tumor). People with aphasia have problems in communication in both spoken and written language. Their abilities to understand conversations or written sentences are strongly affected too. In this paper we analyze both written and spoken texts with a help of the graph theoretical, statistics and linguistics methods. We compare several statistical measures and other properties in texts, written or spoken, by people with and without aphasia. © 2023 Institute of Measurement Science, Slovak Academy o.

关键词： Graph theory

来源：评论

学校读者我要写书评

暂无评论

Digital Forensics Investigation Models: Current State and Analysis 8

Digital Forensics Investigation Models: Current State and An...

引用

8th International Conference on Smart and Sustainable Technologies, SpliTech 2023

作者： Ivanova, Malinka Stefanov, Svetlin University of Sofia Faculty of Applied Mathematics and Informatics Department of Informatics Technical Sofia Bulgaria

ISBN: (纸本)9789532901283

A digital forensics investigation (DFI) is characterized with activities related to search, identification, collection, analysis of digital evidences as all activities should be documented in a given format. Different models and methodologies are proposed to facilitate DFI, trying to describe procedures and activities performed by the investigator. Continuous technological development leads to the emergence of new sophisticated attacks, which also requires new approaches to be taken to crime scene investigation. In this paper a summary and analysis of contemporary achievements in DFI is performed to outline the current state of DFI development and to draw challenging issues and trending research topics. A conceptual model generalizing current state in DFI models is also presented. © 2023 University of Split, FESB.

关键词： Digital forensics

来源：评论

学校读者我要写书评

暂无评论

Constructions of Hypergraphical Regular Representations via k-uniform Hypergraphs of Certain Groups of Order Greater than 32 23

Constructions of Hypergraphical Regular Representations via ...

引用

23rd Conference Information Technologies - Applications and Theory, ITAT 2023

作者： Mihálová, Dominika Comenius University Faculty of Mathematics Physics and Informatics Department of Applied Informatics Bratislava Slovakia

The article explores the problem of hypergraphical regular representation of finite group G via k-uniform hypergraph. A hypergraphical regular representation preserves the group's structure within the hypergraph. The paper builds upon previous research and investigates hypergraphical regular representations of certain groups of orders greater than 32. The paper presents an algorithm based on methods by Mihálová and Erskine and Tuite. The algorithm is implemented in the computational system GAP to find hypergraphical regular representations for certain groups. The results include a table with groups for which hypergraphical regular representations via k-uniform hypergraphs were obtained. © 2023 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0). CEUR Workshop Proceedings (***)

关键词： Dual hypergraphs GAP Groups Hypergraphical Regular Representation k-uniform hypergraph

来源：评论

学校读者我要写书评

暂无评论

Real-time Simulation Framework for Validating Controllers of Virtual Synchronous Generators

Renewable Energy and Power Quality Journal

引用

Renewable Energy and Power Quality Journal 2023年 21卷 286-291页

作者： Chowdhury, M.M.R. Stranyóczky, L. Sütő, Z. Department of Automation and Applied Informatics Faculty of Electrical Engineering and Informatics Budapest University of Technology and Economics Műegyetem rkp. 3 BudapestH-1111 Hungary

The utilization of active rectifiers as converters in the interface between AC and DC microgrids has become a prevalent practice owing to their capacity to facilitate bidirectional power flow. The contemporary methodology for the development of power converters includes the integration of real-time simulation steps for the validation of control schemes and the assurance of safe implementation with hardware. The present study pro-poses a methodology for developing a real-time Hardware-in-the-Loop (HIL) simulation framework, which aims to facilitate the rapid prototyping of advanced control algorithms for an Active-Front-End (AFE) rectifier, especially a Virtual Synchronous Generator (VSG) control strategy. This approach aims to enhance the dynamic performance and stability of low-inertia power systems by mimicking the behavior of a synchronous generator, thereby providing virtual inertia to the power system. The control schemes and the primary circuit models are designed and implemented uti-lizing Matlab/Simulink and are optimized for code generation. © 2023, European Association for the Development of Renewable Energy, Environment and Power Quality (EA4EPQ). All rights reserved.

关键词： Simulink

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：