检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Mohamad, Mazen Department of Computer Science & Engineering Division of Interaction Design and Software Engineering Chalmers University of Technology Gothenburg University Gothenburg Sweden

Security Assurance Cases (SAC) are structured bodies of arguments and evidence used to reason about security properties of a certain artefact. SAC are gaining focus in the automotive domain as the need for security assurance is growing due to software becoming a main part of vehicles. Market demands for new services and products in the domain require connectivity, and hence, raise security concerns. Regulators and standardisation bodies started recently to require a structured for security assurance of products in the automotive domain, and automotive companies started, hence, to study ways to create and maintain these cases, as well as adopting them in their current way of working. In order to facilitate the adoption of SAC in the automotive domain, we created CASCADE, an approach for creating SAC which have integrated quality assurance and are compliant with the requirements of ISO/SAE-21434, the upcoming cybersecurity standard for automotive systems. CASCADE was created by conducting design science research study in two iterative cycles. The design decisions of CASCADE are based on insights from a qualitative research study which includes a workshop, a survey, and one-to-one interviews, done in collaboration with our industrial partners about the needs and drivers of work in SAC in industry, and a systematic literature review in which we identified gaps between the industrial needs and the state of the art. The evaluation of CASCADE was done with help of security experts from a large automotive OEM. It showed that CASCADE is suitable for integration in industrial product development processes. Additionally, our results show that the elements of CASCADE align well with respect to the way of working at the company, and has the potential to scale to cover the requirements and needs of the company with its large organization and complex products Copyright © 2024, The Authors. All rights reserved.

关键词： Automotive industry

来源：评论

学校读者我要写书评

暂无评论

design and Application of a Media Big Data Processing and Analysis Model Based on Artificial Intelligence 4

Design and Application of a Media Big Data Processing and An...

引用

4th IEEE International Conference on Mobile Networks and Wireless Communications, ICMNWC 2024

作者： Xiao, Shufang Wu, Siying Li, Kemin Wu, Dong Institute of Guangzhou University School of Game Department Software Engineering Guangdong Guangzhou China School of Art and Design Guangzhou College of Commerce Guangdong Guangzhou China School of Art Design and Creative Industries Guangzhou Southern University Guangdong Guangzhou China College of Art and Media Guangzhou Xinhua University Guangdong Guangzhou China

ISBN: (纸本)9798350352931

With the advent of the big data era, the amount and diversity of media data have grown exponentially, posing a major challenge to traditional data processing techniques. This paper studies an intelligent model to address these challenges, which uses deep learning and natural language processing to automatically extract and predict target features and achieve high-precision predictions, thereby improving the intelligence of the algorithm. A model that integrates convolutional neural networks and recurrent neural networks is established to effectively analyze multimodal data. It has an average accuracy of 89.072% in classification tasks and 89.184% in regression tasks, which is better than traditional methods such as sequence pattern mining, OLAP, and RDBMS. In addition, the model performs well in clustering tasks. In terms of efficiency, the model takes only 0.53 seconds on average to complete the task, with a CPU usage of 32.7%, a memory usage of 514MB, and an energy consumption of 0.045 units, all of which are better than the comparison methods. © 2024 IEEE.

关键词： Data accuracy

来源：评论

学校读者我要写书评

暂无评论

Explaining Spectrograms in Machine Learning: A Study on Neural Networks for Speech Classification

arXiv

引用

arXiv 2024年

作者： James, Jesin Balamurali, B.T. Abeysinghe, Binu Liu, Junchen Department of Electrical Computer and Software Engineering The University of Auckland New Zealand Singapore University of Technology and Design Singapore

This study investigates discriminative patterns learned by neural networks for accurate speech classification, with a specific focus on vowel classification tasks. By examining the activations and features of neural networks for vowel classification, we gain insights into what the networks "see" in spectrograms. Through the use of class activation mapping, we identify the frequencies that contribute to vowel classification and compare these findings with linguistic knowledge. Experiments on a American English dataset of vowels showcases the explainability of neural networks and provides valuable insights into the causes of misclassifications and their characteristics when differentiating them from unvoiced speech. This study not only enhances our understanding of the underlying acoustic cues in vowel classification but also offers opportunities for improving speech recognition by bridging the gap between abstract representations in neural networks and established linguistic knowledge. © 2024, CC BY.

关键词： Spectrographs

来源：评论

学校读者我要写书评

暂无评论

Accelerating Mutation-Based Fault Localization via Optimized Mutant Execution

Accelerating Mutation-Based Fault Localization via Optimized...

引用

International Conference on software Technology and engineering (ICSTE)

作者： Xia Li Ryan Juza The Department of Software Engineering and Game Design and Development Kennesaw State University Marietta USA

As modern software systems become more and more complex, bugs (also called faults) are prevalent and inevitable. Automated fault localization focuses on identifying faulty program elements that cause software failures. Mutation-based fault localization (MBFL) is one popular approach and has been proved to be more effective in real bugs. However, MBFL brings a problem of execution cost since it requires the execution of the whole test suite against a huge number of generated mutants. In this paper, we propose FastMBFL, a novel technique to improve the efficiency of MBFL by considering the importance of the impact information originated from failed test while maintaining the similar accuracy. The experimental results show that in terms of the widely used evaluation metric Mutant-Test Pair (MTP), FastMBFL can reduce the mutation cost by 24%–40% compared with the state-of-the-art technique.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Explaining Spectrograms in Machine Learning: A Study on Neural Networks for Speech Classification 5th

Explaining Spectrograms in Machine Learning: A Study on Neur...

引用

5th International Conference on Artificial Intelligence and Speech Technology, AIST 2023

作者： James, Jesin Balamurali, B.T. Abeysinghe, Binu Liu, Junchen Department of Electrical Computer and Software Engineering The University of Auckland Auckland New Zealand Singapore University of Technology and Design Singapore Singapore

ISBN: (纸本)9783031751639

关键词： Spectrographs

来源：评论

学校读者我要写书评

暂无评论

Reading Lists Systems' Pedagogical Features: A Comparative Analysis

Reading Lists Systems' Pedagogical Features: A Comparative A...

引用

IEEE/ACM Joint Conference on Digital Libraries(JCDL)

作者： PPNV Kumara Annika Hinze Nicholas Vanderschantz Claire Timpany Department of Software Engineering University of Waikato New Zealand Department of Design University of Waikato New Zealand

Reading Lists Systems are a pedagogical tool used in tertiary education to streamline the creation and management of course reading lists and make copyright compliance easier. This paper explores the design of current Reading Lists systems and how their features support the pedagogical needs of academics and students in tertiary education. A feature review combined with a comparative analysis approach was employed in our study. We analysed and compared Reading Lists systems and their features, implemented through Digital Libraries, that provide pedagogical support for academic teaching. As one of our outcomes, we identify the need to assist teachers to effectively use these tools in their daily practice.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Study of Two Types of Introductory Exercise Problems for Network Programming Learning with Python 23

A Study of Two Types of Introductory Exercise Problems for N...

引用

11th International Conference on Computer and Communications Management, ICCCM 2023

作者： Lu, Xiqin Funabiki, Nobuo Ueda, Kiyoshi Kao, Wen-Chung Department of Information and Communication Systems Distributed System Design Lab. Okayama University Okayama Japan Department of Computer Science Control Software Lab. Nihon University Koriyama Japan Department of Electrical Engineering National Taiwan Normal University Taipei Taiwan

ISBN: (纸本)9798400707735

Network programming is the act of writing computer codes for communications between programs or processes in different computers across networks. It is crucial for applications and services using networks, including e-commerce, gaming, and social media. However, university courses of educating it are very limited. As a result, it has become important to develop and offer IT tools to support self-studies of network programming by novices. In this paper, we present a study of two types of introductory exercise problems, namely, Grammar-concept Understanding Problem (GUP) and Comment Insertion Problem (CIP), for self-studies of five basic network protocols of TCP/IP, ARP, SMTP, POP3, and SSH with Python. A GUP instance requests to answer the keyword such as a library function in the given source code that corresponds to the grammar concept described in the question. A CIP instance requests to insert the comment at each blank of the code. String matching is adopted to mark any answer at the browser-based answer interface. Through solving them, it is expected to understand the meaning of important words and the code structure for network programming. As preliminary evaluations, we generated six GUP and CIP instances respectively, and assigned them to 10 students in Okayama University, Japan. The results confirmed that the proposal is proper for novices to learn network programming with Python. © 2023 ACM.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

Accelerating ab initio melting property calculations with machine learning:application to the high entropy alloy TaVCrW

引用

npj Computational Materials 2024年第1期10卷 328-338页

作者： Li-Fang Zhu Fritz Körmann Qing Chen Malin Selleby Jörg Neugebauer Blazej Grabowski Department for Computational Materials Design Max Planck Institute for Sustainable MaterialsMax-Planck-str.140237 DüsseldorfGermany Institute for Materials Science University of StuttgartPfaffenwaldring 5570569 StuttgartGermany Interdisciplinary Centre for Advanced Materials Simulation(ICAMS) Ruhr-Universität Bochum44801 BochumGermany Thermo-Calc Software AB Råsundavägen 18SE-16967 SolnaSweden Department of Materials Science and Engineering KTH Royal Institute of TechnologySE-10044StockholmSweden

Melting properties are critical for designing novel materials,especially for discovering highperformance,high-melting refractory *** measurements of these properties are extremely challenging due to their high melting *** theoretical predictions are,therefore,*** of the most accurate approaches for this purpose is the ab initio free-energy approach based on density functional theory(DFT).However,it generally involves expensive thermodynamic integration using ab initio molecular dynamic *** high computational cost makes high-throughput calculations ***,we propose a highly efficient DFT-based method aided by a specially designed machine learning *** the machine learning potential can closely reproduce the ab initio phase-space distribution,even for multi-component alloys,the costly thermodynamic integration can be fully substituted with more efficient free energy perturbation *** method achieves overall savings of computational resources by 80%compared to current *** apply the method to the high-entropy alloy TaVCrW and calculate its melting properties,including the melting temperature,entropy and enthalpy of fusion,and volume change at the melting ***,the heat capacities of solid and liquid TaVCrW are *** results agree reasonably with the CALPHAD extrapolated values.

关键词： alloy entropy high

来源：评论

学校读者我要写书评

暂无评论

Building the metaverse using digital twins at all scales,states,and relations

引用

Virtual Reality & Intelligent Hardware 2022年第6期4卷 459-470页

作者： Zhihan LV Shuxuan XIE Yuxi LI M.Shamim HOSSAIN Abdulmotaleb El SADDIK Department of Game Design Faculty of ArtsUppsala UniversitySweden College of Computer Science and Technology Qingdao UniversityQingdaoChina Department of Software Engineering College of Computer and Information SciencesKing Saud UniversityRiyadhSaudi Arabia School of Electrical Engineering and Computer Science(EECS) University of OttawaOttawaOntarioCanada

Developments in new-generation information technology have enabled Digital Twins to reshape the physical world into a virtual digital space and provide technical support for constructing the *** objects can be at the micro-,meso-,or *** Metaverse is a complex collection of solid,liquid,gaseous,plasma,and other uncertain ***,the Metaverse integrates tangibles with social relations,such as interpersonal(friends,partners,and family)and social relations(ethics,morality,and law).This review introduces some principles and laws,such as broken windows theory,small-world phenomenon,survivor bias,and herd behavior,for constructing a Digital Twins model for social ***,from multiple perspectives,this article reviews mappings of tangible and intangible real-world objects to the Metaverse using the Digital Twins model.

关键词： Digital twins Metaverse Sensor

来源：评论

学校读者我要写书评

暂无评论

Analysis of Two Papers Based on RSA Algorithm: Plagiarism Investigation of HRSA Algorithm

Analysis of Two Papers Based on RSA Algorithm: Plagiarism In...

引用

IEEE International Symposium on Information (IT) in Medicine and Education, ITME

作者： Zhiying Liu Chunhua Cao Ruopengyu Xu Chenglian Liu Passino K. M. Bi Department of Network Technology Software Engineering Institute of Guangzhou Guangdong China Digital Media Design Foshan University Guangdong China

ISBN: (数字)9798350356670

ISBN: (纸本)9798350356687

The RSA algorithm, as one of the cornerstones in the field of cyber security, has always received widespread attention and research. Many scholars have published relevant research papers. This article focuses on the highly similar issues between the conference paper "Hybrid Security RSA Algorithm in Application of Web Service" published in 2018 at the 1st International Conference on Data Intelligence and Security and the paper "A Hybrid Security Algorithm for RSA Encryption system" published in 2017 at the International Conference on Advanced Computing and Communication Systems. By comparing algorithm details, experimental data differences, innovative points, and other possible academic misconduct, the aim is to provide readers with a comprehensive and in-depth understanding. This article first introduces the background and importance of the RSA algorithm, followed by a detailed analysis of the main content and research results of the two papers, and then explores their similarities and differences by comparing experimental data and algorithm details. Finally, the article will objectively evaluate the possible plagiarism behavior in the two papers based on academic norms and research ethics, and provide corresponding suggestions and reflections.

关键词： Ethics Web services Plagiarism Education Resists Reflection Data models Encryption Security Information technology

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：