检索结果-内蒙古大学图书馆

Light-Weighted Decision Support Framework for Selecting Cloud Service Providers

computers, Materials & Continua 2023年第2期74卷 4293-4317页

作者： Abdulmajeed Aljuhani Abdulaziz Alhubaishy Mohammad Khalid Imam Rahmani Ahmad A.Alzahrani College of Computer Science and Engineering Taibah UniversityMedina41411Saudi Arabia College of Computing and Informatics Saudi Electronic UniversityRiyadh11673Saudi Arabia Computer Science Common First Year DeanshipUmm-AlQura UniversityMakkahMKSaudi Arabia

Multi-criteria decision making(MCDM)is a technique used to achieve better outcomes for some complex business-related problems,whereby the selection of the best alternative can be made in as many cases as *** paper proposes a model,the multi-criteria decision support method,that allows both service providers and consumers to maximize their profits while preserving the best matching process for resource allocation and task *** increasing number of service providers with different service provision capabilities creates an issue for consumers seeking to select the best service *** consumer seeks a service provider based on various preferences,such as price,service quality,and time to complete the *** the literature,the problem is viewed from different perspectives,such as investigating how to enhance task scheduling and the resource allocation process,improve consumers’trust,and deal with network *** paper offers a novel model that considers the preferences of both service providers and consumers to find the best available service provider for each ***,the model adopts the best-worst method(BWM)to gather and prioritize tasks based on consumers’and service providers’***,the model calculates and matches similarities between the sets of tasks from the consumer’s side with the sets of tasks from the provider’s side to select the best service provider for each consumer using the two proposed *** complexity of the two algorithms is found to be O(n3).

关键词： Best worst method BWM cloud service provider decision support methods

来源：评论

学校读者我要写书评

暂无评论

Developing a Model to Detect Malicious URLs using Different Classification Algorithms 21

Developing a Model to Detect Malicious URLs using Different ...

引用

21st International Learning and Technology Conference, L and T 2024

作者： Hariri, Jana Batouq, Lujain Al-Jarf, Ahd College of Computing Department of Computer Science and Artificial Intelligence Makkah Saudi Arabia College of Computing Department of Cybersecurity Makkah Saudi Arabia

ISBN: (纸本)9798350393569

The number of social media users in Saudi Arabia is increasing by the day, and the rate of cyberattacks has increased accordingly. This can be partially due to the dearth of tools that can be used to check and ensure the integrity of URLs. This study introduced a model for classifying URLs into benign and malicious ones to help users avoid falling victim to phishing schemes using URLs contained in messages. By using five classification algorithms were compared: logistic regression (LR), support vector machine (SVM), random forest (RF), decision tree (DT) and gradient boosting (GB). The algorithms' performances were based on their accuracy and confusion matrices. The SVM algorithm was found to be the most accurate (95.4%) and the best algorithm for verifying the validity of URLs. © 2024 IEEE.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Bias analysis of AI models for undergraduate student admissions

引用

Neural computing and Applications 2025年第12期37卷 7785-7795页

作者： Van Busum, Kelly Fang, Shiaofen Department of Computer Science and Software Engineering Butler University IndianapolisIN United States Computing and Engineering Indiana University Luddy School of Informatics Indiana University Indianapolis IndianapolisIN United States

Bias detection and mitigation is an active area of research in machine learning. This work extends previous research done by the authors Van Busum and Fang (Proceedings of the 38th ACM/SIGAPP Symposium on Applied computing, 2023) to provide a rigorous and more complete analysis of the bias found in AI predictive models. Admissions data spanning six years was used to create an AI model to determine whether a given student would be directly admitted into the School of science under various scenarios at a large urban research university. During this time, submission of standardized test scores as part of a student’s application became optional which led to interesting questions about the impact of standardized test scores on admission decisions. We developed and analyzed AI models to understand which variables are important in admissions decisions, and how the decision to exclude test scores affects the demographics of the students who are admitted. We then evaluated the predictive models to detect and analyze biases these models may carry with respect to three variables chosen to represent sensitive populations: gender, race, and whether a student was the first in his/her family to attend college. We also extended our analysis to show that the biases detected were persistent. Finally, we included several fairness metrics in our analysis and discussed the uses and limitations of these metrics. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Adjusting Logit in Gaussian Form for Long-Tailed Visual Recognition

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第10期5卷 5026-5039页

作者： Li, Mengke Cheung, Yiu-Ming Lu, Yang Hu, Zhikai Lan, Weichao Huang, Hui Shenzhen518132 China Hong Kong Baptist University Department of Computer Science 999077 Hong Kong Xiamen University Fujian Key Laboratory of Sensing and Computing for Smart City School of Informatics Xiamen361005 China Shenzhen University College of Computer Science and Software Engineering Shenzhen518060 China

It is not uncommon that real-world data are distributed with a long tail. For such data, the learning of deep neural networks becomes challenging because it is hard to classify tail classes correctly. In the literature, several existing methods have addressed this problem by reducing classifier bias, provided that the features obtained with long-tailed data are representative enough. However, we find that training directly on long-tailed data leads to uneven embedding space. That is, the embedding space of head classes severely compresses that of tail classes, which is not conducive to subsequent classifier learning. This article therefore studies the problem of long-tailed visual recognition from the perspective of feature level. We introduce feature augmentation to balance the embedding distribution. The features of different classes are perturbed with varying amplitudes in Gaussian form. Based on these perturbed features, two novel logit adjustment methods are proposed to improve model performance at a modest computational overhead. Subsequently, the distorted embedding spaces of all classes can be calibrated. In such balanced-distributed embedding spaces, the biased classifier can be eliminated by simply retraining the classifier with class-balanced sampling data. Extensive experiments conducted on benchmark datasets demonstrate the superior performance of the proposed method over the state-of-the-art ones. © 2020 IEEE.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Privacy-preserving human activity sensing:A survey

引用

High-Confidence computing 2024年第1期4卷 108-117页

作者： Yanni Yang Pengfei Hu Jiaxing Shen Haiming Cheng Zhenlin An Xiulong Liu School of Computer Science and Technology Shandong UniversityQingdao 266237China Department of Computing and Decision Sciences Lingnan UniversityHong KongChina Department of Computing The Hong Kong Polytechnic UniversityHong KongChina Department of Computer Science Princeton UniversityNJ 08544USA College of Intelligence and Computing Tianjin UniversityTianjin 300350China

With the prevalence of various sensors and smart devices in people’s daily lives,numerous types of information are being *** using such information provides critical and convenient services,we are gradually exposing every piece of our behavior and *** are aware of the privacy risks and have been working on preserving privacy while sensing human *** survey reviews existing studies on privacy-preserving human activity *** first introduce the sensors and captured private information related to human *** then propose a taxonomy to structure the methods for preserving private information from two aspects:individual and collaborative activity *** each of the two aspects,the methods are classified into three levels:signal,algorithm,and ***,we discuss the open challenges and provide future directions.

关键词： Human activity sensing Privacy-preserving sensing Activity sensing algorithms Human sensors Privacy protection

来源：评论

学校读者我要写书评

暂无评论

On the Performance Evaluation of Mobility Model-Based GPSR Routing Protocol in Flying Ad hoc Networks 6

On the Performance Evaluation of Mobility Model-Based GPSR R...

引用

6th International Conference on Pattern Analysis and Intelligent Systems, PAIS 2024

作者： Bezziane, Mohamed Ben Sahraoui, Yesin Brik, Bouziane Mekkas, Lina Bougeurra, Sara Khaldi, Anouar University Kasdi Merbah Computer Science And Information Technologies Department Ouargla Algeria National Higher School of Artificial Intelligence Computer Science Algiers Algeria University of Sharjah College of Computing And Informatics Computer Science Department Sharjah United Arab Emirates

ISBN: (纸本)9798350350265

In recent times, we have witnessed the rapid and remarkable evolution of communication technologies, particularly in the domain of Flying Ad Hoc Networks (FANETs). This evolution has necessitated a thorough evaluation and significant enhancement of routing protocols to improve the overall performance of the system. To address the challenge of efficiently routing data in FANETs, where conventional methods may fall short during dynamic scenarios, the need for an effective framework becomes paramount in addressing these challenges. This paper aims to optimize routing efficiency in the context of FANETs, evaluating the performance of Greedy Perimeter Stateless Routing (GPSR) routing protocol under various mobility models, including Random Waypoint Mobility (RWPM), Mass Mobility, and Gauss Markov mobility models, to uncover their strengths and limitations. The simulation results reveal notable variations in performance indicators, including End-to-End delay, Packet Delivery Ratio, and Loss rate across various mobility models. However, Mass Mobility and Gauss-Markov Mobility exhibited consistent increases in Energy Consumption as the UAV count rose. On the other hand, Random Way Point Mobility demonstrated higher energy consumption compared to the former models. These findings offer valuable insights for selecting the most suitable mobility model for specific applications, and improving routing protocols, thereby advancing the reliability and effectiveness of Flying Ad Hoc environments. © 2024 IEEE.

关键词： Routing protocols

来源：评论

学校读者我要写书评

暂无评论

Blockchain-based knowledge-aware semantic communications for remote driving image transmission

引用

Digital Communications and Networks 2025年第2期11卷 317-325页

作者： Yangfei Lin Tutomu Murase Yusheng Ji Wugedele Bao Lei Zhong Jie Li Department of Computer and Network Engineering University of Electro-Communications Information Technology Center Nagoya University National Institute of Informatics(NII) Hohhot Minzu College Toyota Motor Corporation Department of Computer Science and Engineering Shanghai Jiaotong University

Remote driving, an emergent technology enabling remote operations of vehicles, presents a significant challenge in transmitting large volumes of image data to a central server. This requirement outpaces the capacity of traditional communication methods. To tackle this, we propose a novel framework using semantic communications, through a region of interest semantic segmentation method, to reduce the communication costs by transmitting meaningful semantic information rather than bit-wise data. To solve the knowledge base inconsistencies inherent in semantic communications, we introduce a blockchain-based edge-assisted system for managing diverse and geographically varied semantic segmentation knowledge bases. This system not only ensures the security of data through the tamper-resistant nature of blockchain but also leverages edge computing for efficient management. Additionally, the implementation of blockchain sharding handles differentiated knowledge bases for various tasks, thus boosting overall blockchain efficiency. Experimental results show a great reduction in latency by sharding and an increase in model accuracy, confirming our framework's effectiveness.

关键词： Semantic communication Remote driving Semantic segmentation Blockchain Knowledge base management

来源：评论

学校读者我要写书评

暂无评论

Efficient and Secure IoT Based Smart Home Automation Using Multi-Model Learning and Blockchain Technology

引用

computer Modeling in Engineering & sciences 2024年第6期139卷 3387-3415页

作者： Nazik Alturki Raed Alharthi Muhammad Umer Oumaima Saidani Amal Alshardan Reemah M.Alhebshi Shtwai Alsubai Ali Kashif Bashir Department of Information Systems College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadhSaudi Arabia Department of Computer Science and Engineering University of Hafr Al-BatinHafar Al-BatinSaudi Arabia Department of Computer Science&Information Technology The Islamia University of BahawalpurBahawalpurPakistan Department of Computer Science Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddahSaudi Arabia Department of Computer Science College of Computer Engineering and SciencesPrince Sattam bin Abdulaziz UniversityAl-KharjSaudi Arabia Department of Computing and Mathematics Manchester Metropolitan UniversityManchesterUK Woxsen School of Business Woxsen UniversityHyderabadIndia Department of Computer Science and Mathematics Lebanese American UniversityBeirutLebanon

The concept of smart houses has grown in prominence in recent *** challenges linked to smart homes are identification theft,data safety,automated decision-making for IoT-based devices,and the security of the device *** home automation systems try to address these issues but there is still an urgent need for a dependable and secure smart home solution that includes automatic decision-making systems and methodical *** paper proposes a smart home system based on ensemble learning of random forest(RF)and convolutional neural networks(CNN)for programmed decision-making tasks,such as categorizing gadgets as“OFF”or“ON”based on their normal routine in *** have integrated emerging blockchain technology to provide secure,decentralized,and trustworthy authentication and recognition of IoT *** system consists of a 5V relay circuit,various sensors,and a Raspberry Pi server and database for managing *** have also developed an Android app that communicates with the server interface through an HTTP web interface and an Apache *** feasibility and efficacy of the proposed smart home automation system have been evaluated in both laboratory and real-time *** is essential to use inexpensive,scalable,and readily available components and technologies in smart home automation ***,we must incorporate a comprehensive security and privacy-centric design that emphasizes risk assessments,such as cyberattacks,hardware security,and other cyber *** trial results support the proposed system and demonstrate its potential for use in everyday life.

关键词： Blockchain Internet of Things(IoT) smart home automation cybersecurity

来源：评论

学校读者我要写书评

暂无评论

The Role of Privacy and Security Concerns and Trust in Online Teaching: Experiences of Higher Education Students in the Kingdom of Saudi Arabia 16

The Role of Privacy and Security Concerns and Trust in Onlin...

引用

16th International Conference on computer Supported Education, CSEDU 2024

作者： Almekhled, Basmah Petrie, Helen Department of Computer Science University of York Heslington East York United Kingdom College of Computing and Informatics Saudi Electronic University Riyadh Saudi Arabia

ISBN: (纸本)9789897586972

Higher education institutions (HEIs) are increasingly using online teaching, particularly since the COVID-19 pandemic. Numerous digital technologies are now used in online teaching, such as videoconferencing for online classes. This has raised privacy and security concerns for students, as well as a reluctance to have webcams on during online classes. This study investigated the privacy and security concerns in online teaching of HEI students in the Kingdom of Saudi Arabia (KSA), as well as their trust in a range of actors and entities involved in online teaching. It also investigated their use of webcams and their reasons for having their webcams off during online classes. The study was conducted in the real-world context of online courses at a HEI in KSA. It found high levels of concern about online privacy in relation to the institution, but moderate levels in relation to instructors and classmates and in relation to online security. Complex, unexpected relationships were found between online privacy and security concerns and trust. As with previous research, students were reluctant to have their webcams on for a variety of reasons, often concerned with privacy of personal information. Only trust in instructors was a significant predictor of whether students were likely to have their webcams on during online classes. Copyright © 2024 by SCITEPRESS – science and Technology Publications, Lda.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Comparative analysis of Start-up Success Rate Prediction Using Machine Learning Techniques 3

Comparative analysis of Start-up Success Rate Prediction Usi...

引用

3rd International Conference on Smart Technologies and Systems for Next Generation computing, ICSTSN 2024

作者： Belgaum, Mohammad Riyaz Viswanath, Ediga Kasi Chakradhar, Pavukolla Goud, Ediga Chenna Kesava Chandu, Kuruva G. Pullaiah College of Engineering and Technology Department of Computer Science and Engineering Kurnool India Multimedia University Faculty of Computing and Informatics Cyberjaya Malaysia

ISBN: (纸本)9798350391565

Software startups create innovative products or services using programming, which can lead to a need for products from potential customers. Researchers suggest that trial and error methodology can increase the success rate of these organizations by evaluating assumptions about client needs before fostering a product. However, programming new businesses typically do not require trial and error. The study aims to predict the success of startup companies in their early development stages by analyzing their success based on initial funding. A study of 106 unsuccessful software start-ups was conducted to predict the success rate. The experimentation progression model (X Pro) was developed to show that effective experimentation requires understanding trial and error, setting objectives, conducting tests, analyzing results, and acting based on new knowledge. The findings provide insights into supporting procedures and approaches that enhance trial- and-error reception in developing new business models. Researchers can become aware of potential factors leading to startup disappointment and take precautions to avoid them. The research focuses on using web-based open sources, including social networking services and the web, to model the task. The study uses machine learning techniques like Random Forest, Gradient Boost Classifier, XG Boost, and Ada Boost Classifier. The analysis provides insights into the types of useful signals discovered on the web and market mechanisms underlying the funding process. This approach offers a more comprehensive approach to predicting startup success. © 2024 IEEE.

关键词： Ada (programming language)

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：