检索结果-内蒙古大学图书馆

3rd International Conference on Advancement in Electrical and Electronic Engineering, ICAEEE 2024

作者： Islam, Md Aminul Asif Imran, A.T.M. Rahman, Md Habibur Pabel, Md Amran Hossen Mishra, Bhupesh Kumar Basu, Kashinath University of Gloucestershire Data Science School of Engineering and Technology Cheltenham United Kingdom Dhaka Bangladesh University of Chittagong Department of Mathematics Chittagong Bangladesh Wright State University Master of Science in Business Analytics United States United Kingdom Oxford Brookes University Data Science School of Engineering Computing and Mathematics United Kingdom

ISBN: (纸本)9798350388282

Using credit cards is a convenient and efficient payment mechanism. Credit card fraud significantly impacts financial loss, mental health, and the reputation of financial institutions. This study would incorporate an analysis of the preceding statement about eliminating several obstacles associated with the availability of public data, the presence of unbalanced data, the dynamic nature of fraud tendencies, and the prevalence of false alarms. The authors discuss various machine-learning techniques used to detect credit card fraud. Extreme Learning, Decision Trees, Random Forests, Support Vector Machines, Logistic Regression, and XG Boost are among these techniques on the European card benchmark dataset. A comparative evaluation of the effectiveness of machine learning has also been conducted, and precision is increased by incorporating multiple layers. The study's findings indicate significant improvements in several crucial metrics, including accuracy, f1-score, precision, and AUC curves. XGBoost model achieves optimized values of 99.9\% accuracy. The proposed model outperforms contemporary machine learning approaches in credit card fraud detection. It has been observed that the combination of data balancing techniques significantly reduces the occurrence of false negatives. This study has substantial potential for credit card fraud detection applications in the real world, providing an effective and efficient method for addressing this ongoing critical issue. © 2024 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Automated Image Captioning with CNNs and Transformers

arXiv

引用

arXiv 2024年

作者： Cahyono, Joshua Adrian Jusuf, Jeremy Nathan College of Computing and Data Science Nanyang Technological University Singapore

This project aims to create an automated image captioning system that generates natural language descriptions for input images by integrating techniques from computer vision and natural language processing. We employ various different techniques, ranging from CNN-RNN to the more advanced transformer-based techniques. Training is carried out on image datasets paired with descriptive captions, and model performance will be evaluated using established metrics such as BLEU, METEOR, and CIDEr. The project will also involve experimentation with advanced attention mechanisms, comparisons of different architectural choices, and hyperparameter optimization to refine captioning accuracy and overall system effectiveness. © 2024, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimizing Electric Bus Charging Scheduling With Uncertainties Using Hierarchical Deep Reinforcement Learning

引用

IEEE Internet of Things Journal 2025年第12期12卷 22427-22442页

作者： Qi, Jiaju Lei, Lei Jonsson, Thorsteinn Niyato, Dusit University of Guelph School of Engineering GuelphONN1G 2W1 Canada EthicalAI WaterlooONN2L 0C7 Canada Nanyang Technological University College of Computing and Data Science 639798 Singapore

The growing adoption of Electric Buses (EBs) represents a significant step toward sustainable development. By utilizing Internet of Things (IoT) systems, charging stations can autonomously determine charging schedules based on real-time data. However, optimizing EB charging schedules remains a critical challenge due to uncertainties in travel time, energy consumption, and fluctuating electricity prices. Moreover, to address real-world complexities, charging policies must make decisions efficiently across multiple time scales and remain scalable for large EB fleets. In this paper, we propose a Hierarchical Deep Reinforcement Learning (HDRL) approach that reformulates the original Markov Decision Process (MDP) into two augmented MDPs. To solve these MDPs and enable multi-timescale decision-making, we introduce a novel HDRL algorithm, namely Double Actor-Critic Multi-Agent Proximal Policy Optimization Enhancement (DAC-MAPPO-E). Scalability challenges of the Double Actor-Critic (DAC) algorithm for large-scale EB fleets are addressed through enhancements at both decision levels. At the high level, we redesign the decentralized actor network and integrate an attention mechanism to extract relevant global state information for each EB, decreasing the size of neural networks. At the low level, the Multi-Agent Proximal Policy Optimization (MAPPO) algorithm is incorporated into the DAC framework, enabling decentralized and coordinated charging power decisions, reducing computational complexity and enhancing convergence speed. Extensive experiments with real-world data demonstrate the superior performance and scalability of DAC-MAPPO-E in optimizing EB fleet charging schedules. © 2014 IEEE.

关键词： Charging stations

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of Vehicle to Infrastructure Network 6

Performance Analysis of Vehicle to Infrastructure Network

引用

6th International Conference on Advanced Communication Technologies and Networking, CommNet 2023

作者： Mbanzabugabo, Opel N. Kabiri, Charles Jayavel, Kayalvizhi Sibomana, Louis University of the Arts London Data Science and Artificial Intelligence Creative Computing Institute London United Kingdom Kigali Rwanda National Council for Science and Technology Kigali Rwanda

ISBN: (纸本)9798350329391

For improving traffic safety and the driving experience, vehicle-to-infrastructure (V2I) networks require ultra-reliable and low-latency connectivity. However, because of the increased mobility of vehicles, the channel is continuously varying, making it difficult to maintain low latency and high connectivity in V2I networks. Additionally, as the number of vehicles increases, sufficient resources is needed to maintain continuous internet access via a Base Station (BS). By introducing a three-tiered prioritization mechanism, this study aims at improving resource constraints in V2I networks. The highest priority (priority 1) is assigned to emergency communications, which include critical communications such as ambulance notifications, accident reports, and alerts regarding very important people. Priority 2 is assigned to data, such as road conditions and traffic information. data concerning entertainment, such as media and ordinary communications, come into the category of low priority (priority 3). By employing this prioritization strategy, efficient resource allocation is ensured, taking into consideration different levels of urgency within services. An Analytical Priority Resources Allocation Framework (APRAF) based on M/G/1 queuing method, is developed with an objective of enhancing connectivity in the uplink of vehicles to infrastructure networks. The proposed method is evaluated using an M/G/1 queuing method where delays on queue and system are considered as main performance metrics. Using numerical analysis, the lowest latency is obtained gradually from the highest to the lowest class. As a result, the latency (waiting delay on queue and on system) for vehicles on priority 1 is very low, and in this way the connectivity is improved comparatively to existing system without priority. The waiting delay in the system for vehicles in high priority is around 66 ms while in First Come First Served model without priority, the waiting delay is infinite. The reliability i

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

A Survey on Physical Event Verification in User-centric Smart Home Systems

A Survey on Physical Event Verification in User-centric Smar...

引用

IEEE International Conference on Software Reliability Engineering Workshops (ISSRE Wksp)

作者： Bing Huang Kwok-Yan Lam School of Computing and Data Science Nanyang Technological University Singapore

ISBN: (数字)9798350367041

ISBN: (纸本)9798350367058

Recent advances in IoT technologies have led to the rise of home automation (HA) systems, greatly improving users’ daily life quality. With the growing use of smart devices in homes, event sensors play a key role by reporting physical events like doors opening or lights turning on, automatically or manually. However, these sensor reports can be unreliable due to faults or active attackers, leading to false events (event spoofing). This is critical, as smart homes can trigger event chains without user involvement. Therefore, verifying the authenticity of physical events is important in securing smart home automation systems. Despite increasing attention from academia and industry, no survey has yet summarized HA systems’ security research on physical event verification. This paper provides a comprehensive review of physical event verification and future research directions.

关键词： Surveys Systematics Reviews Smart homes Turning Software reliability Security Object recognition Smart devices Intelligent sensors

来源：评论

学校读者我要写书评

暂无评论

BERD+: A Generic Sequential Recommendation Framework by Eliminating Unreliable data with Item- and Attribute-level Signals

引用

ACM Transactions on Information Systems 2023年第2期42卷 1-33页

作者： Sun, Yatong Yang, Xiaochun Sun, Zhu Wang, Bin School of Computer Science and Engineering Northeastern University School of Computing Macquarie University China Australia Institute of High Performance Computing Centre for Frontier AI Research A*STAR Singapore School of Computer Science and Engineering Northeastern University China National Frontiers Science Center for Industrial Intelligence and Systems Optimization China Key Laboratory of Data Analytics and Optimization for Smart Industry [Northeastern University Ministry of Education China

A preliminary work of our study was published at IJCAI’21 [47], which is substantially extended in the following aspects: (1) In Section 1, we analyze the necessity of introducing item attributes for detecting unreliable instances, together with the problems and challenges that attributes may bring in. (2) In Section 2, we add discussions about the limitations of existing attribute-aware recommender systems (Section 2.2) and denoising methods (Section 2.3) in the context of detecting unreliable instances. (3) In Section 4.2, we further conduct an in-depth analysis at the attribute level to demonstrate the capability of attributes for rectifying instance loss and uncertainty, as well as the disturbance caused by attributes. (4) We generalize BERD to a generic framework BERD+ in Section 5.1, equipped with novel modules, i.e., HU-GCN (Section 5.2) and EPE (Section 5.4), which properly incorporate item attributes while reducing their disturbance for rectifying instance uncer tainty (Section 5.5) and loss (Section 5.6). The generic BERD+ can be flexibly plugged into existing SRSs for performance enhanced recommendation via eliminating unreliable data. (5) In Section 6.2, we apply our BERD+ framework to seven state-of-the-art SRSs on five real-world datasets to illustrate its superiority. (6) To avoid unfair comparison caused by item attributes, we build and compare with the baseline that combines the original BERD and an advanced attribute-aware recommender system, KSR [19]. (7) For more comprehensive comparison, in Section 6.2.2, we compare BRED+ with two state-of-the-art denoising approaches;in Section 6.2.3, to examine the efficacy of HU-GCN and EPE, we compare HU-GCN with various attribute embedding techniques, i.e., variants of graph neural networks, and compare EPE with different attribute fusing methods, i.e., adding, concatenation, and weighted sum. (8) In Section 6.2.4, a detailed ablation study is conducted to verify the effectiveness of each module of BERD+. (

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

AI in Education for Corporate Training

AI in Education for Corporate Training

引用

Intelligent Education and Intelligent Research (IEIR), International Conference on

作者： Kuchhal Shourya Zhiqi Shen College of Computing & Data Science Nanyang Technological University Singapore

ISBN: (数字)9798331519827

ISBN: (纸本)9798331519834

The gap between employer demands and the skills highlighted on resumes reveals a major flaw in traditional university education. The current one-size-fits-all approach leaves graduates unprepared for the fast-evolving job market. To address this, we are developing an AI-powered personalized learning platform tailored to corporate training. This platform utilizes a machine learning model that analyzes individual resumes to generate customized course maps based on the user’s unique background and career goals. By aligning educational pathways with specific job requirements, it caters to the growing need for job-specific programs, especially among Gen Z. A Logistic Regression Model is trained on resume datasets to predict suitable professions for users, while tools like Gensim and TensorFlow help construct personalized knowledge graphs of relevant courses. Various graph-based algorithms like PageRank, SimRank, and HITS are used to generate an optimized study map, considering course difficulty and prerequisites. This innovative approach offers a significant leap in helping job seekers refine their skills and meet employer expectations. The platform's findings could ultimately be integrated into corporate training programs, enhancing workforce development and addressing the shortcomings of traditional education systems.

关键词： Training Industries Logistic regression Accuracy Resumes Knowledge graphs Companies Predictive models Prediction algorithms Optimization

来源：评论

学校读者我要写书评

暂无评论

Research on performance optimization of virtual data space across WAN

引用

Frontiers of Computer science 2024年第6期18卷 167-187页

作者： Jiantong HUO Zhisheng HUO Limin XIAO Zhenxue HE State Key Laboratory of Software Development Environment Beihang UniversityBeijing 100191China School of Computer Science and Engineering Beihang UniversityBeijing 100191China High Performance Computing Center Beihang UniversityBeijing 100191China Hebei Key Laboratory of Agricultural Big Data Hebei Agricultural UniversityBaoding 071001China

For the high-performance computing in a WAN environment,the geographical locations of national supercomputing centers are scattered and the network topology is complex,so it is difficult to form a unified view of *** aggregate the widely dispersed storage resources of national supercomputing centers in China,we have previously proposed a global virtual data space named GVDS in the project of“High Performance computing Virtual data Space”,a part of the National Key Research and Development Program of *** GVDS enables large-scale applications of the high-performance computing to run efficiently across ***,the applications running on the GVDS are often data-intensive,requiring large amounts of data from multiple supercomputing centers across *** this regard,the GVDS suffers from performance bottlenecks in data migration and access across *** solve the above-mentioned problem,this paper proposes a performance optimization framework of GVDS including the multitask-oriented data migration method and the request access-aware IO proxy resource allocation *** a WAN environment,the framework proposed in this paper can make an efficient migration decision based on the amount of migrated data and the number of multiple data sources,guaranteeing lower average migration latency when multiple data migration tasks are running in *** addition,it can ensure that the thread resource of the IO proxy node is fairly allocated among different types of requests(the IO proxy is a module of GVDS),so as to improve the application’s performance across *** experimental results show that the framework can effectively reduce the average data access delay of GVDS while improving the performance of the application greatly.

关键词： storage aggregation across WANs large-scale applications GVDS data migration allocation of IO proxy resource

来源：评论

学校读者我要写书评

暂无评论

Question Answering System using NLP and BERT 3

Question Answering System using NLP and BERT

引用

3rd International Conference on Smart Electronics and Communication, ICOSEC 2022

作者： Acharya, Shreya Sornalakshmi, K. Paul, Bidisha Singh, Anshul Srm Institute of Science and Technology School of Computing Department of Data Science and Business Systems Tamil Nadu India

ISBN: (数字)9781665497640

ISBN: (纸本)9781665497640

This project proposes a simple and smart question answering system using Named Entity Recognition (NER) and Bidirectional Encoder Representations from Transformers (BERT) for communication purposes. Communication is a major factor that eases our day-to-day work. In this smart Question answering system, the system will create a customized dataset for the user based on the answers given by the user. Using NER, only the selective answers are taken, i.e., the most important answers, and then updated in the dataset. Based on that dataset, if a person then asks the system a question, the system will use BERT and CDQA (closed domain question answering) to fetch the best answer for the question asked. The resulting system will be an interactive one. © 2022 IEEE.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Fortifying Smart Grids: A Holistic Assessment Strategy against Cyber Attacks and Physical Threats for Intelligent Electronic Devices

引用

Computers, Materials & Continua 2024年第8期80卷 2579-2609页

作者： Yangrong Chen June Li Yu Xia Ruiwen Zhang Lingling Li Xiaoyu Li Lin Ge School of Computer Science Zhengzhou University of AeronauticsZhengzhou450046China Henan Xin’an Century Technology Co. Ltd.Henan Data Security Engineering Technology Research CenterZhengzhou450046China Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of EducationSchool of Cyber Science and EngineeringWuhan UniversityWuhan430072China

Intelligent electronic devices(IEDs)are interconnected via communication networks and play pivotal roles in transmitting grid-related operational data and executing control *** the context of the heightened security challenges within smart grids,IEDs pose significant risks due to inherent hardware and software vulner-abilities,as well as the openness and vulnerability of communication *** grid security,distinct from traditional internet security,mainly relies on monitoring network security events at the platform layer,lacking an effective assessment mechanism for ***,we incorporate considerations for both cyber-attacks and physical faults,presenting security assessment indicators and methods specifically tailored for ***,we outline the security monitoring technology for IEDs,considering the necessary data sources for their security ***,we classify IEDs and establish a comprehensive security monitoring index system,incorporating factors such as running states,network traffic,and abnormal *** index system contains 18 indicators in 3 ***,we elucidate quantitative methods for various indicators and propose a hybrid security assessment method known as GRCW-hybrid,combining grey relational analysis(GRA),analytic hierarchy process(AHP),and entropy weight method(EWM).According to the proposed assessment method,the security risk level of IEDs can be graded into 6 levels,namely 0,1,2,3,4,and *** higher the level,the greater the security ***,we assess and simulate 15 scenarios in 3 categories,which are based on monitoring indicators and real-world situations encountered by *** results show that calculated security risk level based on the proposed assessment method are consistent with actual ***,the reasonableness and effectiveness of the proposed index system and assessment method are validated.

关键词： Smart grid intelligent electronic device security assessment abnormal behaviors network traffic running states

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：