检索结果-内蒙古大学图书馆

2023 IEEE International Conference on Big Data, BigData 2023

作者： Kim, Jeongseon Kim, Sungsoo Lim, Sungsu Chungnam National University Dept. of Computer Science & Engineering Daejeon Korea Republic of Smart Data Research Section Etri Daejeon Korea Republic of

ISBN: (纸本)9798350324457

We present five approaches for interpolating missing data in real-world traffic datasets using basic, statistical, and generative model methods. The effectiveness of these approaches is evaluated using graph deep learning models, and the results show that imputing missing data improves the performance of traffic prediction models, especially when dealing with a higher proportion of missing data. The experiments are conducted on two real-world datasets, METR-LA and PEMS-BAY, to evaluate the proposed methods comprehensively. The results demonstrate that imputing missing data significantly enhances the performance of traffic prediction models, particularly when dealing with a higher proportion of missing data. © 2023 IEEE.

关键词： Deep Learning on Graphs Missing Data Imputation Spatio-Temporal Time-Series

来源：评论

学校读者我要写书评

暂无评论

Improved Dynamic Coupled Graph Convolutional Recurrent Networks for Traffic Forecasting

Improved Dynamic Coupled Graph Convolutional Recurrent Netwo...

引用

2023 IEEE International Conference on Big Data, BigData 2023

作者： Han, Seunghoon Kim, Sungsoo Lim, Sungsu Chungnam National University Dept. of Computer Science & Engineering Daejeon Korea Republic of ETRI Smart Data Research Section Daejeon Korea Republic of

ISBN: (纸本)9798350324457

Traffic forecasting is a crucial application of the Intelligent Transportation System (ITS), with research focusing on various methods, from classical statistical approaches to graph-based methods integrated with RNN-based approaches to capture spatial and temporal correlations simultaneously. During the traffic data collection phase, the absence of vehicles on each road or sensor malfunctions can result in the collection of traffic time series data as zeros. However, storing such zero values makes accurate traffic prediction more challenging. To address this challenge, we present a novel model for improving traffic forecasting using graph convolutional recurrent neural networks. The proposed method is evaluated on two real-world public benchmark datasets and compared with six baseline models, showcasing its superior performance. © 2023 IEEE.

关键词： Graph Neural Networks Spatio-Temporal Time-Series Traffic Forecasting

来源：评论

学校读者我要写书评

暂无评论

UML and NFR-framework based method for the analysis of the requirements of an information system

引用

International Journal of Information Technology (Singapore) 2023年第1期15卷 411-422页

作者： Arif, Mohd. Mohammad, Chaudhary Wali Sadiq, Mohd. Computer Science and Technology Research Group Department of Applied Sciences and Humanities Faculty of Engineering and Technology Jamia Millia Islamia A Central University New Delhi 110025 India Software Engineering Lab Computer Engineering Section UPFET Jamia Millia Islamia A Central University New Delhi 110025 India

Software requirements are the expectation of stakeholders which are identified and modeled by various requirements elicitation and modeling techniques like traditional methods, goal oriented methods, and unified modeling language (UML), etc. The identified software requirements are broadly classified into functional requirements (FRs) and non-functional requirements (NFRs). Based on our literature review, we found that most of the focus in the area of software engineering is on the analysis of FRs as compared to NFRs. For the successful development of any information system both FRs and NFRs should be considered equally during the elicitation and modeling process;and ignoring NFRs may lead to failure of software. Therefore, to address this issue, we developed a method for the analysis of both FRs and NFRs so that a successful software product can be developed by a software company. In the proposed method, FRs are modeled by UML use-case diagram, class-diagram, and activity diagram. The NFRs are analyzed using NFR-framework;and NFR propagation rules have been derived from the requirements of an information system. In this framework, fuzzy based approach has been used to analyze the contribution links of softgoal interdependency graph. The applicability of the proposed method is discussed by using FRs and NFRs of library information system. © 2022, The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of computer Applications and Management.

关键词： Functional requirements Library information system Non-functional requirements Software requirements UML

来源：评论

学校读者我要写书评

暂无评论

Adaptive Droop Control in VSC-Based MT-MVDC Distribution Systems Considering ESS Participation

引用

IEEE Transactions on Energy Conversion 2024年第2期40卷 761-772页

作者： Sun, Pingyang Pinthurat, Watcharakorn Li, Gen Khalid, Muhammad Town, Graham Konstantinou, Georgios UNSW Sydney School of Electrical Engineering and Telecommunications NSW2052 Australia Rajamangala University of Technology Tawan-Ok Department of Electrical Engineering Chanthaburi Thailand Energy Technology and Computer Science Section Department of Engineering Technology Ballerup2750 Denmark King Fahd University of Petroleum and Minerals Electrical Engineering Department Interdisciplinary Research Center for Sustainable Energy Systems Dhahran31261 Saudi Arabia Macquarie University School of Engineering NSW2019 Australia

This paper proposes a novel adaptive droop (ADC) control for voltage source converter (VSC)-based multiterminal medium-voltage direct current (MT-MVDC) distribution systems with heterogeneous energy storage system (ESS) participation. The proposed ADC scheme can achieve MVDC bus voltage management and power sharing between VSCs with overloading operation, solving the issue that all VSCs on the rectifier/inverter side reach their power limits concurrently after a large system disturbance. This is accomplished by factoring in the real-time power/voltage values at VSC stations along with an extended power component. This component is contingent on the actual operational state of the ESSs and inversely correlated with the power delivered/absorbed by the ESSs. Moreover, the controllers of the battery and ultracapacitor systems incorporate two additional control loops, a novel VSC excess power reduction (VEPR) loop as well as inner expanded excess power reduction (EEPR) loop, to obtain the power reference values. The two loops ensure all VSCs operate within individual power limits after the engagement of the ESS. The effectiveness of proposed ADC strategy is confirmed through real-time simulations in a hybrid AC/MT-MVDC system. © 1986-2012 IEEE.

关键词： Charge storage

来源：评论

学校读者我要写书评

暂无评论

Autonomous Deployment of a Robust computer Vision Framework for Real-Time Car Counting on Paraguayan Highways 10

Autonomous Deployment of a Robust Computer Vision Framework ...

引用

10th International Conference on Applied System Innovation, ICASI 2024

作者： Frachi, Maximiliano Pfannl Ruan, Shanq-Jang Chen, Chih-Lun Department of Information Engineering Taiwan-Paraguay Polytechnic University Department of Electronic and Computer Engineering National Taiwan University of Science and Technology No. 43 Section 4 Keelung Rd Da an District Taipei City 106 Taipei Taiwan

ISBN: (纸本)9798350394924

Our research utilizes a custom YOLOv8 model trained with transfer learning on a representative augmented dataset tailored to accurately represent Paraguay's traffic situations. We employ multiple Gaussian Mixture Models (GMMs) for foreground object detection, incorporating motion and spatial cues. Innovative shadow removal techniques ensure robust mask extraction from highway video frames. Finally, virtual lines help determine the direction and number of cars crossing. © 2024 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

A Fully Connected Neural Network For Polar Channel Decoding 20

A Fully Connected Neural Network For Polar Channel Decoding

引用

20th International Conference on Electrical engineering, Computing science and Automatic Control, CCE 2023

作者： Sánchez-Rodríguez, Jesús Ángel Martinez-Enriquez, Ana M. Lara, Mauricio CINVESTAV-IPN Communications Section Dept. Electrical Engineering Mexico City Mexico CINVESTAV-IPN Dept. Computer Science Mexico City Mexico

ISBN: (纸本)9798350306767

One of the most essential components of a communications system is channel coding, which provides protection for the original source message. Polar codes have gained great importance due to the fact that they reach the channel capacity for the Binary Discrete Memoryless Channel. Both encoding and decoding, for this type of codes, are serial processes, which increases latency. In this research, we propose a fully connected neural network architecture that tackles this problem in decoding thanks to the inherent parallelization of this type of structure. Our experimental results demonstrate that a fully connected neural network reduces decoding delay, although further study is still needed to reach the accuracy of the probabilistic decoding methods. © 2023 IEEE.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Intelligent Caching Strategies for 5G Edge Networks using Machine Learning 4

Intelligent Caching Strategies for 5G Edge Networks using Ma...

引用

4th International Conference on Smart Electronics and Communication, ICOSEC 2023

作者： Guduri, Naga Venkata Ramakrishna Sethu, S. Shalinirajan, R. Reena, R. Karthikeyan, M. Uthayakumar, G.S. University of Technology and Applied Sciences-Al Musannah Electrical and Electronics Section Engineering Department Oman Department of Computer Science and Engineering Tamilnadu Chennai India Panimalar Engineering College Department of Computer Science and Business System Tamilnadu Chennai India Prince Shri Venkateshwara Padmavathy Engineering College Department of Computer Science and Engineering Tamilnadu Chennai India Tamilnadu Chennai India St. Joseph's Institute of Technology Department of Electronics and Communication Engineering Tamilnadu Chennai India

ISBN: (纸本)9798350300888

To reduce latency and improve the user experience, content caching solutions at the network periphery will become increasingly important as 5G networks and data-intensive applications. In this proposed work, the deployment of a caching architecture for 5G periphery networks using machine learning is done. Utilizing information on user behavior, network conditions, and content prominence enables more accurate forecasts and cache management decisions. This trains the prediction models using a wide range of machine-learning techniques to accommodate the ever-changing needs of both networks and content. To evaluate the efficiency of the proposed architecture by measuring its ability to increase cache hit rates and decrease latency. These techniques significantly outperform the standard caching methods. With the intelligent caching architecture of 5G periphery networks, throughput is increased, latency is reduced, and congestion is alleviated. The findings of this study contribute to the growing corpus of literature on AI-driven optimization in 5G networks and shed light on how such solutions could be enhanced for future networks. Neural Networks achieved 96% accuracy than SVM which is 93%. © 2023 IEEE.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

A Mathematical Model for the Selection of Software Requirements Elicitation Techniques 6th

A Mathematical Model for the Selection of Software Requireme...

引用

6th International Conference on Information Systems and Management science, ISMS 2023

作者： Saxena, Virat Raj Yadav, Rajeev Parveen, Azra Sadiq, Mohd. Department of Computer Science and Engineering Mangalayatan University Uttar Pradesh Aligarh202001 India Indraprastha Research Laboratory Indraprastha Institute of Information Sciences Private Limited New Delhi110025 India Software Engineering Laboratory Computer Engineering Section UPFET Jamia Millia Islamia A Central University New Delhi110025 India

ISBN: (纸本)9783031664090

Various techniques have been developed for the identification of different types of requirements like interview, questionnaire, group elicitation techniques, attributed goal-oriented requirements analysis, fuzzy based goal-oriented requirements analysis method, non-functional requirements framework, etc. Based on the critical analysis of requirements elicitation methods, we found that single elicitation technique is not suitable to understand the need of the stakeholders. In real life applications, multiple elicitation techniques are required to elicit and select the requirements of an information system because each technique has its strength and limitations. Therefore, to address this issue, this paper presents a mathematical model for the selection of requirements elicitation techniques so that complete set of requirements along with its priority can be identified before the development of an information system. The institute examination system is considered to show the applicability of the proposed mathematical model. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Software testing

来源：评论

学校读者我要写书评

暂无评论

A Mathematical Model for the Selection of Software Requirements Elicitation Techniques 14

A Mathematical Model for the Selection of Software Requireme...

引用

14th International Conference on Cloud Computing, Data science and engineering, Confluence 2024

作者： Saxena, Virat Raj Yadav, Rajeev Parveen, Azra Sadiq, Mohd. Mangalayatan University Department of Computer Science and Engineering Uttar Pradesh Aligarh202001 India Indraprastha Institute of Information Sciences Private Limited Indraprastha Research Laboratory New Delhi110025 India Upfet Jamia Millia Islamia A Central University Software Engineering Laboratory Computer Engineering Section New Delhi110025 India

ISBN: (纸本)9798350344837

关键词： Information systems

来源：评论

学校读者我要写书评

暂无评论

Through the Sci-Fi Lens: Exploring Social Media's Influence on Body Image and Bullying Among Adolescents in Boarding Schools 21

Through the Sci-Fi Lens: Exploring Social Media's Influence ...

引用

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

作者： Mustapha, Jawahir Che Ghazali, Muhammad Azmin Mohamed Abdullah, Munaisyah Sulaiman, Nor Intan Saniah Rahman, Hezlin Aryani Abd Universiti Kuala Lumpur Malaysian Institute of Information Technology Informatics & Analytics Section Kuala Lumpur Malaysia Universiti Kuala Lumpur Malaysian Institute of Information Technology Computer Engineering Tech. Section Kuala Lumpur Malaysia Universiti Kuala Lumpur Malaysian Institute of Information Technology Software Engineering Section Kuala Lumpur Malaysia Universiti Utara Malaysia College of Arts and Science School of Quantitative Sciences Kedah Malaysia Universiti Teknologi Mara Centre of Statistical and Decision Science Studies Faculty of Computer and Mathematical Sciences Selangor Malaysia

ISBN: (纸本)9798350393569

This research investigates the complex relationships between social media, body image, and bullying among adolescent boarding school students, with an emphasis on the Malaysian context. Utilizing science fiction as a conceptual lens, the study presents hypothetical future scenarios to investigate how technological advancements could impact these interconnected issues. The paper seeks to provide nuanced insights into the ethical and policy implications of social media use in boarding schools by drawing on key theories such as Social Comparison Theory, Social-Ecological Model and Uses and Gratifications Theory. Through comparative analysis of hypothetical scenarios, this study aims to provide educators, policymakers, and technologists with a comprehensive understanding of the challenges and opportunities at this intersection. The ultimate objective is to contribute to the ongoing discourse concerning adolescent mental health and to propose actionable strategies for mitigating negative outcomes in the unique context of Malaysian boarding schools. © 2024 IEEE.

关键词： Social networking (online)

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：