检索结果-内蒙古大学图书馆

IEEE General Meeting Power& Energy Society

作者： K. Nosrati A. Tepljakov E. Petlenkov V. Skiparev J. Belikov Y. Levron Department of Computer Systems Tallinn University of Technology Tallinn Estonia Department of Software Science Tallinn University of Technology Tallinn Estonia Faculty of Electrical & Computer Engineering Technion—Israel Institute of Technology Haifa Israel

Variable output power in isolated microgrids (MGs) threatens frequency stability and may even degrade power quality. In response, intelligent control methods have been developed and applied to frequency deviation control systems with excellent results. Nevertheless, a potential problem is that the application of such advanced techniques with a large search space is not enough to deal with highly dynamic environment and real-time operations of MGs. In this light, the present study introduces a flexible artificial neural network (ANN)-based frequency deviation control solution in a constrained structure that operates as follows. First, the stable controller parameter space of the PID-based AC microgrid is derived by using the stability boundary locus method. Then, the controller parameters are tuned and updated online by searching for an optimal combination of the coefficients with consideration of output variations sensed by a constrained ANN in the derived reduced parameter space. To accomplish this step, a reinforcement learning technique is applied to train the ANN-based tuners. The performance of the proposed technique has been verified under a given scenario to demonstrate how the reduced parameter space should facilitate the optimization procedure.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Service Function Chaining in LEO Satellite Networks via Multi-Agent Reinforcement Learning

Service Function Chaining in LEO Satellite Networks via Mult...

引用

IEEE Conference on Global Communications (GLOBECOM)

作者： Khai Doan Marios Avgeris Aris Leivadeas Ioannis Lambadaris Wonjae Shin Department of Systems and Computer Engineering Carleton University Ottawa ON Canada Department of Software and IT Engineering École de Technologie Supérieure Montreal QC Canada Korea University School of Electrical Engineering Seoul South Korea

Low-earth-orbit satellite networks (LSNs) offer an enhanced global connectivity and a wide range of applications such as disaster response and military operations, among others. Each specific application can be represented by a service function chain (SFC) in which each function is considered as a task in the application. Our objective is to optimize the long-term system performance by minimizing the average end-to-end delay of SFC deployments in LSNs. To achieve this, we formulate a dynamic programming (DP) problem to derive an optimal placement policy. To overcome the computational intractability, the need for statistical knowledge of SFC requests, and centralized decision-making challenges, we present a multi-agent Q-learning approach where satellites act as independent agents. To facilitate performance convergence in non-stationary agents' environments, we let agents to collaborate by sharing designated learning parameters. In addition, agents update their Q-tables via two distinct rules depending on selected actions. Extensive experimentation shows that our approach achieves convergence and performance relatively close to the optimum obtained by solving the formulated DP equation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Examining the Use of Non-fungible Tokens (NFTs) as a Trading Mechanism for the Metaverse 1

引用

29th European systems, software and Services Process Improvement, EuroSPI 2022

作者： Yilmaz, Murat Hacaloğlu, Tuna Clarke, Paul Department of Computer Engineering Engineering Faculty Gazi University Ankara Turkey Metaverse Research and Development Laboratory Gazi University Ankara Turkey Department of Information Systems Engineering Atilim University Ankara Turkey School of Computing Dublin City University Dublin Ireland Lero the Science Foundation Ireland Research Centre for Software Limerick Ireland

ISBN: (数字)9783031155598

ISBN: (纸本)9783031155581

The notion of a metaverse seems hard to define but encourages the impression that it can be considered as a new virtual metaphysical landscape that somehow goes beyond our geographical locations and understanding (i.e., independent of time and space). Based on virtual reality, augmented reality, and blockchain, it is envisioned as an independent but extended world that is planned to be a digital virtuality entrenched not only in our old habits such as gaming and entertainment but also in virtual asset trade. In particular, trading is a pillar of the virtual economy, and auction houses will be crucial for Metaverse trading. This exploratory study examines the possibility of using an auction environment to improve the trading capabilities in a virtual universe. We investigate the cases of creating a virtual auction house with the potential of social trading of virtual assets with crypto coins and bartering. To this end, we built a virtual auction house and tested it initially using a set of scenarios. Our preliminary findings suggest that creating a virtual trading environment would be beneficial as an environment for buying and selling virtual assets and exploring their consequences. © 2022, Springer Nature Switzerland AG.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Application of Data Science and Machine Learning in the Prediction of College Dropout: A Data-Driven Predictive Approach

Application of Data Science and Machine Learning in the Pred...

引用

International Conference on software Process Improvement (CIMPS)

作者： Axel Frederick Félix Jiménez Vania Stephany Sanchéz Lee Isaul Ibarra Belmonte Ezra Federico Parra González Engineering in Computer Systems National Polytechnic Institute Zacatecas México Software Engineer Center for Research in Mathematics Zacatecas México Computer Science Department Center for Research in Mathematics Zacatecas México

ISBN: (数字)9798350358568

ISBN: (纸本)9798350358575

This paper presents a study on the prediction of student graduation or failure using two predictive models: K-Nearest Neighbors (KNN) and a forward sequential Artificial Neural Network (ANN). The models, built with a well-chosen set of independent variables, were assessed using metrics like precision and accuracy. The results obtained revealed that both the KNN model and the sequential forward ANN model achieved high efficiency in predicting student graduation or failure, achieving accuracies of 0.9133% (K=3) and 0.9312% (after 50 epochs), respectively. Providing a valuable tool to identify early on students at risk of not graduating and to take preventive measures to improve their academic performance. Comparisons with related research showed consistent outcomes, underscoring the credibility and importance of the employed predictive models.

关键词： Measurement Artificial neural networks Machine learning Predictive models Data science software

来源：评论

学校读者我要写书评

暂无评论

ProSy: API-Based Synthesis with Probabilistic Model

引用

Journal of computer Science & Technology 2020年第6期35卷 1234-1257页

作者： Bin-Bin Liu Wei Dong Jia-Xin Liu Ya-Ting Zhang Dai-Yan Wang College of Computer Science National University of Defense TechnologyChangsha 410072China Key Laboratory of Software Engineering for Complex Systems College of Computer ScienceNational University of Defense TechnologyChangsha 410072China

Program synthesis is an exciting topic that desires to generate programs satisfying user intent automatically. But in most cases, only small programs for simple or domain-specific tasks can be synthesized. The major obstacle of synthesis lies in the huge search space. A common practice in addressing this problem is using a domain-specific language, while many approaches still wish to synthesize programs in general programming languages. With the rapid growth of reusable libraries, component-based synthesis provides a promising way, such as synthesizing Java programs which are only composed of APIs (application programming interfaces). However, the efficiency of searching for proper solutions for complex tasks is still a challenge. Given an unfamiliar programming task, programmers would search for API usage knowledge from various coding resources to reduce the search space. Considering this, we propose a novel approach named ProSy to synthesize API-based programs in Java. The key novelty is to retrieve related knowledge from Javadoc and Stack Overflow and then construct a probabilistic reachability graph. It assigns higher probabilities to APIs that are more likely to be used in implementing the given task. In the synthesis process, the program sketch with a higher probability will be considered first;thus, the number of explored reachable paths would be decreased. Some extension and optimization strategies are further studied in the paper. We implement our approach and conduct several experiments on it. We compare ProSy with SyPet and other state-of-the-art API-based synthesis approaches. The experimental results show that ProSy reduces the synthesis time of SyPet by up to 80%.

关键词： application programming interface(API)-based program Petri net probabilistic reachability graph program synthesis

来源：评论

学校读者我要写书评

暂无评论

Depth-Aware Multi-Modal Fusion for Generalized Zero-Shot Learning 22

Depth-Aware Multi-Modal Fusion for Generalized Zero-Shot Lea...

引用

22nd IEEE International Conference on Industrial Informatics, INDIN 2024

作者： Cao, Weipeng Yao, Xuyang Xu, Zhiwu Pan, Yinghui Sun, Yixuan Li, Dachuan Qiu, Bohua Wei, Muheng Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China College of Computer Science and Software Engineering Shenzhen University Shenzhen China Stony Brook University New York United States Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China ZhenDui Industry Artificial Intelligence Co. Ltd Shenzhen China Department of Automation Shanghai Jiao Tong University Shanghai China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China

ISBN: (纸本)9798331527471

Realizing Generalized Zero-Shot Learning (GZSL) based on large models is emerging as a prevailing trend. However, most existing methods merely regard large models as black boxes, solely leveraging the features output by the final layer while disregarding potential performance enhancements from other layers. Indeed, numerous researchers have visually depicted variations in the features learned across different layers of neural networks. Motivated by this observation, we propose a Vision Transformer (ViT)-based GZSL method named Depth-Aware Multi-Modal ViT (DAM2ViT), which exploits multi-level features of ViT. DAM2ViT incorporates a multi-modal interaction block to align semantic information of categories across multiple layers, thereby augmenting the model’s capacity to learn associations between visual and semantic spaces. Extensive experiments conducted on three benchmark datasets (i.e., CUB, SUN, AWA2) have showcased that DAM2ViT achieves competitive results compared to state-of-the-art methods. © 2024 IEEE.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Accident detection and road monitoring in real time using deep learning and lane detection algorithms 21

Accident detection and road monitoring in real time using de...

引用

4th International Conference on Machine Learning and Machine Intelligence, MLMI 2021

作者： Ayman Mounir, Shehab Eldeen Hussein, Walid H. Karam, Omar Software Engineering Faculty of Informatics and Computer Science The British University in Egypt Egypt Computer Science Faculty of Informatics and Computer Science The British University in Egypt Egypt Information Systems Faculty of Informatics and Computer Science The British University in Egypt Egypt

ISBN: (纸本)9781450384247

Automating the monitoring of the roads would mean safer roads for both car drivers and pedestrians. The objectives of the system were to build a real time surveillance system for intelligent roads of the future. The system should be able to detect lane lines, cars, pedestrians and other moving vehicles on the road. In case a car goes off its course, the system should report it as an accident. Relying on machine learning technology, a real time detection based neural network was constructed to be trained on picking up objects in any given scene like cars, buses, pedestrians, bikes and motor bikes. Also, an algorithm was designed to detect lane lines and highlight them on the screen using image processing techniques and edge detection. The system achieved its main required target which is being able to detect objects in almost real time. © 2021 ACM.

关键词： Accidents

来源：评论

学校读者我要写书评

暂无评论

Simulating the Social Influence in Transport Mode Choices 23

Simulating the Social Influence in Transport Mode Choices

引用

Proceedings of the Winter Simulation Conference

作者： Kathleen Salazar-Serna Lynnette Hui Xian Ng Kathleen Carley Lorena Cadavid Carlos Jaime Franco Department of Civil and Industrial Engineering Pontificia Universidad Javeriana Colombia Software and Societal Systems Carnegie Mellon University Pittsburgh USA Department of Computer and Decision Sciences Universidad Nacional de Colombia Medellin Colombia

ISBN: (纸本)9798350369663

Agent-based simulations have been used in modeling transportation systems for traffic management and passenger flows. In this work, we hope to shed light on the complex factors that influence transportation mode decisions within developing countries, using Colombia as a case study. We model an ecosystem of human agents that decide at each time step on the mode of transportation they would take to work. Their decision is based on a combination of their personal satisfaction with the journey they had just taken, which is evaluated across a personal vector of needs, the information they crowdsource from their prevailing social network, and their personal uncertainty about the experience of trying a new transport solution. We simulate different network structures to analyze the social influence for different decision-makers. We find that in low/medium connected groups inquisitive people actively change modes cyclically over the years while imitators cluster rapidly and change less frequently.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CCT5: A Code-Change-Oriented Pre-Trained Model

arXiv

引用

arXiv 2023年

作者： Lin, Bo Liu, Yepang Wang, Shangwen Xia, Xin Liu, Zhongxin Mao, Xiaoguang College of Computer Science National University of Defense Technology Changsha China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China Zhejiang University Hangzhou China Key Laboratory of Software Engineering for Complex Systems China Research Institute of Trustworthy Autonoumous Systems United Kingdom

software is constantly changing, requiring developers to perform several derived tasks in a timely manner, such as writing a description for the intention of the code change, or identifying the defect-prone code changes. Considering that the cost of dealing with these tasks can account for a large proportion (typically around 70 percent) of the total development expenditure, automating such processes will significantly lighten the burdens of developers. To achieve such a target, existing approaches mainly rely on training deep learning models from scratch or fine-tuning existing pre-trained models on such tasks, both of which have weaknesses. Specifically, the former uses comparatively small-scale labelled data for training, making it difficult to learn and exploit the domain knowledge of programming language hidden in the large-amount unlabelled code in the wild;the latter is hard to fully leverage the learned knowledge of the pre-trained model, as existing pre-trained models are designed to encode a single code snippet rather than a code change (i.e., the difference between two code snippets). We propose to pre-train a model specially designed for code changes to better support developers in software maintenance. To this end, we first collect a large-scale dataset containing 1.5M+ pairwise data of code changes and commit messages. Based on these data, we curate five different tasks for pre-training, which equip the model with diverse domain knowledge about code changes. We fine-tune the pre-trained model, CCT5, on three widely-studied tasks incurred by code changes and two tasks specific to the code review process. Results show that CCT5 outperforms both conventional deep learning approaches and existing pre-trained models on these tasks. Copyright © 2023, The Authors. All rights reserved.

关键词： Domain Knowledge

来源：评论

学校读者我要写书评

暂无评论

Development of Day-Ahead Peer-to-Peer Energy Trading with Time-Series Clustering

Development of Day-Ahead Peer-to-Peer Energy Trading with Ti...

引用

International Conference on Applied Superconductivity and Electromagnetic Devices, ASEMD

作者： Nadya Noorfatima Jaesung Jung Ahmet Onen Yeliz Yoldas Department of Energy Systems Research Ajou University Suwon South Korea Department of Electrical and Computer Engineering Sultan Qaboos University Muscat Oman Department of Software Engineering Kayseri University Kayseri Turkey

Day-ahead trading of electricity has been applied to ensure the balance between the amount of electricity sold and bought. Even so, due to the intermittent distributed energy resources (DERs), the actual condition can be varied significantly, and forecasting can be costly in order to provide high accuracy to minimize losses. Hence, this paper proposes a novel model-based day-ahead peer-to-peer (P2P) energy trading with regionalized trading prices, which are determined through time-series clustering. To improve the determination of price regions, the data parameter is derived from the day-ahead condition, which is forecasted from network condition, trading capacity, and trading price of the P2P energy trading. The performance of the proposed model of day-ahead P2P energy trading is evaluated with respect to the market operation stability and optimality.

关键词：

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：