检索结果-内蒙古大学图书馆

IEEE Workshop on Evolving and Adaptive Intelligent Systems (EAIS)

作者： Henrique O. Caetano Matheus de S. S. Fogliatto N. Luiz Desuó Benvindo R. Pereira J Carlos D. Maciel Marco Aiello Dept. of Electrical and Computer Engineering São Carlos School of Engineering University of São Paulo Department of Service Computing Institute for Architecture of Application Systems University of Stuttgart

ISBN: (数字)9798350366235

ISBN: (纸本)9798350366242

Within the paradigm of Evolving and Adaptive Intelligent Systems, the Electrical Power System (EPS) represents a Critical Infrastructure demanding robust reliability metrics. This study pioneers the application of Variable Neighborhood Search (VNS) heuristic to the Optimal Switch Allocation (OSA) problem in the EPS. Adapting neighborhood structures and local search methods, we consider the joint allocation of Manual Switches and Remote-Controlled switches, addressing interdependencies. Results highlight VNS efficacy in navigating OSA challenges, showcasing its adaptability in an evolving system. Comparative analyses endorse VNS as a valuable tool for addressing EPS reliability within the dynamic landscape of evolving and adaptive intelligent systems.

关键词： Adaptive systems Uncertainty Switches Search problems Robustness Power grids Critical infrastructure

来源：评论

学校读者我要写书评

暂无评论

Quantifying uncertainty in Bayesian Networks structural learning

Quantifying uncertainty in Bayesian Networks structural lear...

引用

IEEE Workshop on Evolving and Adaptive Intelligent Systems (EAIS)

作者： Vitor O. Barth Henrique O. Caetano Carlos D. Maciel Marco Aiello Dept. of Electrical and Computer Engineering São Carlos School of Engineering University of São Paulo Department of Service Computing Institute for Architecture of Application Systems University of Stuttgart

ISBN: (数字)9798350366235

ISBN: (纸本)9798350366242

The key goals in learning Bayesian networks (BNs) from data are to identify significant statistical relationships between variables and to build a Directed Acyclic Graph (DAG) that represents these relationships through Joint Probability Distributions. Most research relies on score-based or conditional test methods for model selection. However, when using real-world data, it can be challenging to identify whether the learned DAG represents the underlying relations inherent in the limited datasets, particularly when evaluating data obtained from multiple independent sources. This study presents a methodology to assess the credible interval for both the existence and direction of each edge within Bayesian networks derived from data. Furthermore, it explores the fusion of models acquired from distinct and independent datasets. This approach enables the Bayesian learning of Bayesian Networks (BNs) from data by treating the uncertainty associated with the existence and orientation of each edge as a random variable. By evaluating the probability of the orientation of each edge, it is possible to suggest the existence of a potential latent variable within the dataset. If an edge exhibits equiprobable directions and is verified to exist, it becomes a plausible hypothesis for a latent variable. The Fast Causal Algorithm, originally introduced by [1], is the foundation of this approach. Finally, by employing a maximum a posteriori estimation, the most prominent edges and their respective orientations are identified and employed to create the leading DAG. We present our findings in simulated datasets with different length sizes. By comparing the structure of the learned DAGs with existing structures and evaluating the inference capabilities of the final BN, we establish that our approach achieves results comparable to the most recent studies in the field, while offering insights into the model’s reliability and improving the use of the data.

关键词： Maximum a posteriori estimation Uncertainty Scalability Data models Probability distribution Bayes methods Random variables

来源：评论

学校读者我要写书评

暂无评论

Predicting Intention to Recommend Digital Citizen Participation using Machine Learning

Predicting Intention to Recommend Digital Citizen Participat...

引用

IEEE International Conference on System engineering and Technology

作者： Alexander A. Hernandez Mideth B. Abisado Lany L. Maceda Ramon L. Rodriguez Myron Darrel L. Montefalcon Jay Rhald C. Padilla Hersel Danna E. Sangalang College of Computing and Information Technologies National University Philippines College of Science Bicol University Albay Philippines School of Engineering Computing and Architecture National University - Dasmarińas Philippines

Digital citizen participation uses innovative technologies to enable, engage, and empower citizens to communicate with the government on different needs, concerns, and challenges. To this date, limited studies explain the intention and recommendation for digital citizen participation, particularly from the Philippines. Thus, this study aims to understand digital citizen participation through a survey that examines factors on the intention to use and recommend digital citizen participation among Filipino citizens. A conceptual model was developed based on trust, technology acceptance, and empowerment theory. The framework relationships were tested using machine learning algorithms. The results show that perceived ease of use, perceived usefulness, trust, and empowerment theory positively predicted the intention to recommend digital citizen participation. Furthermore, this study indicates that Filipinos have positive intention and are willing to recommend digital citizen participation. Finally, this work provides evidence of the explanatory power of the conceptual model through machine learning models on digital citizen participation. This work presents some important research and practical implications in digital citizen participation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Stock market prediction based on machine learning and social sentiment analysis

TechRxiv

引用

TechRxiv 2023年

作者： Ghazanfar, Mustansar Ali Anwar, Madiha Lee, Sin Wee Qazi, Nadeem Karimi, Amin Jhanjhi, N.Z. Javed, Ali School of Architecture Computing and Engineering University of East London United Kingdom Deputy Head of School of Computing Arden University United Kingdom School of Computer Science SCS Taylor’s University Malaysia Department of Software Engineering UET Taxila Pakistan

Precise stock market prediction is crucial for investors, but the volatility of the stock market is influenced by multiple factors such as public sentiments, business news, and related product volatility. While several algorithms have been proposed to predict the stock exchange index based on historical data, they are not ideal as external factors play a critical role in market volatility. To address this issue, we proposed a machine learning model that incorporates historical data with external factors such as social media sentiments, oil and gold trends, and financial news data to enhance prediction accuracy. Our study used HPQ, IBM, ORCL, and MSFT stock market datasets to validate the effectiveness of the proposed model, including an analysis of the impact of Covid19 on companies. Our experimental results showed the highest accuracy of 87.2% using oil and sentiment datasets. Additionally, we identified that social media significantly affects IBM stocks, and the GBM (Gradient Boosting Classifier) classifier produced consistent results. © 2023, CC BY.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Predictive Classification of Covid-19: Assessing the Impact of Digital Technologies 7

Predictive Classification of Covid-19: Assessing the Impact ...

引用

7th International Conference on Electronics, Communication and Aerospace Technology, ICECA 2023

作者： Kumar, Bonda Kiran Majumdar, Anurima Ismail, Saidatul Akmar Dixit, Rohit R Wahab, Hairani Ahsan, Md Hafizi KL School of Architecture KL Deemed to Be University Koneru Lakshmaiah Educational Foundation Andhra Pradesh Vaddeswaram India Guru Nanak Institute of Technology Department of Electronics and Communication Engineering India School of Information Science College of Computing Informatics & Mathematics Universiti Teknologi MARA Shah Alam Malaysia Siemens Healthineers India School of Information Science College of Computing Informatics and Mathematics Universiti Teknologi MARA Malaysia Universiti Malaysia Sabah Labuan Faculty of International Finance Malaysia

ISBN: (纸本)9798350340600

The recent severe outbreak of the disease has been linked to the COVID-19 virus. It is essential for healthcare professionals and individuals with the capacity to provide intensive care to offer clear explanations of this situation. To address this issue, the World Health Organization (WHO) has implemented several measures. The National Emergency Telecritical Care Network (NETCCN) has the capability to assess these actions using digital technologies. This section provides a comprehensive explanation of these developments, and NETCCN has put forth a recommendation. Version 2.0 of this digital health data will be made available;it will significantly enhance potential crises in the future. Artificial Intelligence (AI) is used in the suggested digital prediction approach to gather past data on the infection. Telemetry, sophisticated maintenance robotics, and monitoring intelligence may all be found with this technology. These may be created to incorporate data relevant to various infections. Health experts will coordinate all of these. To maintain sustained preparedness for emergency catastrophe protection, frequent testing should be conducted. © 2023 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Statistical Analysis of Digital Financial Technology Adoption Research

Statistical Analysis of Digital Financial Technology Adoptio...

引用

2024 International Conference on Science, engineering and Business for Driving Sustainable Development Goals, SEB4SDG 2024

作者： Ajibade, Temiloluwa Iyanuoluwa Ayodele, Olamide Emmanuel Ajibade, Samuel-Soma M. Goles, Nanet A. Dayupay, Johnry P. Adediran, Anthonia Oluwatosin Scholar School System Department of Business Management Birmingham United Kingdom Ekiti State University Department of Banking and Finance Ekiti State Ado Ekiti Nigeria Sunway University School of Engineering and Technology Department of Computing and Information Systems Selangor Malaysia Cebu Technological University Moalboal Cebu Philippines Federal University of Uberlandia Faculty of Architecture and Urban Design Uberlandia Brazil

ISBN: (纸本)9798350358155

Digital financial technology adoption (DFTA) studies published in Scopus between 2019 and 2022 were examined in this study. After that, we assessed relevant literature, did bibliometric studies, and examined publication and citation patterns. The statistics showed 2643 citations and 176 publications. DFTA research has gained popularity when time-varying TP and TC values increased gradually. This topic's most popular sources are "articles"and "Sustainability (Switzerland)". A search of DFTA research stakeholders revealed several authors, organizations, and nations. Most famously associated with the University of Johannesburg in South Africa, David Mhlanga has produced more publications than anyone else. The National Natural Science Foundation and other Chinese donors who dominate DFTA research funding contributed to researchers' and affiliations' output. Cluster and hotspot analysis revealed two themes, "Digital financial technology adoption"and "Sustainable Banking Inclusion,"and three keywords, Digital financial technology adoption, monetary inclusion, and finance. According to the examined literature, DFTA's effects on international financial stability and GDP growth are understudied. Future research should examine DFTA's environmental impact, long-term profitability, and commercial strategies for low-income and rural communities. © 2024 IEEE.

关键词： Decentralized finance

来源：评论

学校读者我要写书评

暂无评论

Semantic Data engineering for Intelligent Educational Learning Systems through Process Mining

Semantic Data Engineering for Intelligent Educational Learni...

引用

2023 Future of Educational Innovation-Workshop Series Data in Action, FEIWS 2023

作者： Okoye, Kingsley Islam, Syed Naeem, Usman Hosseini, Samira Institute for Future of Education College of Arts Technologies and Innovation Tecnologico de Monterrey Writing Lab University of East London Monterrey Mexico London United Kingdom College of Arts Technologies and Innovation University of East London School of Architecture Computing and Engineering London United Kingdom

ISBN: (纸本)9781665494168

Today, the growing technological turnaround from ''big data'' to ''big analytics'' has made it essential for process scientists and analysts to leverage more powerful techniques in analyzing and understanding the different types of data and formats, otherwise allied to the notion of''semantic data engineering Technological advancement has provided data mining solutions capable of processing the data/information in formats that are conceptually comprehended by humans and computers in real-Time or realworld settings, and facilitating building of systems and applications that inclusively manage the information or data they contain (machine-understandable systems). For this purpose, this study introduced a ''semantic-based process mining'' technique capable of discovering abstract or useful information or models from event logs of a learning process (educational domain), and then subsequently used to predict users' patterns through the semantically-inclined modeling and exploration of the discovered process models. Technically, the study focused on improving the results/outcomes of the learning process and mining using the set of proposed algorithms and model that incorporates semantic annotation (labeling), semantic representations (ontology), and semantic reasoning (inference modules or reasoner) of the discovered models. In turn, the outcome of the method shows that data processing and models analyses provided by traditional process mining techniques in education can be enhanced by adding ''semantic information'' (properties description) to the discovered models or events about the processes and domain. © 2023 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Climate change and wind energy potential in South America

引用

Science of the Total Environment 2024年 957卷 177675页

作者： Martinez, A. Iglesias, G. School of Engineering & Architecture & MaREI Environmental Research Institute University College Cork College Road Cork Ireland University of Plymouth School of Engineering Computing & Mathematics Marine Building Drake Circus PlymouthPL4 8AA United Kingdom

Wind energy is crucial in mitigating greenhouse gas emissions and combating global warming. However, the economic viability of wind energy projects is tied to wind resources, which may be affected by climate change. The objective of this work is to investigate the evolution of wind energy resources in South America using the most up-to-date climate-change scenarios: the Shared Socioeconomic Pathways. Three scenarios are considered, corresponding to low, medium and high emissions pathways. A multi-model ensemble is constructed with Global Climate Models selected for their accuracy in the study region in a historical period. Results indicate that east of the Andes, in Brazil, Paraguay and Venezuela, substantial increases in average wind power density are expected, surpassing 100 % in certain areas and in the most pessimistic scenario (the fossil-fuelled development pathway). By contrast, significant reductions (up to ~50 %) are projected for certain areas west of the Andes: South Chile, Peru and the waters off West Colombia. South Chile has the windiest climate in the continent, which makes this reduction due to climate change all the more important. Even under the low-emissions scenario, the projected evolution in wind resources is relevant, which highlights the necessity of considering climate change in wind energy planning. © 2024 The Authors

关键词： Renewable energy Sustainability Wind energy Wind power SSP Climate change

来源：评论

学校读者我要写书评

暂无评论

Makespan and Security-Aware Workflow Scheduling for Cloud Service Cost Minimization Using Firefly Optimizer 22nd

Makespan and Security-Aware Workflow Scheduling for Cloud ...

引用

22nd International Conference on Algorithms and architectures for Parallel Processing, ICA3PP 2022

作者： Zhou, Chengliang Wang, Tian Li, Liying Sun, Jin Zhou, Junlong School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China National Trusted Embedded Software Engineering Technology Research Center East China Normal University Shanghai200062 China

ISBN: (纸本)9783031226762

As efficient commercial information technology, cloud computing has attracted more and more users to submit their requests to the cloud platform and pay for them based on the amount and quality of services. One of the most important concerns of cloud service providers is to minimize the monetary cost for completing users’ requests while meeting constraints on the quality of services such as makespan and security. To solve this concern, this paper proposes a makespan and security-aware workflow scheduling method based on an improved firefly optimizer that consists of a new solution initialization scheme, a firefly position updating scheme, a firefly-to-solution mapping operator, and two task-to-virtual machine assignment schemes. We carry out extensive simulation experiments on real-world workflows to validate our proposed workflow scheduling method. The results reveal that the monetary cost reduction achieved by our method can be up to 54.0% compared to a baseline and two state-of-the-art approaches. © 2023, Springer Nature Switzerland AG.

关键词： Cloud computing

来源：评论

学校读者我要写书评

暂无评论

Rail Transit Event Extraction based on the Fusion of Semantic and Local Dependency Features

Rail Transit Event Extraction based on the Fusion of Semanti...

引用

IEEE International Conference on Big Knowledge (ICBK)

作者： Qiang Chen Haining Meng Yihao Bao Mingsong Yang Xinyu Tong Qin Zhao Muhammad Bilal Khan Xinhong Hei School of Computer Science and Engineering Xi’an University of Technology Xi’an China School of Computer Science and Engineering Shaanxi Key Laboratory of Network Computing and Security Technology Xi’an University of Technology Xi’an China School of Civil Engineering and Architecture Xi’an University of Technology Xi’an China

ISBN: (数字)9798331508821

ISBN: (纸本)9798331508838

Event extraction in rail transit plays a vital role in all stages of design, construction, and final acceptance. Event extraction is a key part of building event logic graph (ELG). However, the difficulty in obtaining semantic features and event local dependencies poses a challenge to accurate event extraction, which hinders the informatization and intelligent development of rail transit projects. To address these challenges, we proposes an event extraction method that fuses semantic and local dependency features. The study initially preprocesses the rail transit design codes dataset and performs sequence labeling. Then, the event trigger words are mined by combining the term frequency-inverse document frequency (TF-IDF) and minimum edit distance (MED) algorithms. Based on the semantic similarity measurement method and the trigger word mining results, the features representation of event semantic information is enhanced by using the Bidirectional Encoder Representations from Transformers (BERT) model and Bi-directional Long Short-Term Memory (BiLSTM) model. At the same time, event arguments are mined and a local dependency graph is generated based on their mining results, and then the enhanced local dependency features are obtained by using the graph convolutional network (GCN). Finally, the event semantic features and local dependency features are fused, and the conditional random field (CRF) is used to predict the labels to obtain the event extraction results. Through the comparison with five baseline methods on the datasets of rail transit design codes, it is found that the Precision, Recall, and F1 score of the proposed method are improved, with an average improvement of 9.604% on Precision, 9.342% on Recall, and 9.730% on F1 score, respectively. The contribution of the sub-modules to the overall performance is further evaluated through ablation experiments, which confirms the effectiveness and feasibility of the proposed method.

关键词： Rails Codes Semantics Bidirectional control Knowledge graphs Feature extraction Transformers Conditional random fields Logic Labeling

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：