检索结果-内蒙古大学图书馆

Decentralized control in active distribution grids via supervised and reinforcement learning

Energy and AI 2024年第2期16卷 137-149页

作者： Stavros Karagiannopoulos Petros Aristidou Gabriela Hug Audun Botterud Laboratory for Information and Decision Systems(LIDS) Massachusetts Institute of TechnologyCambridgeUSA EEH-Power Systems Laboratory ETH Zurichhysikstrasse 38092 ZurichSwitzerland Department of Electrical Engineering Computer Engineering&InformaticsCyprus

While moving towards a low-carbon, sustainable electricity system, distribution networks are expected to host a large share of distributed generators, such as photovoltaic units and wind turbines. These inverter-based resources are intermittent, but also controllable, and are expected to amplify the role of distribution networks together with other distributed energy resources, such as storage systems and controllable loads. The available control methods for these resources are typically categorized based on the available communication network into centralized, distributed, and decentralized or local. Standard local schemes are typically inefficient, whereas centralized approaches show implementation and cost concerns. This paper focuses on optimized decentralized control of distributed generators via supervised and reinforcement learning. We present existing state-of-the-art decentralized control schemes based on supervised learning, propose a new reinforcement learning scheme based on deep deterministic policy gradient, and compare the behavior of both decentralized and centralized methods in terms of computational effort, scalability, privacy awareness, ability to consider constraints, and overall optimality. We evaluate the performance of the examined schemes on a benchmark European low voltage test system. The results show that both supervised learning and reinforcement learning schemes effectively mitigate the operational issues faced by the distribution network.

关键词： Supervised learning Reinforcement learning Deep deterministic policy gradient Decentralized control Active distribution systems

来源：评论

学校读者我要写书评

暂无评论

Origami Microfluidics: A Review of Research Progress and Biomedical Applications

引用

Biomedical Materials and Devices 2023年第1期1卷 388-401页

作者： Sun, Kaixin Fan, Yiqiang Hebda, Michael Zhang, Yajun School of Mechanical and Electrical Engineering Beijing University of Chemical Technology Beijing China Faculty of Engineering and Informatics University of Bradford Bradford United Kingdom

In recent years, origami/paper folding art has been applied to more and more scientific research due to the efficiently producing tiny structures at a low cost;inspired by this, origami microfluidics (the combination of origami/paper folding with paper-based microfluidics) has also been proposed. In origami microfluidic devices, three-dimensional fluid paths can be formed directly by folding the paper with pre-deposited hydrophobic barriers to accomplish complex fluid manipulation. Compared with the layer-by-layer approach, paper folding is more convenient and easier to fabricate three-dimensional microchannels and can meet the increasing requirements of microfluidic end users and improve the functionality of paper-based microdevices. This review is trying to introduce the most current developments of origami paper-based microfluidics, focusing on hydrophobic barrier processing, paper folding, and methods to fix the folded paper. By paper folding, the application prospects of paper-based microfluidics in the biomedical field have been expanded;thus, some biomedical applications of origami microfluidics are also briefly reviewed in this study. Finally, the challenges and perspectives of origami microfluidics were discussed in this review. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC 2022. Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s);author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

关键词： Biomedical applications Origami Paper folding Paper-based microfluidics Three-dimensional paper devices

来源：评论

学校读者我要写书评

暂无评论

An Ensemble-Based Machine Learning Approach to Identify SARS-CoV-2 Virus Infection by Analyzing S Protein Sequences 2nd

An Ensemble-Based Machine Learning Approach to Identify SARS...

引用

2nd International Conference on Big Data, IoT and Machine Learning, BIM 2023

作者： Moni, Raka Zahid Hasan, Md. Shahriar Shakil, Md. Ferdous, Most. Jannatul Arefin, Mohammad Shamsul Bhuiyan, Touhid Health Informatics Research Lab Computer Science and Engineering Daffodil International University Dhaka Bangladesh Computer Science and Engineering Chittagong University of Engineering and Technology Chittagong Bangladesh

ISBN: (纸本)9789819989362

Coronavirus disease (COVID-19), an effect of the SARS-CoV-2 virus, is an emerging infectious disease that infects humans due to interspecies transmission. Typically, Spike (S) protein plays a crucial role in entering host cells and beginning infection in contrast to the Membrane (M) and Envelope (E) proteins which are primarily involved in virus assembly. The purpose of this research is to examine the S protein sequences of the human virus to forecast SARS-CoV-2 infection potential. Using computational modeling and bioinformatics approaches, we analyzed the dataset taken from the Virus Pathogen Database except for 47 SARS2-CoV sequences from the SARS2-CoV Database containing aligned sequences of lengths 2396. This study suggests using several machine learning methods to determine infectivity based on the sequence of the coronavirus spike protein. The classical machine learning approach such as k-nearest neighbors (KNNs), Gaussian Naive Bayes (GaussianNB), support vector machine (SVM), decision tree (DT) is used. Bagging Classifier, Gradient Boosting algorithm, and Random Forest are used as the ensemble machine learning algorithm. Artificial Neural Network (ANN) is also applied as a deep learning model. The Gradient Boosting algorithm demonstrates the best accuracy in determining infectivity status. According to our research, the outcome of this study has a chance to accurately forecast coronavirus infectivity from genetic information. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Coronavirus

来源：评论

学校读者我要写书评

暂无评论

Predicting Mobility Management Demands of Cellular Networks based on User Behavior 36

Predicting Mobility Management Demands of Cellular Networks ...

引用

36th IEEE/IFIP Network Operations and Management Symposium, NOMS 2023

作者： Makai, Lajos Bence Varga, Pal Access Chapter Dt Technology Delivery International Magyar Telekom Plc. Budapest Hungary Budapest University of Technology and Economics Faculty of Electrical Engineering and Informatics Department of Telecommunications and Media Informatics Budapest Hungary

ISBN: (纸本)9781665477161

Mobile network operators continuously !aim to optimize network resources to satisfy user demands and be energy efficient. In the era of network function virtualization, predicting the demands for certain functional resources becomes a necessity. Resource optimization is usually based on modeling the user behavior and demands - which gets more challenging if the behavior and demand change dynamically. This applies to the mobile network control plane, where session and mobility management load could have certain seasonality, although the ever-changing user behavior modulates the models. As user behavior keeps varying, traditional mathematical time series analysis cannot provide sub-optimal results. This paper proposes using machine learning methods to predict certain mobility management efforts, such as handovers and tracking area updates. In the cellular network, HO (Handover) and TAU (Tracking Area Update) messages are used for user mobility management, among others. These appear in the S1AP protocol for LTE and 5G NSA (Non-Standalone Architecture). In this paper, we use real-life HO and TAU message records and aim to predict their volumetric appearance for the upcoming time window. We compare the prediction results for a baseline, a linear, a CNN (Convolutional Neural Network), and an LSTM (Long Short-Term Memory NN) model. The ultimate aim of these predictions is to estimate the expected network demands for certain network functions. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Classification of Illustrated Question for Indonesian National Assessment with Deep Learning 14

Classification of Illustrated Question for Indonesian Nation...

引用

14th International Conference on Information and Communication technology and System, ICTS 2023

作者： Rachman, Rudy Alfian, Muhammad Yuhana, Umi Laili Sepuluh Nopember Institute of Technology Faculty of Intelligent Electrical and Informatics Technology Dept. of Informatic Engineering Surabaya Indonesia

ISBN: (纸本)9798350312164

Reading literacy is a part of the Indonesian National Assessment. Each question has an illustrative image to help the reader understand the information conveyed. The dataset in this study was collected manually from official government platforms. However, in this study, we encountered a small dataset problem, so data augmentation was needed to increase the variation of the training data. This research focuses on the use of deep learning, namely the Convolutional Neural Network (CNN) to classify illustrative images into information or literature classes. We use five backbones, Visual Geometry Group 16 (VGG-16), MobileNetV2, Residual Network 50 (ResNet-50), Dense Network (DenseNet-121), and EfficientNetB4. Then we compared accuracy, F1 score, loss function to our evaluation metrics. We apply the transfer and fitting learning method to solve small data set problems. The best result in this study is using the ResNet-50 model and the fastest is using the Adam optimizer but it easily causes overfitting. © 2023 IEEE.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Secure Optical-transport-network technology in Anticipation of the Quantum Computer Era

引用

NTT Technical Review 2023年第4期21卷 60-66页

作者： Murakami, Keizo Taniguchi, Atsushi Kudo, Fumiaki Chikara, Sakae Kiyomura, Yutaro Mukaiyama, Akio Iijima, Yusuke Mochida, Yasuhiro Sanari, Yasuyuki Kimura, Naohiro Social Information Sharing Research Project NTT Social Informatics Laboratories Japan NTT Network Innovation Laboratories Japan Security Engineering Group Information Security Technology Research Project NTT Social Informatics Laboratories Japan Frontier Communication Laboratory NTT Network Innovation Laboratories Japan

In the January 2022 issue of NTT Technical Review, we introduced the secure optical transport network for enabling secure optical transport even in the era of quantum computers. In this article, two concepts, cryptographic agility and Multi-Factor Security, which are key factors in the transition from current cryptographic techniques to quantum-resistant cryptographic techniques and need to be considered in the era of quantum computers, are explained, and our efforts to incorporate these concepts into secure optical transport networks (i.e., elastic-key-control technology and disaggregation technology for cryptographic processing) are introduced. © 2023 Nippon Telegraph and Telephone Corp.. All rights reserved.

关键词： Quantum chemistry

来源：评论

学校读者我要写书评

暂无评论

Detection and Classification of Cognitive Distortions: A Literature Review

Detection and Classification of Cognitive Distortions: A Lit...

引用

2023 International Conference on Smart-Green technology in Electrical and Information Systems, ICSGTEIS 2023

作者： Putu Gede Hendra Suputra, I. Linawati, Linawati Sastra, Nyoman Putra Sukadarmika, Gede Er, Ngurah Agus Sanjaya Purwitasari, Diana Made Agus Setiawan, I. Udayana University Doctoral Engineering Departement Denpasar Indonesia Sepuluh Nopember Institute of Technology Department of Informatics Engineering Surabaya Indonesia Udayana University Department of Informatics Denpasar Indonesia University of Pittsburgh United States

ISBN: (纸本)9798350382822

Various machine learning and deep learning approaches have recently been applied to detecting and classifying cognitive distortions (CD). However, there are several challenges in detecting and classifying cognitive distortions. This paper outlines current research in CD detection and classification, challenges and problems. The first challenge lies in the limited availability and accessibility of public datasets. Another issue relates to CD domains, which involve short text data that may only partially represent a particular CD category. The performance of CD detection model has a relatively good value, while in general, the classification process has not shown promising results. One model that works well and consistently is BERT, both in terms of vector representation and as a classifier. In addition to the model, dataset availability and reliability remains an important issues to address. © 2023 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

An efficient framework for evaluating the usability of academic websites: Calibration, validation, analysis, and methods

引用

Neutrosophic Sets and Systems 2023年 53卷 179-201页

作者： Eldrandaly, Basma K. Ali, Ahmed A. Chakrabortty, Ripon K. Abdel-Basset, Mohamed Faculty of Computers and Informatics Zagazig University Ash Sharqia Governorate Zagazig44519 Egypt School of Engineering and Information Technology University of New South Wales Canberra Australia

The success of an organization nowadays is heavily dependent on the usability of its website. Offering educational content and services online is becoming more commonplace in the higher education sector. University websites serve a wide range of users, like students, faculty, parents, staff, etc. Hence, the website must address the different needs of these users while maintaining good usability. Good usability makes it easier for users to find what they are looking for, understand how to use the website, and navigate through the content. This helps improve user satisfaction and engagement with the website, which can lead to increased productivity and better outcomes. Therefore, usability testing and analysis is the unspoken metric for success. Understanding the many factors contributing to the usability of academic websites is a multi-criteria decision-making (MCDM) topic. In this paper, we propose a framework for evaluating the usability of academic websites using the Entropy and Weighted Aggregated Sum Product Assessment (WASPAS) MCDM methods under type-2 neutrosophic sets. The entropy method is used to compute the objective weights of four main criteria contributing to the usability of academic websites, namely (Content, Organization, Presentation and Interaction, and Trustworthiness), with 31 sub-criteria. The WASPAS method is then used to rank five Egyptian university websites and select the best one in terms of usability. This framework will help designers understand the important criteria to consider while designing for university websites in addition to providing them with a usability evaluation method tailored to university websites. © 2023,Neutrosophic Sets and Systems. All Rights Reserved.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Improving Diabetes Mellitus Diagnosis Performance Using DBSCAN Case-Based Reasoning and Clustering Approaches 10

Improving Diabetes Mellitus Diagnosis Performance Using DBSC...

引用

10th IEEE Information technology International Seminar, ITIS 2024

作者： Heriyani, Dina Yulina Sulistyorini, Dewi Irawan, Buntoro Purnomo, Agus Sidiq Yasin, Iskandar Kurniawan, V. Reza Bayu Universitas Sarjanawiyata Tamansiswa Faculty of Engineering Department of Informatics Yogyakarta Indonesia Universitas Sarjanawiyata Tamansiswa Faculty of Engineering Department of Civil Engineering Yogyakarta Indonesia Universitas Mercu Buana Yogyakarta Faculty of Information Technology Department of Informatics Yogyakarta Indonesia Universitas Sarjanawiyata Tamansiswa Faculty of Engineering Department of Industrial Engineering Yogyakarta Indonesia

ISBN: (纸本)9798331521295

Diabetes Mellitus (DM) is a chronic disease whose prevalence continues to increase throughout the world, including in Indonesia. The limited number of medical personnel and the large amount of health data that must be managed require technology that can help the diagnosis process faster and more accurately. In this study, a Case-Based Reasoning (CBR) system was developed which was optimized with the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) method to improve the performance of Diabetes Mellitus diagnosis. CBR works by utilizing previous cases to solve new cases, while DBSCAN is used to group large and irregular medical data. This grouping process reduces the complexity of searching for relevant cases, thereby increasing the efficiency of diagnosis. The test results show that the proposed system is able to increase the accuracy of diagnosis by up to 93%, with a shorter case encounter time compared to other methods. The accuracy value was obtained from the results of the diagnosis test using case data of 30 diabetes mellitus patients. The innovation in this study is the development of a CBR-DBSCAN-based diagnostic system in the health system to support medical personnel in providing a fast and accurate diagnosis. © 2024 IEEE.

关键词： Case-Based Reasoning (CBR) clustering DBSCAN Diabetes Mellitus medical diagnosis

来源：评论

学校读者我要写书评

暂无评论

Automatic Deployment to Kubernetes Cluster by Applying a New Learning Tool and Learning Processes 10

Automatic Deployment to Kubernetes Cluster by Applying a New...

引用

10th Workshop on Software Quality Analysis, Monitoring, Improvement, and Applications, SQAMIA 2023

作者： Golis, Tomáš Dakić, Pavle Vranić, Valentino Institute of Informatics Information Systems and Software Engineering Faculty of Informatics and Information Technologies Slovak University of Technology in Bratislava Ilkovičova 2 Bratislava842 16 4 Slovakia Faculty of Informatics and Computing Singidunum University Danijelova 32 Belgrade Serbia

The rapid growth and widespread adoption of containerization technologies, such as Docker, and the increasing popularity of Kubernetes as a container orchestration platform have significantly shaped the landscape of modern software development and deployment. Containers have created a paradigm shift in application packaging, offering a consistent and portable environment across diverse infrastructure setups. Meanwhile, Kubernetes has emerged as the dominant choice for managing containerized applications at scale, providing features such as automated scaling, load balancing, and fault tolerance. However, despite the numerous advantages containers and Kubernetes offer, deploying applications to a Kubernetes cluster often poses challenges due to the steep learning curve and complex configuration requirements. To address these challenges, this paper aims to introduce a comprehensive learning tool that automates and simplifies the deployment process on Kubernetes clusters. © 2023 Copyright for this paper by its authors.

关键词： CI/CD Container orchestration Docker image Kubernetes

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：