检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Asadi, Saeed Gharibzadeh, Sonia Zangeneh, Shiva Reihanifar, Masoud Rahimi, Morteza Abdullah, Lazim Department of Civil Engineering The University of Texas at Arlington ArlingtonTX United States Department of Computer Engineering South Tehran Branch Islamic Azad University Tehran Iran Faculty of Engineering University of Malayer Malayer Iran Department of Civil and Environmental Engineering University of California at Berkeley BerkeleyCA United States Department of Civil and Environmental Engineering BarcelonaTech Technical University of Catalonia Barcelona Spain Knight Foundation School of Computing and Information Sciences Florida International University MiamiFL United States Faculty of Ocean Engineering Technology and Informatics Universiti Malaysia Terengganu Kuala Nerus Malaysia

This study examines several renowned gradient-based optimization techniques and focuses on their computational efficiency and precision. In the study, the steepest descent, conjugate gradient (Fletcher-Reeves and Polak-Ribiere variants), Newton-Raphson, quasi-Newton (BFGS), and Levenberg-Marquardt techniques were evaluated. These methods were benchmarked using Rosenbrock's, Spring Force Vanderplaats', Ackley's, and Himmelblau's functions. We emphasize the critical role that initial point selection plays in optimizing optimization outcomes in our analysis. It is also important to distinguish between local and global optima since gradient-based methods may have difficulties dealing with nonlinearity and multimodality. We illustrate optimization trajectories using 3D surface visualizations in order to increase understanding. While gradient-based methods have been demonstrated to be effective, they may be limited by computational constraints and by the nature of the objective functions, necessitating the use of heuristic and metaheuristic algorithms in more complex situations. Copyright © 2024, The Authors. All rights reserved.

关键词： Heuristic algorithms

来源：评论

学校读者我要写书评

暂无评论

A pricing scheme for electric utility’s participation in day-ahead and real-time flexibility energy markets

引用

Journal of Modern Power Systems and Clean Energy 2019年第5期7卷 1294-1306页

作者： Ioannis MAMOUNAKIS Nikolaos EFTHYMIOPOULOS Dimitrios J.VERGADOS Georgios TSAOUSOGLOU Prodromos MAKRIS Emmanouel Manos VARVARIGOS Department of Electrical and Computer Engineering Institute of Communication and Computer SystemsNational Technical University of AthensAthensGreece Department of Computer Engineering and Informatics University of PatrasRio-PatrasGreece Department of Electrical and Computer Systems Engineering Monash UniversityMelbourneAustralia

Liberalized electricity markets,smart grids and high penetration of renewable energy sources(RESs)led to the development of novel markets,whose objective is the harmonization between production and demand,usually noted as real time of flexibility *** necessitates the development of novel pricing schemes able to allow energy service providers(ESPs)to maximize their aggregated profits from the traditional markets(trading between wholesale/day-ahead and retail markets)and the innovative flexibility *** the same time,ESPs have to offer their end users(consumers)competitive(low cost)energy *** this context,novel pricing schemes must act,among others,as automated demand side management(DSM)techniques that are able to trigger the desired behavioral changes according to the flexibility market prices in energy consumption curves(ECCs)of the *** pricing schemes proposed so far,*** pricing,interact in an efficient way with wholesale *** they do not provide consumers with strong enough financial incentives to modify their energy consumption habits towards energy cost ***,they do not interact efficiently with flexibility ***,we develop a flexibility real-time pricing(FRTP)scheme,which offers a dynamically adjustable level of financial incentives to participating users by fairly rewarding the ones that make desirable behavioral changes in their *** evaluation results demonstrate that the proposed FRTP is able to offer a 15%–30%more attractive trade-off between the stacked profits of ESPs,*** sum of the profits from retail and flexibility markets,and the satisfaction of consumers.

关键词： Demand response Flexibility markets Realtime pricing(RTP) Behavioral change Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

DOES AN ENSEMBLE OF GANS LEAD TO BETTER PERFORMANCE WHEN TRAINING SEGMENTATION NETWORKS WITH SYNTHETIC IMAGES?

arXiv

引用

arXiv 2022年

作者： Larsson, Måns Akbar, Muhammad Usman Eklund, Anders Eigenvision Malmö Sweden Division of Medical Informatics Department of Biomedical Engineering Sweden Division of Statistics & Machine Learning Department of Computer and Information Science Sweden Linköping University Sweden

Large annotated datasets are required to train segmentation networks. In medical imaging, it is often difficult, time consuming and expensive to create such datasets, and it may also be difficult to share these datasets with other researchers. Different AI models can today generate very realistic synthetic images, which can potentially be openly shared as they do not belong to specific persons. However, recent work has shown that using synthetic images for training deep networks often leads to worse performance compared to using real images. Here we demonstrate that using synthetic images and annotations from an ensemble of 20 GANs, instead of from a single GAN, increases the Dice score on real test images with 4.7% to 14.0% on specific classes. © 2022, CC BY.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

An advanced deep neural network for fundus image analysis and enhancing diabetic retinopathy detection

引用

Healthcare Analytics 2024年 5卷 100303-100303页

作者： Mehedi Shamrat, F M Javed Shakil, Rashiduzzaman Sharmin Hoque ovy, Nazmul Akter, Bonna Ahmed, Md Zunayed Ahmed, Kawsar Bui, Francis M. Moni, Mohammad Ali Department of Computer System and Technology University of Malaya Kuala Lumpur 50603 Malaysia Department of Computer Science and Engineering Daffodil International University Dhaka 1216 Bangladesh Department of Software Engineering Daffodil International University Dhaka 1216 Bangladesh Department of Computer Science and Engineering European University of Bangladesh Dhaka 1216 Bangladesh Department of Electrical and Computer Engineering University of Saskatchewan 57 Campus Drive Saskatoon S7N 5A9 SK Canada Group of Biophotomatiχ Department of Information and Communication Technology Mawlana Bhashani Science and Technology University Santosh Tangail 1902 Bangladesh Health Informatics Research Lab Department of Computer Science and Engineering Daffodil International University Daffodil Smart City (DSC) Birulia Savar Dhaka 1216 Bangladesh School of Health and Rehabilitation Sciences Faculty of Health and Behavioural Sciences The University of Queensland St Lucia 4072 QLD Australia

Diabetic retinopathy (DR) involves retina damage due to diabetes, often leading to blindness. It is diagnosed via color fundus injections, but the manual analysis is cumbersome and error-prone. While computer vision techniques can predict DR stages, they are computationally intensive and struggle with complex data extraction. In this research, our prime objective was to automate the process of DR classification into its various stages using convolutional neural network (CNN) models. We employed the performance of fifteen pre-trained models with our novel proposed diabetic retinopathy network (DRNet13) model. We aimed to discern the most efficient model for accurate diabetic retinopathy (DR) staging based on fundus images from five DR classes. We preprocessed the image using a median filter for noise reduction and Gamma correction for image enhancement. We expanded our dataset from 3662 to 7500 images to create a more generalized training model through various augmentation techniques. We also evaluated multiple evaluation metrics, including accuracy, precision, F1-score, Sensitivity, Specificity, Area under the curve (AUC), Mean Squared Error (MSE), False Positive Rate (FPR), False Negative Rate (FNR), in addition to confusion matrices for an in-depth comparison of the performance of these models. Feature maps were employed to illuminate decision making areas in the DRNet13 model, which achieved a 97 % accuracy rate for DR detection, surpassing other CNN architectures in speed and efficiency. Despite a few misclassifications, the model's capability to identify critical features demonstrates its potential as an impactful diagnostic tool for timely and accurate identification of diabetic retinopathy. © 2024 The Authors

关键词： Classification Convolutional neural network Diabetic retinopathy network Diagnostic analytics Feature map

来源：评论

学校读者我要写书评

暂无评论

Few-Shot Segmentation and Semantic Segmentation for Underwater Imagery

Few-Shot Segmentation and Semantic Segmentation for Underwat...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Imran Kabir Shubham Shaurya Vijayalaxmi Maigur Nikhil Thakurdesai Mahesh Latnekar Mayank Raunak David Crandall Md Alimoor Reza College of Information Sciences and Technology Pennsylvania State University PA USA Luddy School of Informatics Computing and Engineering Indiana University Bloomington IN USA Department of Mathematics and Computer Science Drake University Des Moines IA USA

This paper tackles image segmentation problems for underwater environments. First, we introduce a novel under-water animal-centric dataset with dense pixel-level annotations containing diverse fine-grained animal categories to mitigate the lack of diverse categories in the existing benchmarks. Then, we solve two image segmentation tasks using underwater images in this dataset: (i) few-shot segmentation, and (ii) semantic segmentation. For the segmentation task in a few-shot learning framework, we propose a novel attention-guided deep neural network architecture by infusing attention modules in various stages of our proposed network. We systematically explore how the learned attention maps can improve few-shot segmentation performance for underwater imagery. Finally, we assess the semantic segmentation problem on our proposed dataset by benchmarking it with two state-of-the-art semantic segmentation methods. We believe our new problem setup, i.e., few-shot segmentation for underwater environments, will be a valuable addition to the existing underwater semantic segmentation task. We believe our novel dataset will pave the way for developing better algorithms and exploring new research directions for marine robotics and underwater image understanding. We publicly release our dataset and the code to advance image understanding research in underwater environments: https://***/Imran220S/uwsnet.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Riemannian manifold-based geometric clustering of continuous glucose monitoring to improve personalized diabetes management

引用

computers in Biology and Medicine 2024年 183卷 109255-109255页

作者： Song, Jiafeng McNeany, Jocelyn Wang, Yifei Daley, Tanicia Stecenko, Arlene Kamaleswaran, Rishikesan Department of Biomedical Engineering Georgia Institute of Technology AtlantaGA30332 United States Department of Biomedical Informatics Emory University AtlantaGA30322 United States Department of Biomedical Engineering Duke University DurhamNC27708 United States Department of Pediatrics Emory University AtlantaGA30322 United States Department of Biological Sciences Georgia Institute of Technology AtlantaGA30322 United States Department of Surgery Duke University School of Medicine DurhamNC27708 United States Department of Anesthesiology Duke University DurhamNC27708 United States Department of Electrical and Computer Engineering Duke University DurhamNC27708 United States

Background: Continuous Glucose Monitoring (CGM) provides a detailed representation of glucose fluctuations in individuals, offering a rich dataset for understanding glycemic control in diabetes management. This study explores the potential of Riemannian manifold-based geometric clustering to analyze and interpret CGM data for individuals with Type 1 Diabetes (T1D) and healthy controls (HC), aiming to enhance diabetes management and treatment personalization. Methods: We utilized CGM data from publicly accessible datasets, covering both T1D individuals on insulin and HC. Data were segmented into daily intervals, from which 27 distinct glycemic features were extracted. Uniform Manifold Approximation and Projection (UMAP) was then applied to reduce dimensionality and visualize the data, with model performance validated through correlation analysis between Silhouette Score (SS) against HC cluster and HbA1c levels. Results: UMAP effectively distinguished between T1D on daily insulin and HC groups, with data points clustering according to glycemic profiles. Moderate inverse correlations were observed between SS against HC cluster and HbA1c levels, supporting the clinical relevance of the UMAP-derived metric. Conclusions: This study demonstrates the utility of UMAP in enhancing the analysis of CGM data for diabetes management. We revealed distinct clustering of glycemic profiles between healthy individuals and diabetics on daily insulin indicating that in most instances insulin does not restore a normal glycemic phenotype. In addition, the SS quantifies day by day the degree of this continued dysglycemia and therefore potentially offers a novel approach for personalized diabetes care. © 2024 Elsevier Ltd

关键词： Continuous glucose monitoring (CGM) Type 1 diabetes (T1D) Uniform manifold approximation and projection (UMAP) Glycemic control Personalized diabetes management

来源：评论

学校读者我要写书评

暂无评论

The Application of Smart and Precision Agriculture (SPA) for Measuring Leaf Nitrogen Content of Oil Palm in Peat Soil Areas

The Application of Smart and Precision Agriculture (SPA) for...

引用

computer Science, Information Technology and engineering (ICCoSITE), International Conference on

作者： Sirojul Munir Kudang Boro Seminar Sudradjat Heru Sukoco Departemen of Computer Science Bogor Agricultural University Bogor Indonesia Departemen of Informatics Nurul Fikri College of Technology Depok Indonesia Departement of Mechanical and Biosystem Engineering Bogor Agricultural University Bogor Indonesia Department of Agronomy and Horticulture Bogor Agricultural University Bogor Indonesia Department of Computer Science Bogor Agricultural University Bogor Indonesia

One of the laborious tasks in operating and managing oil palm lands is measuring the nutrient content of leaves in a timely and periodic manner. It takes a manual process and takes a long time to get leaf samples that are representative of the observed oil palm area, especially in peat soil area. In addition, laboratory analysis of leaf samples is expensive and introduces creates significant time delays for queuing. This paper discusses methods for measuring leaf nitrogen levels in a timely manner based on imagery obtained by C-SAR Sentinel-1A using smart and precision agricultural approaches and applications. The intelligent computational model uses Random Forest Regression to calculate leaf nitrogen content based on spatial image processing and analysis. The calculated leaf nitrogen content is then used to examine and identify the variability of nitrogen content in a given oil palm area. Identification of nutrient variability is one of the approaches and goals of precision agriculture. Our computation model was developed using 553 leaf sampling units (LSU) and validated using 10-Fold validation method, resulting in correctness, MAPE, RMSE and R2 of 95.69%, 4.31%, 0.1119 and 93.28% respectively. The validated model was tested using a set of new data, which is not in the data samples for model development and validation, was resulting in correctness, MAPE, RMSE and R2 of 89.91%, 10.11%, 0.284, and 53.89% respectively. The visual maps can be produced and displayed to visualize variability of nitrogen contents in a peat soil area. This improves visibility and transparency in monitoring nutrient in timely and periodic manner. The future use of the proposed method is to support the application of smart and precision agriculture practices to recommend fertilizers types and dozes for oil palm in peat soil areas based on the variability of leaf nutrient contents.

关键词： Visualization Soil measurements Computational modeling Oils Soil Data models Agriculture

来源：评论

学校读者我要写书评

暂无评论

ROSTAM: A Passwordless Web Single Sign-on Solution Mitigating Server Breaches and Integrating Credential Manager and Federated Identity Systems

arXiv

引用

arXiv 2023年

作者： Mahnamfar, Amin Bicakci, Kemal Uzunay, Yusuf Informatics Institute Istanbul Technical University Istanbul34467 Turkey Computer Engineering Department Istanbul Technical University Istanbul34467 Turkey Securify Information Technology and Security Training Consulting Inc. Ankara06378 Turkey

The challenge of achieving passwordless user authentication is real given the prevalence of web applications that keep asking passwords. Complicating this issue further, in an enterprise environment, a single sign-on (SSO) service is often maintained but not all applications can be integrated with it. We envision a passwordless future which provides a frictionless and trustworthy online experience for users by integrating credential management and federated identity systems. In this regard, our implementation ROSTAM offers a dashboard that presents all applications the user can access with a single click after a passwordless SSO. The security of web passwords on the credential manager is ensured with a Master Key, rather than a Master Password, so that encrypted passwords can remain secure even if stolen from the server. We propose and implement novel techniques for synchronization (pairing) and recovery of this Master Key. We compare our solution to previous work using different evaluation frameworks, demonstrating that our hybrid solution combines the benefits of credential management and federated identity systems. Copyright © 2023, The Authors. All rights reserved.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Smart Education with DNA Testing: A Pathway to Personalized Academic Success

Smart Education with DNA Testing: A Pathway to Personalized ...

引用

International Conference on ICT For Smart Society (ICISS)

作者： Davy Ronald Hermanus Sasmoko Yasinta Indrianti Computer Science Department Research Interest Group in Educational Technology Bina Nusantara University School of Electrical Engineering and Informatics Institut Teknologi Bandung Bandung Indonesia Primary Teacher Education Department Faculty of Humanities Research Interest Group in Educational Technology Bina Nusantara University Jakarta Indonesia Entrepreneurship Department Universitas Agung Podomoro Jakarta Indonesia

ISBN: (数字)9798350389654

ISBN: (纸本)9798350389661

This paper examines the incorporation of DNA testing into intelligent education systems to develop customized learning plans that respond to the specific needs of each student. Through the examination of distinct genetic indicators associated with personality traits, talent, and inborn abilities, educators can formulate approaches that optimize academic achievement and boost the overall welfare of students. This approach not only enhances learning outcomes but also promotes a supportive and inclusive educational environment. The study critically examines the present state of literature regarding the correlation between genetics and learning. It digs into the ethical implications surrounding this topic and shows case studies that provide evidence of the effectiveness of teaching methods informed by DNA analysis. The results underscore the capacity of DNA testing to transform education by enhancing its adaptability and responsiveness to the distinct genetic composition of individual students. This underscores the need for additional research and ethical guidelines to guarantee responsible integration in educational environments.

关键词： Ethics Data privacy Correlation Law Scalability DNA Transforms Educational technology Testing Guidelines

来源：评论

学校读者我要写书评

暂无评论

Study and Simulation of Wind Farms Based on Squirrel Cage Induction Generator in Electrical Distribution System

Study and Simulation of Wind Farms Based on Squirrel Cage In...

引用

International Symposium on Applied Computational Intelligence and informatics ( SACI)

作者： Sayed Mohammad Ali Zanjani Majid Moazzami Mohammad Amin Honarvar Amir Mosavi Arman Fathollahi Smart Microgrid Research Center Najafabad Branch Islamic Azad University Najafabad Iran Department of Electrical Engineering Najafabad Branch Islamic Azad University Najafabad Iran John von Neumann Faculty of Informatics Obuda University Budapest Hungary Department of Electrical and Computer Engineering Aarhus University Aarhus Denmark

Wind power sources are evolving and becoming more prevalent in energy systems, which has implications for a variety of operational metrics, including stability and frequency regulation. To guarantee the stability and reliability of the modern power system, it is crucial that grid-connected wind turbines operate consistently and reliably. It is still challenging to accurately and reliably characterize these generators and their components to analyze sequestered operational possibilities like short-circuit faults, soft-starting, and generator switching. To comprehensively understand the stability interactions within distribution grids or localized networks, an accurate simulation is essential. The current study investigates the impact of a static synchronous compensator (STATCOM) on a distribution system that incorporates an induction generator wind farm. Specifically, we analyze and simulate the effect of STATCOM on a 25 kV distribution system, which delivers the power generated by a 9 MW wind farm to the grid via a 25 kV line. The outcomes demonstrate that STATCOM plays a pivotal role in regulating the voltage changes at the common connection point between the distribution system and the wind farm during both normal and faulty conditions. In addition to improving the stability and efficiency of the distribution network, STATCOM can also provide active power during short-circuit fault conditions. Based on the outcomes, the effectiveness of the proposed approach is highly dependent on the wind energy system’s parameters. Due to the inherent parameter uncertainty, non-stationarity, and nonlinearity in the wind power system, the use of a parameter prediction approach based on artificial intelligence (AI) is recommended for future research.

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：