检索结果-内蒙古大学图书馆

7th International Conference on Computational Intelligence and Intelligent Systems, CIIS 2024

作者： Lebaka, Kagiso Blessing Sithungu, Siphesihle Philezwini Academy of Computer Science and Software Engineering University of Johannesburg Gauteng Johannesburg South Africa

ISBN: (纸本)9798400717437

This paper situates itself within the broader medical imaging field, focusing on applying generative modelling techniques for anomaly detection in retinal images. Given the complexity of retinal structures, detecting subtle abnormalities that signal disease requires models that can learn intricate patterns and discern deviations. This study explores the use of a Variational Autoencoder (VAE) to reconstruct healthy retinal images and identify anomalies through reconstruction loss and latent space analysis. With the use of a dataset with an imbalance of healthy and abnormal samples, the model was trained exclusively on healthy images to capture a baseline of normal retinal features. The findings suggest that while the VAE can effectively reconstruct broader structural patterns, it needs to work on finer details, impacting its sensitivity in anomaly detection. These results highlight the challenges inherent in applying generative models to medical diagnostics and emphasise the need for advanced techniques, such as contrastive learning, that may enhance feature extraction. Thus, this paper contributes to the ongoing discourse on the suitability of generative models for medical imaging and supports continued research into more nuanced methods to meet the specific demands of retinal anomaly detection. © 2024 Copyright held by the owner/author(s).

关键词： Ophthalmology

来源：评论

学校读者我要写书评

暂无评论

Line-to-Ground Arc Flash Fault Detection Using Distance Protection Scheme for Wildfire 13

Line-to-Ground Arc Flash Fault Detection Using Distance Prot...

引用

13th IEEE Power and Energy Society: Innovative Smart Grid Technologies - Asia, ISGT Asia 2024

作者： Liu, Emily Nair, Nirmal-Kumar C. The University of Auckland Department of Electrical Computer and Software Engineering Auckland New Zealand

ISBN: (纸本)9798350373929

The outbreak of wildfires due to undetected arc-flash faults poses serious safety hazards to the New Zealand power system and community, resulting in fatalities and infrastructure damage. The consequences of arc-flash faults are particularly significant in low-voltage (LV) distribution systems due to the relatively short overhead line lengths, high fault resistance, and low line-to-ground fault current. This paper explores a distance protection scheme using IEDs with a quadrilateral characteristic on an IEEE LV test feeder to leverage its separately settable resistance and reactance reach for superior arc-fault compensation. The proposed method is validated through analysis and simulations in the software environments of DIGSI 5, OMICRON Test Universe, and OpenDSS. Simulation outcomes indicate that the proposed scheme is feasible for the detection and prevention of wildfires. © 2024 IEEE.

关键词： Premixed flames

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Analysis for Efficient Single Input Multiple Output Inductive Wireless Power Transfer Systems 50

A Comprehensive Analysis for Efficient Single Input Multiple...

引用

50th Annual Conference of the IEEE Industrial Electronics Society, IECON 2024

作者： Bhisti, Ummemisbah Williamson, Sheldon Department of Electrical Computer and Software Engineering Ontario Tech University Oshawa Canada

ISBN: (纸本)9781665464543

The area of wireless power transfer (WPT) technology is developing rapidly and has a wide range of possible uses. In-depth reviews, comparisons, and analysis of power converters and compensation topologies designed especially for Single Input Multiple Output (SIMO) WPT systems are provided in this study. A particular focus is on evaluating compensation topologies in terms of their efficiency and output load independence. To achieve both independence and higher efficiency in SIMO WPT systems, a hybrid compensation strategy with different converters topology is suggested based on a thorough examination and analysis of the literature. This review article opens opportunities for future developments and applications in this emerging sector by offering insightful information about the state of SIMO WPT systems today. © 2024 IEEE.

关键词： Hybrid power

来源：评论

学校读者我要写书评

暂无评论

UGR Calculation Methods Reliability Investigation for LED Luminaires

UGR Calculation Methods Reliability Investigation for LED Lu...

引用

2024 IEEE Sustainable Smart Lighting World Conference and Expo, LS24 2024

作者： Abbasinejad, Reza Kacprzak, Dariusz Abeywardana, Dulsha K. The University of Auckland Department of Electrical Computer and Software Engineering Auckland New Zealand

ISBN: (纸本)9798331540197

In pursuit of energy efficiency goals, LEDs have been widely adopted, though considerations of discomfort remain crucial. LED luminaires with non-uniform luminous intensity distribution (LID), seems contribute to visual discomfort, particularly glare, assessed through the Unified Glare Rating (UGR) index. Although UGR index updates e.g., CIE 232:2019 offer technics to improve UGR calculation for non-uniform LID and LED luminaires, through an investigation of two popular methods - software simulation and manual calculation - this research underscores substantial disparities and inconsistencies in outputs. © 2024 IEEE.

关键词： Energy consumption Indoor lighting LED (Light Emitting Diode) UGR (Unified Glare Rating)

来源：评论

学校读者我要写书评

暂无评论

Hybrid Opinion Dynamics Model Based on Community Relations and Neighbourhood Similarity 4

Hybrid Opinion Dynamics Model Based on Community Relations a...

引用

4th International Symposium on Artificial Intelligence and Intelligent Manufacturing, AIIM 2024

作者： Cao, Zhoulin Xie, Chunzhi Huang, Yu Li, Yanli Liu, Jia Gao, Zhisheng School of Computer and Software Engineering Xihua University Sichuan Chengdu610039 China

ISBN: (纸本)9798331541729

Opinion dynamics models provide essential theoretical and practical tools for comprehending and optimizing information dissemination, policy design, and social phenomena. These models analyze the interactions between individuals to uncover and predict the mechanisms of group behavior and opinion formation. The existing hybrid opinion dynamics model, which combines SNDG and SNHK, is an innovative model that integrates the DeGroot model and the HK model. It also introduces dynamic network updating, incorporating a wider range of agent communication modes. However, this model overlooks the fact that the evolution of individual opinions in real life is often influenced by multiple factors. In this paper, we propose a new opinion dynamics model, NS-SNDG-HK, based on SNDG and SNHK. This model introduces a novel network updating strategy by considering the influence of opinions from the community and neighbors on individual opinions. We conduct experiments using several evaluation metrics on ER Random Networks and Scale-Free Networks to demonstrate that the community and neighbor relationships incorporated in the proposed NS-SNDG-HK model can significantly impact opinion evolution and network outcomes. Furthermore, the model accurately reveals and predicts group opinion propagation behavior, which aligns more closely with that observed in real social networks. © 2024 IEEE.

关键词： Community Relationships Hybrid Opinion Dynamics Model Neighborhood Similarity Network Updates Opinion Dynamics

来源：评论

学校读者我要写书评

暂无评论

A Solid State Transformer-based Charging Station for Catering Heavy/Medium and Light Electric Vehicles 4

A Solid State Transformer-based Charging Station for Caterin...

引用

4th International Conference on Smart Grid and Renewable Energy, SGRE 2024

作者： De Seram, Ruvini Lulbadda, Kushan Tharuka Sidhu, Tarlochan Williamson, Sheldon S. Ontario Tech University Department of Electrical Computer and Software Engineering Oshawa Canada

ISBN: (纸本)9798350306262

Incorporating solid-state transformers into EV charging stations can greatly improve their power density, reliability, efficiency, etc. This paper presents an solid state transformer (SST)-based EV charging station that can cater to three different types of vehicles according to the charging power requirement;heavy, medium, and light electric vehicles. Also, the proposed charging station provides both AC on-board charging and DC off-board charging ports. A MATLAB model of the proposed system was developed and simulated to validate the feasibility. The simulation results verifies that the proposed 10 kV, 1 MVA charging station is capable of charging the all categories of electric vehicles from 20% state of charge (SoC) to 80% SoC within 17.8 mins using constant current charging strategy. Furthermore, one heavy duty electric vehicle which is 30% of the charging station capacity is disconnected to demonstrate a sudden EV demand drop and the total harmonic distortion (THD) of grid current is observed to be laid below 2.6% before and after the event of disconnecting ensuring the stability of the proposed system. © 2024 IEEE.

关键词： MATLAB

来源：评论

学校读者我要写书评

暂无评论

An Analysis of Single- and Dual-Phase Shift Modulation Techniques for Closed-loop Control of Dual-Active Bridge Converter 50

An Analysis of Single- and Dual-Phase Shift Modulation Techn...

引用

50th Annual Conference of the IEEE Industrial Electronics Society, IECON 2024

作者： De Seram, Ruvini Lulbadda, Kushan Tharuka Varaprasad, Oruganti V.S.R. Williamson, Sheldon S. Department of Electrical Computer and Software Engineering Ontario Tech University Oshawa Canada

ISBN: (纸本)9781665464543

The Dual-Active Bridge (DAB) converter’s versatility and ability to support bidirectional power flow make it a highly suitable option for modern power systems, especially in electric vehicle (EV) charging infrastructure. This paper explores phase shift control strategies for regulating power flow in DAB converters, with a particular emphasis on Single-Phase Shift (SPS) and Dual-Phase Shift (DPS) modulation techniques. The theoretical principles of power transmission within a DAB converter are detailed, and closed-loop control under both SPS and DPS modulation is demonstrated with simulation results using PLECS software. To validate these simulations, the closed-loop controllers were implemented in a 1kVA, 200V/200V DAB converter prototype, where the average efficiencies for SPS and DPS modulation were recorded at 96.69% and 97.05%, respectively. The paper concludes with a comparative analysis of the two modulation techniques. © 2024 IEEE.

关键词： Phase shift

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Methods of Symptom Extraction from Medical Notes

Machine Learning Methods of Symptom Extraction from Medical ...

引用

2024 International Russian Smart Industry Conference, SmartIndustryCon 2024

作者： Galai, Olesia Kurdiumov, Dmitrii Rusak, Alena ITMO University Faculty of Software Engineering and Computer Systems Saint-Petersburg Russia

ISBN: (纸本)9798350395044

Medical notes contain valuable information about patient conditions, treatments, and progress. Extracting symptoms from these unstructured notes is crucial for clinical research, population health analysis, and decision support systems. Traditional manual methods are time-consuming, but recent advances in natural language processing (NLP) and machine learning offer automated solutions. This article presents a novel approach that combines NLP techniques, such as conditional random fields (CRF) and transformer-based architectures. The proposed method demonstrates effective symptom extraction from medical notes, overcoming challenges such as varied terminologies and linguistic nuances. The study utilizes a dataset of Russian medical records, transforming it into a tabular format for training and employing unique tokenization algorithms for different models. Among the evaluated models, RuBERT achieved the highest accuracy of 91%, indicating its strong performance on the test dataset. SBERT exhibited the highest precision and F1 score, suggesting its effectiveness in accurately identifying specific sequence labels. © 2024 IEEE.

关键词： Clinical research

来源：评论

学校读者我要写书评

暂无评论

Author profiling from Romanized Urdu text using transfer learning models

引用

Neural Computing and Applications 2025年第6期37卷 4455-4470页

作者： Ali, Abid khan, Muhammad Sohail Khan, Muhammad Amin Khan, Sajid Ullah Khan, Faheem Department of Computer Software Engineering University of Engineering & Technology Mardan KPK Mardan23200 Pakistan Islamabad H-11/4 Islamabad44000 Pakistan Department of Information Systems College of Computer Engineering and Sciences Prince Sattam Bin Abdulaziz University Al-Kharj Saudi Arabia Department of Computer Engineering Gachon University Seongnam-Si Korea Republic of

This research concentrates on author profiling using transfer learning models for classifying age and gender. The investigation encompassed a diverse set of transfer learning techniques, including Roberta, BERT, ALBERT, Distil BERT, Distil Roberta, ELECTRA, and XLNet. Through meticulous evaluation using metrics such as the Matthews Correlation Coefficient, Accuracy, Precision, Recall, and F1 Score, the study examined the efficacy of these models. The curated dataset was divided for gender and age tasks, resulting in robust gender prediction with the XLNet model and age prediction with the BERT model. Notably, the XLNet model achieved the highest MCC (0.7946), Accuracy (0.8957), Precision (0.8992), Recall (0.8957), and F1 Score (0.8958) values in gender classification, while the BERT model excelled in age prediction with an MCC of (0.7338), Accuracy of (0.8220), Precision of (0.8324), Recall of (0.8220), and F1 Score of (0.8243). Visualized outcomes provide valuable insights into the model’s performance nuances, paving the way for their practical implementation. This research offers novel contributions to author profiling tasks, bridging the gap between theory and real-world applications. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Crucial Examination of Thermal Behavior of Solid-State Battery for Intelligent Gray Box Model-based Automotive Battery Management Systems 50

Crucial Examination of Thermal Behavior of Solid-State Batte...

引用

50th Annual Conference of the IEEE Industrial Electronics Society, IECON 2024

作者： Samanta, Akash Chetri, Chandan Williamson, Sheldon Department of Electrical Computer and Software Engineering Ontario Tech University Oshawa Canada

ISBN: (纸本)9781665464543

Solid-state batteries (SSBs) represent one of the most promising technologies for next-generation energy storage systems, offering potential advantages in safety, energy density, and longevity compared to traditional lithium-ion batteries. However, comprehending and managing the thermal behavior of these batteries across a wide range of operating conditions is essential for ensuring their safe and reliable operation. Furthermore, gray box modeling-based state estimation and control are extremely crucial due to the higher degree of nonlinearity exhibited under dynamic operating conditions of SSBs. Gray box modeling is a fusion of equivalent circuit models and data-driven techniques, requiring battery test data and information on charging/discharging and thermal characteristics of SSBs. Therefore, this paper presents a comprehensive analysis of the thermal behavior of SSBs through laboratory experiments conducted in a controlled environment. Additionally, it investigates the thermal characteristics of SSBs under various charging and discharging conditions to assess their suitability for e-mobility applications. Moreover, it examines the thermal behavior and stability of SSBs and introduces a concept of a gray box modeling-based temperature detection scheme for an effective thermal management system. The insights gained from this study can inform the development of advanced thermal management strategies and contribute to the design of safer and more efficient solid-state battery technologies for e-mobility applications. © 2024 IEEE.

关键词： Solid-State Batteries

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：