检索结果-内蒙古大学图书馆

2024 CHI Conference on Human Factors in Computing Sytems, CHI 2024

作者： Bai, Yunpeng Ikkala, Aleksi Oulasvirta, Antti Zhao, Shengdong Wang, Lucia J. Yang, Pengzhi Xu, Peisen Dept. of Computer Science National University of Singapore Singapore Dept. of Computer Science Aalto University Espoo Finland Dept. of Information and Communications Engineering Aalto University Helsinki Finland School of Creative Media Dept. of Computer Science City University of Hong Kong Hong Kong Hong Kong Dept. of Electrical Engineering and Computer Science Massachusetts Institute of Technology Cambridge United States Dept. of Electrical Engineering Mathematics and Computer Science Delft University of Technology Delft Netherlands Dept. of Computer Science IPAL National University of Singapore Singapore

ISBN: (纸本)9798400703300

Optical Head-Mounted Displays (OHMDs) allow users to read digital content while walking. A better understanding of how users allocate attention between these two tasks is crucial for improving OHMD interfaces. This paper introduces a computational model for simulating users' attention switches between reading and walking. We model users' decision to deploy visual attention as a hierarchical reinforcement learning problem, wherein a supervisory controller optimizes attention allocation while considering both reading activity and walking safety. Our model simulates the control of eye movements and locomotion as an adaptation to the given task priority, design of digital content, and walking speed. The model replicates key multitasking behaviors during OHMD reading while walking, including attention switches, changes in reading and walking speeds, and reading resumptions. © 2024 Copyright held by the owner/author(s)

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

On Crowdsourcing-Design with Comparison Category Rating for Evaluating Speech Enhancement Algorithms 48

On Crowdsourcing-Design with Comparison Category Rating for ...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Suarez, Angelica S. Z. Laroche, Clement Clemmensen, Line H. Das, Sneha Technical University of Denmark Dept. of Applied Mathematics and Computer Science Denmark GN Audio Research Ballerup Denmark

ISBN: (纸本)9781728163277

Speech enhancement techniques improve the quality or the intelligibility of an audio signal by removing unwanted noise. It is used as preprocessing in numerous applications such as speech recognition, hearing aids, broadcasting and telephony. The evaluation of such algorithms often relies on reference-based objective metrics that are shown to correlate poorly with human perception. In order to evaluate audio quality as perceived by human observers it is thus fundamental to resort to subjective quality assessment and in doing so we identify subgroups of users where the subjective assessments correlate better to objective metrics. In this paper, a user evaluation based on crowdsourcing (subjective) and the Comparison Category Rating (CCR) method is compared against the DNS-MOS, ViSQOL and 3QUEST (objective) metrics. The overall quality scores of three speech enhancement algorithms from real time communications (RTC) are used in the comparison using the P.808 toolkit. Results indicate that while the CCR scale allows participants to identify differences between processed and unprocessed audio samples, two groups of preferences emerge: some users rate positively by focusing on noise suppression processing, while others rate negatively by focusing mainly on speech quality. We further present results on the parameters, size considerations and speaker variations that are critical and should be considered when designing the CCR-based crowdsourcing evaluation1. © 2023 IEEE.

关键词： Speech enhancement

来源：评论

学校读者我要写书评

暂无评论

Automated Road Extraction in Urban and Rural Regions from Remote Sensing Imagery with U-Net and ResNet-Based Architectures 1

Automated Road Extraction in Urban and Rural Regions from Re...

引用

1st IEEE International Conference on Advances in Computing, Communication and Networking, ICAC2N 2024

作者： Sharma, Palvi Kumar, Rakesh Gupta, Meenu Obaid, Ahmed J. Chandigarh University Dept. of Computer Science & Engineering Punjab India Chandigarh University Dept. of Computer Science & Engineering Punjab India University of Kufa Faculty of Computer Science and Mathematics Najaf Iraq National University of Science and Technology College of Technical Engineering Dhi Qar Iraq

ISBN: (纸本)9798350356816

Accurate road extraction from Remote Sensing Imagery (RSI) is crucial for various applications, including urban planning, navigation, and disaster response. This study investigates automated road extraction in rural, semi-urban and urban regions using deep learning architectures, specifically UNet and Deep Residual U-Net (ResNet) models. We leverage High-Resolution Satellite Imagery (HRSI) to train and validate our models, focusing on the distinct characteristics and challenges presented by urban and rural environments. Our methodology involves comprehensive data preprocessing and augmentation techniques to enhance model robustness. We evaluate the performance of both architectures using metrics and achieved an accuracy of 90.29%, recall of 80.95%, precision of 74.89%, and F1- score of 77.80% for the Deep Residual U-Net. Experimental results demonstrates that while both models perform well, the Deep Residual U-Net exhibits superior accuracy and generalization, particularly in complex urban landscapes. © 2024 IEEE.

关键词： Urban planning

来源：评论

学校读者我要写书评

暂无评论

Thermal Model Validation of a Power Electronics Module for Digital Twin Application

Thermal Model Validation of a Power Electronics Module for D...

引用

2024 Energy Conversion Congress and Expo Europe, ECCE Europe 2024

作者： Zoller, Svenja Cabre-Piqueras, Claudia Schilder, Boris Filba-Martinez, Alber Acker, Lukas Frankfurt University of Applied Science Faculty of Computer Science and Engineering Frankfurt Germany Power Systems Dept. Barcelona Spain

ISBN: (纸本)9798350364446

Thermal stress is a critical failure factor for power electronics components. Hence, when developing a precise digital twin for a power system, it is imperative that thermal models provide a reliable portrayal of the component physics. In that regard, manufacturers offer simplified thermal models that enable designers and users to estimate its behaviour. Nevertheless, the accuracy of these models remains unknown, thus compromising the overall certainty of the digital twin. Therefore, it is of interest to discern whether these simplified models are sufficient for the precision required by the digital twin, and to assess the need of developing a more accurate model. Hence, this paper focuses on validating the theoretical thermal model of a power electronics switch module setup by using the deviation of the module mean time to failure (MTTF) as the acceptance parameter. To achieve this, a novel experimental validation methodology is proposed to retrieve an experimental thermal model and compare it to the theoretical one. This validation is performed considering the discrete thermal impedances and introducing the study of the coupling effects within the module. © 2024 IEEE.

关键词： Insulated gate bipolar transistors (IGBT)

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Algorithms for Predicting Chronic Diseases 3

Machine Learning Algorithms for Predicting Chronic Diseases

引用

3rd IEEE World Conference on applied Intelligence and Computing, AIC 2024

作者： Bulus, Furkan Saoud, Bilal Shayea, Ibraheem Syzdykova, Zuleikha Faculty of Electrical and Electronics Engineering Dept. Electronics & Communications Engineering Istanbul34469 Turkey University of Bouira Faculty of Sciences and Applied Sciences Lisea Laboratory Dept. Electrical Engineering Bouira10000 Algeria Astana It University Dept. of Computer Engineering Astana Kazakhstan

ISBN: (纸本)9798350384598

Chronic diseases are the leading cause of death and disability worldwide, necessitating early detection and management to mitigate their adverse effects on health and improve quality of life. Leveraging machine learning algorithms has become a prominent approach in predicting the risk of various chronic diseases. These algorithms excel in analyzing complex datasets to identify patterns and risk factors associated with chronic conditions. This study explores the application of two different machine learning algorithms on an open-source dataset to predict the risk of chronic diseases. The outcomes of these implementations are analyzed and discussed in the final section, providing insights into their effectiveness and potential for enhancing chronic disease management. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

GENAIR: GENERATIVE AI FOR RESILIENT URBAN AIR MOBILITY WITH VTOLS IN DISASTER EVACUATION

GENAIR: GENERATIVE AI FOR RESILIENT URBAN AIR MOBILITY WITH ...

引用

2024 Winter Simulation Conference, WSC 2024

作者： Alsaheal, Abdullah Hoy, William Haro, Priscila Rehman, Asad Celik, Nurcin Dept. of Industrial and Systems Engineering University of Miami Coral GablesFL United States Dept. of Mathematics and Computer Science Saint Louis University Madrid Spain

ISBN: (纸本)9798331534202

Coastal regions face growing threats, making timely and safe evacuation paramount. Current plans rely heavily on congested ground transportation, leading to delays and heightened stress levels. The emerging field of Urban Air Mobility (UAM), utilizing Vertical Take-Off and Landing Vehicles (VTOLs), promises to alleviate these issues by providing solutions for quick evacuation strategies. Here, we aim to leverage Generative Adversarial Networks (GANs) to expand limited datasets with synthetic data specific to disaster scenarios, evacuation routes, airspace considerations, and the impact of real-time weather events, enabling robust simulation of UAM deployment in disaster evacuations. We identified two applicable scenarios: i) UAM for Extreme Weather Emergency Evacuation and ii) Hospital Evacuations using VTOLs as use cases and illustrated their impact. This research seeks to pave the way for optimized, data-driven evacuation planning with UAM and VTOLs, ultimately enhancing the safety and efficiency of evacuations in the face of extreme events. © 2024 IEEE.

关键词： Air mobility

来源：评论

学校读者我要写书评

暂无评论

Experimental Investigation of Torque Ripple Minimization in Three-Phase PMSMs Under Open-Circuit Fault Conditions Utilizing an Adaptive Proportional-Integral-Resonant Controller 50

Experimental Investigation of Torque Ripple Minimization in ...

引用

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

作者： Ghanayem, Haneen Alathamneh, Mohammad Nelms, R.M. Dept. of Electrical and Electronics Engineering Al-Huson University College Al-Balqa Applied University Irbid Jordan Dept. of Electrical and Computer Engineering Auburn University AuburnAL United States

ISBN: (纸本)9781665464543

This study investigates the reduction of torque ripple in Permanent Magnet Synchronous Motors (PMSMs) during open-circuit fault (OCF) conditions using an adaptive Proportional-Integral-Resonant (PIR) control approach. Torque ripples, commonly exacerbated by faults in motor operation, result in undesirable vibrations, noise, and mechanical stress, thereby impacting the motor’s performance and longevity. The proposed PIR control method integrates a resonant controller with a conventional PI-current controller to enhance torque ripple suppression during OCF operation. Experimental validation, conducted using a dSPACE DS1104 platform, focuses on reducing torque ripple during OCF events. The results show that the adaptive PIR control method significantly reduces torque ripples, thus promoting smoother motor operation, increased efficiency, and increased reliability under fault conditions. © 2024 IEEE.

关键词： Permanent magnets

来源：评论

学校读者我要写书评

暂无评论

Enhanced Power Control of Three-Phase Grid-Connected Inverters Using Proportional-Integral-Resonant Controller Under Unbalanced Conditions with a Comparative Analysis between PI and PR Controllers 50

Enhanced Power Control of Three-Phase Grid-Connected Inverte...

引用

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

作者： Alathamneh, Mohammad Ghanayem, Haneen Yang, Xingyu Nelms, R.M. Dept. of Electrical and Electronics Engineering Al-Huson University College Al-Balqa Applied University Irbid Jordan Dept. of Electrical and Computer Engineering Auburn University AuburnAL United States

ISBN: (纸本)9781665464543

This paper introduces an advanced approach to achieve real and reactive power control in grid-connected three-phase inverters under unbalanced grid conditions. A novel Proportional-Integral-Resonant (PIR) control strategy is proposed, aiming to address two primary objectives: maintaining balanced grid currents and point of common coupling voltages (PCC), while simultaneously injecting the grid with the desired real and reactive power. Comparative analyses with conventional Proportional-Integral (PI) and Proportional-Resonant (PR) controllers are conducted. The PI controller exhibits a better transient response and lower steady-state error compared to the PR controller. However, under unbalanced grid conditions, the PI controller exhibits oscillations in the real and reactive power output. In contrast, the PR controller effectively manages unbalanced situations and maintains power control. Thus, the proposed PIR method combines the advantages of both PI and PR controllers: superior transient response and lower steady-state error of PI, and effective handling of unbalanced conditions and power control of PR. The simulation and Hardwre’s experimental validation confirm the efficacy of the proposed method. © 2024 IEEE.

关键词： Transient analysis

来源：评论

学校读者我要写书评

暂无评论

Site Connectivity with Towalink - Implementing an Open Source "SD-WAN Light" 30

Site Connectivity with Towalink - Implementing an Open Sourc...

引用

30th Telecommunications Forum, TELFOR 2022

作者： Henrici, Dirk Wischhof, Lars University of Applied Sciences Dept. of Computer Science and Mathematics Munich Germany

ISBN: (数字)9781665472739

ISBN: (纸本)9781665472739

Towalink is an open source solution for interconnecting multiple sites securely and flexibly. It is based on WireGuard and BGP. With central management of the site routers, it can be considered an "SD-WAN light". We explain the rationale and design decisions of the implementation and share the experiences of using the solution in a real-world setup with a complex topology. © 2022 IEEE.

关键词： Wide area networks

来源：评论

学校读者我要写书评

暂无评论

IMPROVING THE EFFICIENCY OF THE STRETCHING PROCESS OF ALUMINUM ALLOY PLATES

引用

UPB Scientific Bulletin, Series B: Chemistry and Materials Science 2023年第2期85卷 155-166页

作者： Veli, Yelda Petre, Marin Morega, Alexandru M. Dept. of Electrical Machines Materials and Drives Faculty of Electrical Engineering University POLITEHNICA of Bucharest Romania Vimetco ALRO Slatina Romania "Gheorghe Mihoc – Caius Iacob" Institute of Statistical Mathematics and Applied Mathematics Romanian Academy Dept. of Electrical Machines Materials and Drives Faculty of Electrical Engineering University POLITEHNICA of Bucharest Bucharest Romania

Aluminum alloys are subjected to controlled stretching operation. For non-heat-treated plates of 1xxx, 3xxx, 4xxx, and 5xxx aluminum series, the aim is to obtain flatness, and for heat-treated plates (2xxx, 6xxx, and 7xxx series alloys), to obtain the reduction of internal stresses induced by the solution heat treatment. The stretching operation supposes gripping both ends of the plate and pulling the plate in one direction. The initial normal efforts induced by the quenching process were obtained using the Deep-Hole Drilling method (DHD). The model was solved using finite element method (FEM) and the results were confirmed by industrial tests. © 2023, Politechnica University of Bucharest. All rights reserved.

关键词： Aluminum alloys

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：