检索结果-内蒙古大学图书馆

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

作者： Charlotte Cathcart María Santos Shinkyu Park Naomi Ehrich Leonard Department of Mechanical and Aerospace Engineering Princeton University Princeton NJ USA Park is with the Electrical and Computer Engineering program King Abdullah University of Science and Technology Thuwal Saudi Arabia

We propose, analyze, and experimentally verify a new proactive approach for robot social navigation driven by the robot's “opinion” for which way and by how much to pass human movers crossing its path. The robot forms an opinion over time according to nonlinear dynamics that depend on the robot's observations of human movers and its level of attention to these social cues. For these dynamics, it is guaranteed that when the robot's attention is greater than a critical value, deadlock in decision making is broken, and the robot rapidly forms a strong opinion, passing each human mover even if the robot has no bias nor evidence for which way to pass. We enable proactive rapid and reliable social navigation by having the robot grow its attention across the critical value when a human mover approaches. With human-robot experiments we demonstrate the flexibility of our approach and validate our analytical results on deadlock-breaking. We also show that a single design parameter can tune the trade-off between efficiency and reliability in human-robot passing. The new approach has the additional advantage that it does not rely on a predictive model of human behavior.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Beyond Distribution Shift: Spurious Features Through the Lens of Training Dynamics

arXiv

引用

arXiv 2023年

作者： Murali, Nihal Puli, Aahlad Yu, Ke Ranganath, Rajesh Batmanghelich, Kayhan Intelligent Systems Program University of Pittsburgh United States Department of Computer Science New York University United States Department of Electrical and Computer Engineering Boston University United States

Deep Neural Networks (DNNs) are prone to learning spurious features that correlate with the label during training but are irrelevant to the learning problem. This hurts model generalization and poses problems when deploying them in safety-critical applications. This paper aims to better understand the effects of spurious features through the lens of the learning dynamics of the internal neurons during the training process. We make the following observations: (1) While previous works highlight the harmful effects of spurious features on the generalization ability of DNNs, we emphasize that not all spurious features are harmful. Spurious features can be "benign" or "harmful" depending on whether they are "harder" or "easier" to learn than the core features for a given model. This definition is model and dataset dependent. (2) We build upon this premise and use instance difficulty methods (like Prediction Depth (Baldock et al., 2021)) to quantify "easiness" for a given model and to identify this behavior during the training phase. (3) We empirically show that the harmful spurious features can be detected by observing the learning dynamics of the DNN’s early layers. In other words, easy features learned by the initial layers of a DNN early during the training can (potentially) hurt model generalization. We verify our claims on medical and vision datasets, both simulated and real, and justify the empirical success of our hypothesis by showing the theoretical connections between Prediction Depth and information-theoretic concepts like V-usable information (Ethayarajh et al., 2021). Lastly, our experiments show that monitoring only accuracy during training (as is common in machine learning pipelines) is insufficient to detect spurious features. We, therefore, highlight the need for monitoring early training dynamics using suitable instance difficulty metrics. © 2023, CC BY.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Homography Estimation on Multimodal Image Pair via Alternating Optimization

arXiv

引用

arXiv 2024年

作者： Song, Sanghyeob Lew, Jaihyun Jang, Hyemi Yoon, Sungroh Interdisciplinary Program in Artificial Intelligence Seoul National University Korea Republic of Department of Electrical and Computer Engineering Seoul National University Korea Republic of Samsung Electro-Mechanics Korea Republic of

Estimating the homography between two images is crucial for mid- or high-level vision tasks, such as image stitching and fusion. However, using supervised learning methods is often challenging or costly due to the difficulty of collecting ground-truth data. In response, unsupervised learning approaches have emerged. Most early methods, though, assume that the given image pairs are from the same camera or have minor lighting differences. Consequently, while these methods perform effectively under such conditions, they generally fail when input image pairs come from different domains, referred to as multimodal image pairs. To address these limitations, we propose AltO, an unsupervised learning framework for estimating homography in multimodal image pairs. Our method employs a two-phase alternating optimization framework, similar to Expectation-Maximization (EM), where one phase reduces the geometry gap and the other addresses the modality gap. To handle these gaps, we use Barlow Twins loss for the modality gap and propose an extended version, Geometry Barlow Twins, for the geometry gap. As a result, we demonstrate that our method, AltO, can be trained on multimodal datasets without any ground-truth data. It not only outperforms other unsupervised methods but is also compatible with various architectures of homography estimators. The source code can be found at: https://***/songsang7/AltO Copyright © 2024, The Authors. All rights reserved.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

Understanding the stability of advanced inorganic-organic hybrid thin films for advanced resist applications 41

Understanding the stability of advanced inorganic-organic hy...

引用

Advances in Patterning Materials and Processes XLI 2024

作者： Le, Dan N. Chu, Thi Thu Huong Kim, Jin-Hyun Veyan, Jean-Francois Lee, Won-Il Tiwale, Nikhil Lee, Minjong Choi, Seungsoo Woo, Jihoon Nam, Chang-Yong Choi, Rino Kim, Jiyoung Department of Materials Science and Engineering University of Texas at Dallas RichardsonTX75080 United States Department of Materials Science and Chemical Engineering Stony Brook University Stony BrookNY11794 United States Center for Functional Nanomaterials Brookhaven National Laboratory UptonNY11973 United States Department of Electrical and Computer Engineering University of Texas at Dallas RichardsonTX75080 United States Program in Enviromental and Polymer Engineering Inha University Incheon22212 Korea Republic of Department of Materials Science and Engineering Inha University Incheon22212 Korea Republic of

ISBN: (纸本)9781510672208

In this study, we focus on examining the stability of Al-based inorganic-organic hybrid thin films deposited through the molecular atomic layer deposition (MALD) process in ambient environment. Our observations reveal an initial reduction in material thickness within the first 3 days, followed by a period of stability. XPS analysis is employed to further investigate the chemical alternations in the aged Al-based hybrid thin films, revealing an increase in C=O species as well as overall oxygen content in the material. We also evaluate the effects of atmospheric exposure on the sensitivity of the Al-based hybrid thin films using electron flood exposure. This study aims to enhance the understanding of the stability of a vapor-phase synthesized hybrid thin film system for advanced resist applications. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Atomic layer deposition

来源：评论

学校读者我要写书评

暂无评论

Terahertz Time-Domain Imaging for Radiotherapy Treatment Monitoring in Pancreatic Ductal Adenocarcinoma

Terahertz Time-Domain Imaging for Radiotherapy Treatment Mon...

引用

CLEO: Applications and Technology in CLEO 2024, CLEO: A and T 2024 - Part of Conference on Lasers and Electro-Optics

作者： Chakraborty, Debamitra Mills, Bradley N. Cheng, Jing Komissarov, Ivan Gerber, Scott Sobolewski, Roman Materials Science Graduate Program University of Rochester RochesterNY14627 United States Laboratory for Laser Energetics University of Rochester RochesterNY14623-1299 United States Department of Surgery University of Rochester Medical Center RochesterNY14642 United States Department of Electrical and Computer Engineering University of Rochester RochesterNY14627-0231 United States

ISBN: (纸本)9781957171395

Terahertz time-domain imaging was performed of stereotactic body radiotherapy-treated murine pancreatic ductal adenocarcinoma (PDAC) with a high spatial resolution. To generate 2D maps of the tissue samples, the refractive index and absorption coefficient were used as imaging markers extracted with the maximum a-posteriori probability (MAP) estimation algorithm. The results were then compared with the terahertz maps of untreated murine PDAC tissue samples and demonstrated that terahertz imaging can probe physical changes with high sensitivity in the tissue post treatment. © Optica Publishing Group 2024, © 2024 The Author(s)

关键词： Tissue

来源：评论

学校读者我要写书评

暂无评论

Multi-Resonant Class-E2 DC-DC Converter based on Voltage-Controlled Oscillator

Multi-Resonant Class-E2 DC-DC Converter based on Voltage-Con...

引用

IEEE Kansas Power and Energy Conference

作者： Lucas Sangoi Mendonça Valmir de Oliveira Academic Department of Electronics Federal University of Technology-Paraná Curitiba Brazil Academic Department of Electronics Graduate Program in Electrical and Computer Engineering Federal University of Technology-Paraná Curitiba Brazil

ISBN: (数字)9798350372403

ISBN: (纸本)9798350372410

This paper shows the design and implementation of a multi-resonant Class-E 2 DC-DC converter based on voltage- controlled oscillator. By cascading a Class-E inverter to a Class-E rectifier, a double soft-switching converter is obtained, in which, the active switch turns-on with zero voltage switching and the diode turns-off with zero derivative voltage switching. This work relies on design equations based on normalized charts that relate the resonant frequency to the current transfer function, quality factor and peak values for the switch variables. In order to activate the switch, a circuit scheme is proposed based on a voltage-controlled oscillator connected to a low-side gate-driver. Therefore, it is not necessary to use a microcontroller neither auxiliary power sources. Experimental results are presented to show the feasibility of the proposed converter.

关键词： Q-factor Voltage-controlled oscillators Transfer functions Resonant frequency Rectifiers Switches DC-DC power converters

来源：评论

学校读者我要写书评

暂无评论

Uncertain Fault Diagnosis of Grid-Connected PV Systems based Improved Data-Driven Paradigms 19

Uncertain Fault Diagnosis of Grid-Connected PV Systems based...

引用

19th IEEE International Multi-Conference on Systems, Signals and Devices, SSD 2022

作者： Dhibil, Khaled Mansouri, Majdi Bouzrara, Kais Nounou, Hazem Nounou, Mohamed National Engineering School of Monastir Research Laboratory of Automation Signal Processing and Image 5019 Tunisia Electrical and Computer Engineering Program Texas A&M University at Qatar Doha23874 Qatar Prince Sultan Univer-sity Department of Mathematics and Sciences Riyadh11586 Saudi Arabia Chemical Engineering Program Texas A&m University at Qatar Doha23874 Qatar

ISBN: (数字)9781665471084

ISBN: (纸本)9781665471084

The main idea behind this work is to diagnose Grid-Connected Photovoltaic (PV) systems. The uncertainty was treated by using the interval-valued data representation. The main interventions are threefold: first, interval ensemble techniques based on the combination of several models (SVM, KNN, and tree) into one improved model are proposed in order to isolate the different PV systems operating modes using interval raw data. Then, feature extraction and selection steps are proposed to improve the fault diagnosis results. Therefore, the interval KPCA (IKPCA) method is performed in order to extract and select the important characteristics. The proposed techniques were used to diagnose the GCPV system under different operating modes. The results demonstrated the superiority of the proposed methods. © 2022 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

An Efficient Formulation for Optimal Placement of Capacitor Banks in Distribution Feeders Connected to Time-Varying Loads

An Efficient Formulation for Optimal Placement of Capacitor ...

引用

IEEE Kansas Power and Energy Conference

作者： Meisam Mahdavi Augustine Awaafo Konrad Schmitt Manohar Chamana Department of Electrical Engineering University of Jaén Linares Jaén Spain Electrical and Computer Engineering Department Texas Tech University Lubbock TX USA Renewable Energy Program Texas Tech University Lubbock USA

The capacitor placement in radial feeders is an efficient way to mitigate energy losses of distribution networks, where the power converted to useless heat is much higher than transmission system. These considerable power losses increase network operating costs and also decrease quality and quantity of delivered power. Shunt capacitors by compensating part of load reactive power reduce magnitude of feeder current and subsequent distribution losses. However, electricity demand variations with time affects power distributed through feeders and therefore have important role in energy losses determination. Thus, load variability may change the optimal places of capacitors, but considering whole load variations substantially increases the burden and computational time of capacitor placement problem in large-sized distribution systems. Therefore, current study poses an effective capacitor placement formulation for energy loss reduction in the presence of time-varying loads. The numerical results analysis demonstrates the good performance of the presented framework for the optimal placement of capacitor banks in radial distribution feeders with variable loads.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Wheat Agricultural Residences for Bioenergy Generation in Morocco

Wheat Agricultural Residences for Bioenergy Generation in Mo...

引用

Renewable Energy and Hydrogen Technologies (GlobConHT), IEEE IAS Global Conference on

作者： Meisam Mahdavi Francisco Jurado Konrad Schmitt Stephen Bayne Manohar Chamana Department of Electrical Engineering University of Jaén Linares Jaén Spain Electrical & Computer Engineering Department Texas Tech University Lubbock TX USA Renewable Energy Program Texas Tech University Lubbock USA

Morocco is one of the important producers of wheat in Africa, in which this crop is the first agricultural product in the country. In spite of obtaining a huge quantity of wheat residues in the Moroccan agriculture sector, a small portion of this great bioenergy resource is reused for energy generation in the country. This is a big challenge for Morocco because its energy sector highly depends on costly fossil fuel imports. Furthermore, the country has to decrease harmful gases emission based on the Paris and Kyoto agreements. Regarding the importance of rainfall amount and water resources available for this agricultural product that is the main feedstock of Moroccan food, the use of wheat biomass to produce energy will remove high pressure from both the national energy and agriculture sectors. Besides that, the problems related to crop residue removal are reduced by using wheat biomass. Also, the use of wheat residues for energy generation pushes farmers to prevent the open firing of wheat straws and unnecessary air pollutants release. Thus, the present paper, for the first time, calculates possible energy production from wheat straws and root biomasses in Morocco, aiming to provide useful information for Morocco's energy sector.

关键词： Productivity Firing Plants (biology) Hydrogen Crops Air pollution Fossil fuels

来源：评论

学校读者我要写书评

暂无评论

Robust System Reconfiguration in the Presence of Uncertain Loads and Renewable Generation

Robust System Reconfiguration in the Presence of Uncertain L...

引用

IEEE Texas Power and Energy Conference (TPEC)

作者： Meisam Mahdavi Konrad Schmitt Stephen Bayne Manohar Chamana Department of Electrical Engineering University of Jaén Linares Jaén Spain Electrical & Computer Engineering Department Texas Tech University Lubbock TX USA Renewable Energy Program Texas Tech University Lubbock USA

Although distributed generation (DG) operation in modern distribution systems reduces energy losses, DG penetration in such networks is restricted by technical and investment limitations. In order to reduce these losses more efficiently, active distribution systems should be reconfigured based on their time-varying and uncertain load and renewable generation levels. However, considering demand variability in distribution systems’ reconfiguration increases the mathematical efforts, computational burden, and processing time. Besides, the reconfiguration model must be robust enough to avoid consecutive reconfigurations under small load and generation variations. Accordingly, reconfiguration strategies should be chosen so that they have enough robustness and good convergence speed regarding load and generation uncertainty and variability. Therefore, the present paper develops an effective and robust strategy for active distribution systems’ reconfiguration with load and renewable generation variability and uncertainty. The model is submitted to two standard distribution systems where the results are compared with other models presented by the literature. The comparison highlights the robustness and computational time efficiency of the presented model.

关键词： Renewable energy sources Energy loss Uncertainty Computational modeling Distribution networks Robustness Topology

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：