检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Hong, Seongmin Park, Inbum Chun, Se Young Dept. of Electrical and Computer Engineering INMC Interdisciplinary Program in AI Seoul National University Korea Republic of

Conditional normalizing flows can generate diverse image samples for solving inverse problems. Most normalizing flows for inverse problems in imaging employ the conditional affine coupling layer that can generate diverse images quickly. However, unintended severe artifacts are occasionally observed in the output of them. In this work, we address this critical issue by investigating the origins of these artifacts and proposing the conditions to avoid them. First of all, we empirically and theoretically reveal that these problems are caused by "exploding inverse" in the conditional affine coupling layer for certain out-of-distribution (OOD) conditional inputs. Then, we further validated that the probability of causing erroneous artifacts in pixels is highly correlated with a Mahalanobis distance-based OOD score for inverse problems in imaging. Lastly, based on our investigations, we propose a remark to avoid exploding inverse and then based on it, we suggest a simple remedy that substitutes the affine coupling layers with the modified rational quadratic spline coupling layers in normalizing flows, to encourage the robustness of generated image samples. Our experimental results demonstrated that our suggested methods effectively suppressed critical artifacts occurring in normalizing flows for super-resolution space generation and low-light image enhancement. Copyright © 2022, The Authors. All rights reserved.

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

A Preliminary Study on Analysing Mandarin Tone Values of Romance L2 Mandarin Learners

A Preliminary Study on Analysing Mandarin Tone Values of Rom...

引用

Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)

作者： Wu-Hao Li Te-hsin Liu Chen-Yu Chiang College of Electrical Engineering and Computer Science National Taipei University Taiwan Graduate Program of Teaching Chinese as the Second Language National Taiwan University Dept. of Communication Engineering National Taipei University New Taipei City Taiwan

ISBN: (数字)9798350367331

ISBN: (纸本)9798350367348

The 5-level tone value labeling system helps characterize pitch contours of syllables for L2 Mandarin learners and teachers to facilitate tone acquisition and tone error analysis, respectively. In the past, linguistic experts did the tone value labeling and initially used it to represent or analyze the pitch contours of monosyllables. Some L2 Mandarin teachers also used the tone value labeling system to analyze pitch contours of continuous speech and illustrate pitch realizations for L2 Mandarin learners. However, the pitch contours of the labeled tone values of continuous speech were rarely objectively measured or analyzed. This paper presents a preliminary analysis of tone values of a continuous read speech corpus uttered by six Romance L2 Mandarin learners. The pitch contours of the tone value classes were explored, and some experiments related to the automatic recognition of tone and tone value classes were reported. We expect the results reported by this study to shed light on the development of an automatic tone value classification mechanism, which will be used in computer-assisted pronunciation training for L2 learners in the future.

关键词： Training Error analysis Asia Information processing Linguistics Labeling

来源：评论

学校读者我要写书评

暂无评论

Low-Crosstalk in 2D Waveguide Crossings by Metaheuristic Optimization Methods

Low-Crosstalk in 2D Waveguide Crossings by Metaheuristic Opt...

引用

Optics and Photonics Conference (SBFoton IOPC), SBFoton International

作者： Luana da França Vieira C. E. Rubio-Mercedes Vitaly Felix Rodriguez Esquerre Department of Computer Science Federal University of Western Bahia Barreiras Brazil Physics Engineering Program State University of Mato Grosso do Sul Dourados Brazil Graduate School of Electrical Engineering Federal University of Bahia Salvador Brazil

ISBN: (数字)9798350388176

ISBN: (纸本)9798350388183

This work describes the investigation of planar waveguide crossings using metaheuristic methods associated with the two-dimensional finite element method (2D-FEM). An optimization and measurement process are performed on the power transmission and crosstalk of the waveguide crossings and then the values calculated are compared with other studies in the literature. The best performing adjusted crossing is optimally designed by applying the following metaheuristics: Particle Swarm Optimization (PSO), Grey Wolf Optimizer (GWO), and a hybrid algorithm combining the Greedy Randomized Adaptive Search Procedure and Simulated Annealing (GRASP-SA). Transmission efficiency results higher than 97% and crosstalk below the -50 dB over a wide wavelength range, with a footprint of $\mathbf{4.9}\times \mathbf{4.9}\ \boldsymbol{\mu} \mathbf{m}^{\mathbf{2}}$ .

关键词： Performance evaluation Power measurement Metaheuristics Crosstalk Power transmission Simulated annealing Silicon Planar waveguides Optical waveguides Photonics

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Networks for Handwritten Bangla Character Recognition

引用

IAENG International Journal of Applied Mathematics 2023年第4期53卷 1页

作者： Begum, H. Islam, M.M. Eva, H.S. Emon, N.H. Siddique, F.A. Department of Electrical and Electronic Engineering East West University A/2 Aftabnagar Dhaka Bangladesh Department of Electrical Engineering and Computer Science South Dakota State University United States Engineering and Design Department Reverie Power and Automation Engineering Limited Bangladesh Program in Smart System Integrated Solutions Aalto University Finland

In recent years, deep convolutional networks (DCNN) have gained popularity for different classification (or recognition) tasks. In this paper, three well known DCNN structures were used, i.e., AlexNet, SqueezeNet and GoogLeNet, and their classification performances in recognizing handwritten Bangla isolated characters were compared. These networks have simpler structures compared to the recent DCNNs. Experiments on a standard Bangla database revealed that the overall performance of GoogLeNet is slightly better than the other two networks. Further analysis using saliency maps of the test samples revealed the important features that are learned by the networks for classifying characters. This information led us to understand why classification of some samples fail and how to rectify these. © (2023), (International Association of Engineers). All Rights Reserved.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Deep Learning for Fault Detection and Diagnosis: Application to Photovoltaic System 19

Deep Learning for Fault Detection and Diagnosis: Application...

引用

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

作者： Marweni, Manel Fezai, Radhia Hajji, Mansour Mansouri, Majdi National Engineering School of Monastir Research Laboratory of Automation Signal Processing and Im-age 5019 Tunisia Electrical and Computer Engineering Program Texas A&m University at Qatar Doha23874 Qatar Prince Sultan University Department of Mathematics and Sciences Riyadh11586 Saudi Arabia

ISBN: (数字)9781665471084

ISBN: (纸本)9781665471084

With expanding requests for effectiveness and product quality and advancing integration of au-tomatic control systems in high-cost and safety-critical processes, Fault Detection and Diagnosis (FDD) in photo-voltaic (PV) have gained a very important role. However, PV systems can be subject to failures. These faults may include the distinctive system components such as PV modules, converters/inverters, connection lines, which can lead to a reduce in the operation performance. Thus, FDD is one of the key technologies to improve the efficiency of grid-connected PV performances. The most well-known data-driven based FDD methods are Deep Learning (DL)-basd approaches. The main advantages of DL algorithms, are that they can learn automatically high- level features from PV data in a high-order. This paper therefore presents the appli-cation of DL-based tools for fault diagnosis purposes and provides a comparative study using PV systems. These techniques include Convolutional Neural Network (CNN), Long-Short Term Memory (LSTM) and BIdirectional Long-Short Term Memory (BILSTM). The implemented FDD based frameworks are validated using an emulated Grid-Connected PV (GCPV) system. The results show that the DL-based diagnosis methods are able to detect and diagnose faults under different operating modes. © 2022 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Development of Mobile Robot Education Kit Prototype for Elementary School Students

Development of Mobile Robot Education Kit Prototype for Elem...

引用

2021 International Conference on computer System, Information Technology, and electrical engineering, COSITE 2021

作者： Priandana, Karlisa Margaretha, Friska Sinaga, Doli Aryo Dani Kusumoputro, Benyamin Bogor Agricultural University Computer Science Department Bogor Indonesia Bogor Agricultural University Vocational School of Computer Engineering Program Bogor Indonesia Research Development Interactive Robotics Bogor Indonesia Universitas Indonesia Dept of Electrical Engineering Depok Indonesia

ISBN: (纸本)9781665425094

Electronic technologies are growing very rapidly, especially those related to automation and robotics. Robotics technology is currently being developed and implemented in various fields including military, search and rescue, education, transportation, sports, and many other fields. Various researches on robotics technology continue to be carried out by various universities in the world including in Indonesia. To increase the interest of the young generation in the field of robotics, an attractive educational kit especially for elementary school level is necessary. This work aims to develop a robotics education kit in the form of a unique and interesting mobile robot as a learning media for elementary school students. The robot was developed using an Arduino microcontroller and can be operated by elementary school students using an easy and user-friendly blocks program.ing. The testing shows that the developed robotics education kit has been able to function properly, in accordance with the design and the specified requirements. © 2021 IEEE.

关键词： Mobile robots

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

Mobile robot position control in environment with static obstacles

引用

IET Cyber-Systems and Robotics 2020年第2期2卷 78-87页

作者： Konstantinos Giannousakis Anthony Tzes Electrical&Computer Engineering Department University of PatrasRio 26500Greece Electrical&Computer Engineering Program New York University Abu DhabiAbu DhabiP.O.Box 129188United Arab Emirates

This study addresses the problem of efficiently navigating a differential drive mobile robot to a target pose in a region with obstacles,without explicitly generating a *** robot is assumed to be equipped with an omnidirectional range sensor,while the region may or may not be a priori *** the known obstacles in each iteration of the controller,the shortest path connecting the robot and the target point provides a raw desired movement *** the unobstructed area in that direction,the size of the robot and the obstacle contours in its visibility range,the reference direction is ***,respecting the velocity and acceleration constraints of the robot,the angular velocity is properly selected to rotate the robot towards the reference direction,while the linear velocity is chosen to efficiently minimise the distance to the final target,as well as to avoid *** the robot has reached the target,the controller switches to orientation mode in order to fix the *** studies demonstrate the effectiveness of the algorithm.

关键词： robot visibility shortest

来源：评论

学校读者我要写书评

暂无评论

Digital Forensics Investigation and Incident Response in Internet of Things (IoT-DFIR): Challenges and Models 9

Digital Forensics Investigation and Incident Response in Int...

引用

9th International Conference on Wireless and Telematics, ICWT 2023

作者： Ahdan, Syaiful Zaki Hamidi, Eki Ahmad Riskiono, Sampurna Dadi Negara, Ridha Muldina Mayasari, Ratna Ramadona, Suci Nurhayati, Ade Sucipto, Adi Jupriyadi Nurkahfi, Galih Nugraha Farahiyah, Dzata Naseer, Muchammad Universitas Teknokrat Indonesia Faculty of Engineering & Computer Science Lampung35132 Indonesia Uin Sunan Gunung Djati Bandung Electrical Engineering Department Bandung40614 Indonesia School of Electrical Engineering Telkom University Bandung40257 Indonesia Elearical Engineering Study Program Politeknik Caltex Riau Riau28265 Indonesia Institut Teknologi Telkom Jakarta Faculty of Engineering Jakarta11710 Indonesia Bandung40135 Indonesia Universitas Islam Indonesia Yogyakarta Faculty of Industrial Technology Yogyakarta55584 Indonesia Sekolah Tinggi Teknologi Bandung Informatics Department Bandung40235 Indonesia

ISBN: (纸本)9798350305029

Many different industries are currently making substantial use of the Internet of Things (IoT). IoT is the process through which electronic devices communicate with their surrounding virtual environment by continuously exchanging data via sensors. Due to increased IoT security concerns, digital forensic investigators now possess greater knowledge and abilities to investigate IoT devices. IoT-DigFor are required in terms of cybercrime due to the rapid growth in the number of electronic devices and the collection and consumption of enormous amounts of data. IoT systems with billions of devices have produced a significant amount of evidence, which presents a significant challenge to digital investigators and practitioners who must connect with IoT devices to conduct fast and thorough investigations into cybercrimes. This article presents detailed information about forensics in the IoT environment. The IoT forensic paradigm and the challenges that design-based security requirements and IoT system security offer for IoT-DigFor are covered in great detail at the beginning of the article. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Modern Flexible Alternating Current Transmission System Controllers (Project)

Modern Flexible Alternating Current Transmission System Cont...

引用

2022 IEEE International Conference on electrical, computer, and Energy Technologies, ICECET 2022

作者： Allen, Larry Beckum, Brandon Taylor, Mathew Qian, Jason El-Shahat, Adel Georgia Southern University Dept. of Electrical and Computer Eng StatesboroGA30460 United States Purdue University School of Engineering Technology West LafayetteIN47906 United States Purdue University Energy Program School of Engineering Technology West LafayetteIN47906 United States

ISBN: (数字)9781665470872

ISBN: (纸本)9781665470872

FACTS controllers are very important machines in the world of Power System engineering. Due to the growing demand for electricity from many different customers, transmission systems are being burdened more than in previous years. The issue is that power providers cannot simply build new lines or an entirely new grid with a better layout, using more modern methods because of cost and legality issues. In our project we built two different FACTS controllers. The first was in a Simulink simulation and it was a Static Synchronous Compensator with fuzzy logic controls, and the other was a physical version that represents a series controller like a Thyristor Controlled Series Compensator or TCSC. We were successful in using fuzzy logic controls in our project as well as scaling down a series compensator in order present the idea of FACTS devices for small scale experimentation in academia. © 2022 IEEE.

关键词： Flexible AC transmission systems

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：