检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Rahman, Md Hafizur Azam, Md Ali Hossen, Md Abir Ragi, Shankarachary Gadhamshetty, Venkataramana GM Core System Tools & Automation 29755 Louis Chevrolet Road WarrenMI48093 United States GE HealthCare 9900 W Innovation Dr WauwatosaWI53226 United States Department of Computer Science University of South Carolina ColumbiaSC29208 United States Department of Electrical Engineering South Dakota Mines Rapid CitySD57701 United States Department of Civil and Environmental Engineering South Dakota Mines Rapid CitySD57701 United States

Desulfovibrio alaskensis G20 (DA-G20) is utilized as a model for sulfate-reducing bacteria (SRB) that are associated with corrosion issues caused by microorganisms. SRB-based biofilms are thought to be responsible for the billion-dollar-per-year bio-corrosion of metal infrastructure. Understanding the extraction of the bacterial cells’ shape and size properties in the SRB-biofilm at different growth stages will assist with the design of anti-corrosion techniques. However, numerous issues affect current approaches, including time-consuming geometric property extraction, low efficiency, and high error rates. This paper proposes BiofilScanner, a Yolact-based deep learning method integrated with invariant moments to address these problems. Our approach efficiently detects and segments bacterial cells in an SRB image while simultaneously invariant moments measure the geometric characteristics of the segmented cells with low errors. The numerical experiments of the proposed method demonstrate that the BiofilmScanner is 2.1x and 6.8x faster than our earlier Mask-RCNN and DLv3+ methods for detecting, segmenting, and measuring the geometric properties of the cell. Furthermore, the BiofilmScanner achieved an F1-score of 85.28% while Mask-RCNN and DLv3+ obtained F1-scores of 77.67% and 75.18%, respectively. © 2023, CC BY.

关键词： Biofilms

来源：评论

学校读者我要写书评

暂无评论

Experimental Realization of Entangled Coherent States in Two-dimensional Harmonic Oscillators of a Trapped Ion

arXiv

引用

arXiv 2023年

作者： Jeon, Honggi Kang, Jiyong Kim, Jaeun Choi, Wonhyeong Kim, Kyunghye Kim, Taehyun Department of Physics and Astronomy Seoul National University Seoul08826 Korea Republic of Automation and System Research Institute Seoul National University Seoul08826 Korea Republic of Department of Computer Science and Engineering Seoul National University Seoul08826 Korea Republic of Inter-university Semiconductor Research Center Seoul National University Seoul08826 Korea Republic of Institute of Computer Technology Seoul National University Seoul08826 Korea Republic of Institute of Applied Physics Seoul National University Seoul08826 Korea Republic of

Entangled coherent states play pivotal roles in various fields such as quantum computation, quantum communication, and quantum sensing. We experimentally demonstrate the generation of entangled coherent states with the two-dimensional motion of a trapped ion system. Using Raman transitions with appropriate detunings, we simultaneously drive the red and blue sidebands of the two transverse axes of a single trapped ion and observe multi-periodic entanglement and disentanglement of its spin and two-dimensional motion. Then, by measuring the spin state, we herald entangled coherent states of the transverse motions of the trapped ion and observe the corresponding modulation in the parity of the phonon distribution of one of the harmonic oscillators. Lastly, we trap two ions in a linear chain and realize Mølmer-Sørensen gate using two-dimensional motion. © 2023, CC BY.

关键词： Trapped ions

来源：评论

学校读者我要写书评

暂无评论

Super-resolution Reconstruction of Single Image for Latent features

arXiv

引用

arXiv 2022年

作者： Wang, Xin Yan, Jing-Ke Cai, Jing-Ye Deng, Jian-Hua Qin, Qin Cheng, Yao School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu610000 China State Key Laboratory of Rail Transit Vehicle System Southwest Jiaotong University Chengdu610000 China School of Marine Engineering Guilin University of Electronic Technology Guilin541000 China School of Computer and Information Security Guilin University of Electronic Technology Guilin541000 China

Single-image super-resolution (SISR) typically focuses on restoring various degraded low-resolution (LR) images to a single high-resolution (HR) image. However, during SISR tasks, it is often challenging for models to simultaneously maintain high quality and rapid sampling while preserving diversity in details and texture features. This challenge can lead to issues such as model collapse, lack of rich details and texture features in the reconstructed HR images, and excessive time consumption for model sampling. To address these problems, this paper proposes a Latent Feature-oriented Diffusion Probability Model (LDDPM). First, we designed a conditional encoder capable of effectively encoding LR images, reducing the solution space for model image reconstruction and thereby improving the quality of the reconstructed images. We then employed a normalized flow and multimodal adversarial training, learning from complex multimodal distributions, to model the denoising distribution. Doing so boosts the generative modeling capabilities within a minimal number of sampling steps. Experimental comparisons of our proposed model with existing SISR methods on mainstream datasets demonstrate that our model reconstructs more realistic HR images and achieves better performance on multiple evaluation metrics, providing a fresh perspective for tackling SISR tasks. © 2022, CC0.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Hyperspectral video tracker based on spectral difference matching reduction and deep spectral target perception features

引用

Optics and Lasers in engineering 2025年 194卷

作者： Dong Zhao Bin Hu Wenhao Jiang Weixiang Zhong Pattathal V. Arun Kuanhong Cheng Zhe Zhao Huixin Zhou Jiangsu Province Engineering Research Center of Photonic Devices and System Integration for Communication Sensing Convergence Wuxi University Wuxi 214105 China Computer Science and Engineering Group Indian Institute of Information Technology Sri City 441108 India School of Computer Science and Engineering Xi'an University of Technology Xi'an 710048 China School of Physics Xidian University Xi'an 710071 China

To address the challenge of tracking drift caused by background clutter in hyperspectral video tracking, this paper proposes a novel hyperspectral video tracker that utilizes spectral difference matching dimensionality reduction and deep spectral target perception features. The spectral difference matching dimensionality reduction technique compresses complex redundant hyperspectral data, and generates spectral mask in the process of compression. The spectral mask is then used to locate the target and suppress background clutter information. In order to enhance the ability of tracker that perceives spectral information, spectral target perception features are derived from spectral entropy. These features integrate deep semantic information with real-time background entropy information, effectively suppressing background clutter. Furthermore, a novel confidence judgment criterion is proposed to update targets, addressing challenges posed by interference from similar objects. The advantage of the proposed method is that it can make full use of the spectral information in the hyperspectral image and enhance the ability of the model to identify the target from the complex background. Experimental results conducted on benchmark datasets demonstrate that the proposed tracker has superior robustness against background clutter, compared to existing twelve state-of-the-art tracking methods, achieving an AUC of 0.609 and a DP@20 of 0.895, respectively. The source code along with parameter setting of this work is publicly available at https://***/gmk312/*** .

关键词： Clutter (information theory)

来源：评论

学校读者我要写书评

暂无评论

Review of feasibility wind turbine technologies for highways energy harvesting 1

Review of feasibility wind turbine technologies for highways...

引用

1st International Conference on Emerging Electrical Energy, Electronics and Computing Technologies 2019, ICE4CT 2019

作者： Liew, H.F. Baharuddin, I. Rosemizi, Abd R Muzamir, I. Hassan, S.I.S. Faculty of Engineering Technology University Malaysia Perlis Sungai Chuchuh Perlis02100 Malaysia School of Electrical System Engineering Universiti Malaysia Perlis Pauh Putra Campus Arau Perlis02600 Malaysia School of Computer and Communication Engineering Universiti Malaysia Perlis Pauh Putra Campus Perlis Arau02600 Malaysia

Wind energy is one of the non-conventional forms of energy and it is available in affluence. It is also claimed that the wind power is pollution-free, replacement of fossil fuel and that its source of energy is freely available. Electricity can be generated with the help of a wind turbine generator. In this paper, a comprehensive study on contemporary portable wind energy harvesters has been conducted. The different existing performance such as reliability evaluation models, various problems related to structure wind turbine components (blade, gearbox, generator and transformer) and grid for wind energy system have been discussed. At the same time, experimental analysis is focused on behaviour, especially characteristics of impact wind energy, performance as lots of advanced research work has already been done or going on the harnessing of natural wind energy. In this review paper, a different model wind turbine has been studied from previous testing purpose presented. This review aim of utilizing this wind energy in a most effective manner to get the maximum electric output, and therefore the government can think over implementing the suitable type of wind turbine configuration selected highway at low cost as our installation site taking the advantage of the moving vehicles on both sides of the road. © Published under licence by IOP Publishing Ltd.

关键词： Wind power

来源：评论

学校读者我要写书评

暂无评论

SLRFormer: Continuous Sign Language Recognition Based on Vision Transformer

SLRFormer: Continuous Sign Language Recognition Based on Vis...

引用

International Conference on Affective Computing and Intelligent Interaction Workshops and Demos (ACIIW)

作者： Feng Xiao Ruyu Liu Tiantian Yuan Zhimin Fan Jiajia Wang Jianhua Zhang School of Computer Science and Engineering Tianjin University of Technology Tianjin P.R. China Engineering Research Center of Learning-Based Intelligent System Ministry of Education Tianjin P.R. China School of Hangzhou Normal University Hangzhou P.R. China School of Technical College for the Deaf Tianjin University of Technology Tianjin P.R. China

Human-Robot interaction (HRI) usually focuses on the interaction between normal people and robots, ignoring the needs of deaf-mute people. Deaf-mute individuals utilize sign language to communicate their thoughts and emotions. Therefore, continuous sign language recognition (CSLR) can be introduced to the robot for communicating with deaf-mute people. However, the mainstream CSLR, which consists of two main modules, i.e., visual feature extraction and contextual modeling, has several problems. Visual features are usually extracted frame-by-frame and lack global contextual information, which results in a crucial impact on subsequent context modeling. In addition, we discovered a substantial degree of redundancy in the sign language data, which can significantly slow down model training and exacerbate the problem of model overfitting. To solve these problems, in this paper, we propose a novel vision transformer-based sign language recognition network combined with the off-frame extraction (KFE) module for accurate end-to-end recognition of input video sequences. Two CSLR benchmarks, TJUT-SLRT and USTC-CSL, have been the subject of our experiments. The outcomes of our experiments illustrate the efficacy of our method.

关键词： Training Visualization Human-robot interaction Gesture recognition Assistive technologies Feature extraction Transformers

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of Control Methods for Grid Side Converters in PMSG-Based Wind Energy Conversion systems

A Comparative Study of Control Methods for Grid Side Convert...

引用

IEEE International Symposium on Industrial Electronics (ISIE)

作者： Mohammad Sadegh Eslahi Sadegh Vaez-Zadeh Alireza Jabbarnejad Advanced Motion System Research Lab School of Electrical and Computer Engineering College of Engineering University of Tehran Tehran Iran Advanced Motion System Research Lab and the Center of Excellence on Applied Electromagnetic Systems School of Electrical and Computer Engineering College of Engineering University of Tehran Tehran Iran

ISBN: (数字)9781728156354

ISBN: (纸本)9781728156361

Wind energy conversion systems are interfaced with the power grids through power electronic converters. The main duty of grid side converters is to deliver the power to the grid, while fulfilling the grid code requirements. In this paper, the grid codes for the integration of wind power to the grids are presented first. Then the principles of three main control methods for the grid side converters, i.e. vector control, direct power control, and combined control, for permanent magnet synchronous generators are reviewed. In addition, their capabilities and weaknesses in meeting grid codes are investigated. Finally, a comparison of the control performances in fulfilling grid code requirements are presented by extensive simulation results.

关键词： Reactive power Wind turbines Control systems Couplings Wind power generation Power quality Wind energy

来源：评论

学校读者我要写书评

暂无评论

IoT enabled elbow range of motion for rehabilitation therapy

引用

AIP Conference Proceedings 2024年第1期2937卷

作者： K. Praveen J. S. Leena Jasmine R. Dhanagopal R. Suresh Kumar P. T. Vasanth Raj A. Jaya Rosy S. Subathra Department of Electronics and Communication Engineering Chennai Institute of Technology Chennai India Department of Computer Science and Engineering Velammal Engineering College Chennai India Centre for System Design Chennai Institute of Technology Chennai India UG Scholar Department of Electronics and Communication Engineering Chennai Institute of Technology Chennai India

In order to analyze and improve in physical therapy, professional sports, and the performing arts, it is crucial to monitor human joint angle movement. For both acute and chronic injuries, as well as to assess how well a treatment is functioning, range of motion assessment is essential. Athletes are more susceptible to fractures from acute elbow injuries (e.g. in gymnasts falling on an extended elbow). The industry standard for assessing joint ROM is now manual ROM measurements using a hand-held goniometer because of their accessibility and ease of use. We now present the fibre optic approach to assess elbow range of motion because the precision and repeatability of manual goniometer measurement have been questioned. In terms of size and robustness, optical fibre technology provides an exceptional solution for motion capture sensing. The method under study is based on an approach that has been used in the past to quantify spine movement and respiration rate: angular displacement between two separated fibres using intensity modulated optical fibre. By adding IoT, all data are uploaded to the cloud, where they are processed and conclusions are drawn for use in Rehabilation therapy using Functional Electrical Stimulation Therapy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

E-learning techniques and technologies analysis for a moroccan virtual university perspective 2

E-learning techniques and technologies analysis for a morocc...

引用

2nd IEEE International Conference on Electronics, Control, Optimization and computer Science, ICECOCS 2020

作者： Khachouch, Mohamed Karim Loukili, Yassine Benjelloun, Sarah Korchi, Ayoub Lakhrissi, Younes Moumen, Aniss Aghoutane, Badraddine Abdellah University Sidi Mohamed Ben SIGER Laboratory Fez Morocco IbnTofaîl University ENSA System Engineering Laboratory Kenitra Morocco IA Laboratory Computer Science Dept. Faculty of Sciences Meknes Morocco

ISBN: (纸本)9781728169217

Since the beginning of the state of health emergency due to the covid-19 pandemic, and with the closure of schools and universities, Morocco has relied on distance education to ensure the continuity of the educational program. The latter therefore continue to follow their courses thanks in particular to the distance learning system commissioned by the Ministry of Education. Morocco can thus rely on a second mean of education and teaching even after the end of the pandemic for the many advantages it has. At present, each Moroccan university has its own platform;it is obvious that students, today, have their own institutional account that allows them to access these platforms, a crossroads for information exchange and document sharing. Students are relatively initiated to this kind of platform such as Moodle or Google Classroom. However, this is not enough. Morocco needs a complete virtual university capable of providing a good quality of education to all those who deserve and demand it. This paper aims to explain the different categories of learners according to learning models, and to make a comparison between the existing virtual universities in order to make our vision of the Moroccan virtual university more concrete by proposing a model for the latter in a forthcoming work. © 2020 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Exogenous input and state estimation for a class of nonlinear dynamic systems in the presence of the unknown but bounded disturbances

引用

International Journal of Dynamics and Control 2019年第1期7卷 226-240页

作者： Alirezapouri, M.A. Vali, A.R. Khaloozadeh, H. Arvan, M.R. Faculty of Electrical and Computer Engineering Malek-Ashtar University of Technology Tehran Iran Departments of System and Control Faculty of Electrical Engineering K. N. Toosi University of Technology Tehran Iran

Estimation of the exogenous input is an important topic in various applications. Unknown inputs can dramatically degrade the estimation performance in systems with unknown but bounded (UBB) disturbances. In this study, based on UBB assumption of the input and observation disturbances, a method is proposed for simultaneous estimation of the unknown input, state vector, and disturbance for a class of nonlinear dynamical systems. Based on the affine transformation of convex sets, disturbance and unknown input are considered as new state variables and therefore the nonlinear system of state equations is rearranged. Based on interval mathematics, the linearization error of the process and observation equations are bounded with convex closed sets and then combined with the ellipsoidal sets that representing system disturbance. The augmented state vector is estimated based on extended set value observer. To satisfy the stability of the proposed method, the input to state stability and boundedness of the estimation error is analyzed. The proposed method performance is verified by various numerical simulations and compared with other input estimation methods. Numerical simulations show the acceptable performance of the proposed algorithm in the simultaneously estimation of the unknown input, disturbance, and state vector rather than other unknown input estimation method. © 2018, Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Nonlinear dynamical 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：