检索结果-内蒙古大学图书馆

An Improved Time Feedforward Connections Recurrent Neural Networks

Intelligent Automation & Soft Computing 2023年第6期36卷 2743-2755页

作者： Jin Wang Yongsong Zou Se-Jung Lim School of Hydraulic&Environmental Engineering Changsha University of Science&TechnologyChangsha410014China School of Computer&Communication Engineering Changsha University of Science&TechnologyChangsha410014China AI Liberal Arts Studies Division of ConvergenceHonam UniversityGwangju-si62399Korea

Recurrent Neural Networks(RNNs)have been widely applied to deal with temporal problems,such as flood forecasting and financial data *** the one hand,traditional RNNs models amplify the gradient issue due to the strict time serial dependency,making it difficult to realize a long-term memory *** the other hand,RNNs cells are highly complex,which will signifi-cantly increase computational complexity and cause waste of computational resources during model *** this paper,an improved Time Feedforward Connections Recurrent Neural Networks(TFC-RNNs)model was first proposed to address the gradient issue.A parallel branch was introduced for the hidden state at time t−2 to be directly transferred to time t without the nonlinear transforma-tion at time t−*** is effective in improving the long-term dependence of ***,a novel cell structure named Single Gate Recurrent Unit(SGRU)was *** cell structure can reduce the number of parameters for RNNs cell,consequently reducing the computational ***,applying SGRU to TFC-RNNs as a new TFC-SGRU model solves the above two ***,the performance of our proposed TFC-SGRU was verified through sev-eral experiments in terms of long-term memory and anti-interference *** results demonstrated that our proposed TFC-SGRU model can cap-ture helpful information with time step 1500 and effectively filter out the *** TFC-SGRU model accuracy is better than the LSTM and GRU models regarding language processing ability.

关键词： Time feedforward connections long-short term memory gated recurrent unit SGRU RNNs

来源：评论

学校读者我要写书评

暂无评论

Correlation between hydration properties and electrochemical performances on Ln cation size effect in layered perovskite for protonic ceramic fuel cells

引用

Journal of Energy Chemistry 2024年第1期88卷 1-9,I0001页

作者： Inhyeok Cho Jiwon Yun Boseok Seong Junseok Kim Sun Hee Choi Ho-Il Ji Sihyuk Choi Department of Mechanical Engineering Kumoh National Institute of TechnologyGumi 39177GyeongbukRepublic of Korea Department of Aeronautics Mechanical and Electronic Convergence EngineeringKumoh National Institute of TechnologyGumi 39177GyeongbukRepublic of Korea Center for Energy Materials Research Korea Institute of Science and Technology(KIST)Seoul 02792Republic of Korea Center for Hydrogen and Fuel Cell Research Clean Technology Research DivisionKorea Institute of Science and Technology(KIST)Seoul 02792Republic of Korea Department of Energy and Environmental Engineering University of Science and TechnologySeoul 02792Republic of Korea Nanomaterials Science and Engineering Korea University of Science and Technology(UST)KIST CampusSeoul 02792Republic of Korea

PrBa_(0.5)Sr_(0.5)Co_(1.5)Fe_(0.5)O_(5+δ)(PrBSCF) has attracted much research interest as a potential triple ionic and electronic conductor(TIEC) electrode for protonic ceramic fuel cells(PCFCs). The chemical formula for Pr BSCF is AA'B_(2)O_(5+δ), with Pr(A-site) and Ba/Sr(A'-site) alternately stacked along the c-axis. Due to these structural features, the bulk oxygen ion diffusivity is significantly enhanced through the disorder-free channels in the PrO layer;thus, the A site cations(lanthanide ions) play a pivotal role in determining the overall electrochemical properties of layered perovskites. Consequently, previous research has predominantly focused on the electrical properties and oxygen bulk/surface kinetics of Ln cation effects,whereas the hydration properties for PCFC systems remain unidentified. Here, we thoroughly examined the proton uptake behavior and thermodynamic parameters for the hydration reaction to conclusively determine the changes in the electrochemical performances depending on LnBa_(0.5)Sr_(0.5)Co_(1.5)Fe_(0.5)O_(5+δ)(LnBSCF,Ln=Pr, Nd, and Gd) cathodes. At 500 ℃, the quantitative proton concentration of PrBSCF was 2.04 mol% and progressively decreased as the Ln cation size decreased. Similarly, the Gibbs free energy indicated that less energy was required for the formation of protonic defects in the order of Pr BSCF < Nd BSCF < Gd BSCF. To elucidate the close relationship between hydration properties and electrochemical performances in LnBSCF cathodes, PCFC single cell measurements and analysis of the distribution of relaxation time were further investigated.

关键词： Protonic ceramic fuel cell Cathode Triple ionic and electronic conductor Hydration property Proton uptake Gibbs free energy

来源：评论

学校读者我要写书评

暂无评论

Health Monitoring of Old Buildings in Bangladesh: Detection of Cracks and Dampness Using Image Processing

Health Monitoring of Old Buildings in Bangladesh: Detection ...

引用

2023 International Conference on Next-Generation Computing, IoT and Machine Learning, NCIM 2023

作者： Angan, Rafiul Bari Hossain, Md. Safaiat Nobel, Sadman Sakib Hasan, Md Mahmudul School of Civil Mining Environmental and Architectural Engineering University of Wollongong WollongongNSW2522 Australia University of Engineering and Technology Department of Electrical and Electronic Engineering Bangladesh Army Natore6431 Bangladesh North South University Department of Electrical and Computer Engineering Dhaka1229 Bangladesh School of Computer Science and Engineering University of New South Wales KensingtonNSW2052 Australia

ISBN: (纸本)9798350316001

Numerous buildings in Bangladesh were constructed without following standard building codes. As a result, those are vulnerable to increased earthquake frequency and variable loads. To address this issue, old buildings need to be monitored frequently by non-destructive testing (NDT) to avoid any failures. The identification of cracks and dampness is one of the most important parts of this test. Generally, this detection part is costly and time-consuming to conduct it manually. To resolve this, the current study has been performed for intelligent structural damage identification based on deep learning techniques. A state-of-the-art Convolutional Neural Network (CNN)-based object detection model YOLOv4-tiny has been used to detect cracks and dampness and repair cost analysis of damages. The study outcome suggests that using our proposed deep model, it is possible to detect building cracks with a mean Average Precision (%mAP) of 72.46%. In addition to traditional structural health monitoring, computer vision-based structural health monitoring enables the development of an easily accessible, cost-effective, real-time crack and dampness detection system. © 2023 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

An Approach for Performance Calculation of AVS/RS in Multi-floor Workshop 3rd

An Approach for Performance Calculation of AVS/RS in Multi-f...

引用

3rd International Conference on Smart Manufacturing, Industrial and Logistics engineering, SMILE 2023 and the 7th Asian Conference of Management Science and Applications, ACMSA 2023

作者： Liu, Xiaopeng Wu, Cuiying Zhang, Baolin Xi, An Chen, Xuanrui Ministry of Industry and Information Technology Key Laboratory of Industrial Software Engineering Application Technology China Electronic Product Reliability and Environmental Testing Research Institute Guangzhou510619 China School of Computer and Information Engineering Hanshan Normal University Guangdong Chaozhou521041 China

ISBN: (纸本)9789819701933

Warehouse management is an important part of the production process. As a result of the development of technology, more and more companies tend to use automated logistics technologies such as AVS/RS to handle the internal logistics of the production system. Especially in multi-floor workshops, the production process on each floor are connected with each other through AVS/RS. It is becoming more and more important to study the integration process of AVS/RS and multi-floor workshop production process. In this paper, an integrated queuing network model of multi-floor workshop and AVS/RS was established, and a calculation method of system performance index was proposed. The accuracy and efficiency of the proposed method are demonstrated by comparing the results with simulations from numerical experiments. The work of this article can provide a basis for the design of autonomous vehicle storage and retrieve systems in multi-floor workshop, and the calculation method can be used as the support of WMS technology base. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Floors

来源：评论

学校读者我要写书评

暂无评论

Deep learning analysis of smart meter data from a small sample of room air conditioners facilitates routine assessment of their operational efficiency

引用

Energy and AI 2024年第2期16卷 42-52页

作者： Weiqi Wang Zixuan Zhou Sybil Derrible Yangqiu Song Zhongming Lu Department of Computer Science and Engineering Hong Kong University of Science and TechnologyClear Bater BayKowloonHong Kong Special Administrative Region Division of Environment and Sustainability Hong Kong University of Science and TechnologyClear Water BayKowloonHong Kong Special Administrative Region Department of Civil Materials and Environmental EngineeringUniversity of Illinois at ChicagoChicagoIllinoisUnited States

Room air conditioners (RACs) are crucial household appliances that consume substantial amounts of electricity. Their efficiency tends to deteriorate over time, resulting in unnecessary energy wastage. Smart meters have become popular to monitor electricity use of home appliances, offering underexplored opportunities to evaluate RAC operational efficiency. Traditional supervised data-driven analysis methods necessitate a large sample size of RACs and their efficiency, which can be challenging to acquire. Additionally, the prevalence of zero values when RACs are off can skew training. To overcome these challenges, we assembled a dataset comprising a limited number of window-type RACs with measured operational efficiencies from 2021. We devised an intuitive zero filter and resampling protocol to process smart meter data and increase training samples. A deep learning-based encoder–decoder model was developed to evaluate RAC efficiency. Our findings suggest that our protocol and model accurately classify and regress RAC operational efficiency. We verified the usefulness of our approach by evaluating the RACs replaced in 2022 using 2022 smart meter data. Our case study demonstrates that repairing or replacing an inefficient RAC can save electricity by up to 17 %. Overall, our study offers a potential energy conservation solution by leveraging smart meters for regularly assessing RAC operational efficiency and facilitating smart preventive maintenance.

关键词： Room air conditioning Operational energy efficiency Smart meter Deep learning Smart preventive maintenance

来源：评论

学校读者我要写书评

暂无评论

Location-Independent Human Activity Recognition Using WiFi Signal 8th

Location-Independent Human Activity Recognition Using WiFi S...

引用

8th International Conference on Signal and Information Processing, Network and computers, ICSINC 2021

作者： Kiazolu, Gogo Dauda Aslam, Sehrish Ullah, Muhammad Zakir Han, Mingda Weamie, Sonkarlay J. Y. Miller, Robert H. B. School of Information Science and Engineering Shandong Normal University Jinan250358 China College of Computer Science and Electronic Engineering Hunan University Hunan Changsha410082 China College of Safety and Environmental Engineering Shandong University of Science and Technology Qingdao266590 China

ISBN: (纸本)9789811933868

The WiFi sensor constrains the Human activity recognition scheme to an immovable orientation when providing training samples, drastically reducing practical applications. In addition, the empirical investigation through the ubiquitous experience of participants in environments with wireless signals makes it imperatively challenging to evaluate a location-independent method to recognize human activity. In this research, a 1D CNN-LSTM model was built to comparatively analyze location-independent human activity recognition through WiFi CSI. Thus, the method reduces the impact of human activity recognition on location independent. Nevertheless, the experimental results demonstrate that our method can achieve over 94.9% coverage accuracy for location-independent human activity recognition and 90% coverage accuracy for CNNs using our proposed method. The location-independent model developed can be used possibly for practical applications in any situation, and data from each antenna is processed independently, making it applicable in any location or antenna setup. A variety of input sample lengths has been tested to overcome the measurement sensors’ sampling rate limitations. The results show that human activities can be recognized in real-time through WiFi signaling. Therefore, the CSI WiFi connectivity is potentially enhancive in building an excellent platform to locate human activities in modern age. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Channel state information

来源：评论

学校读者我要写书评

暂无评论

Strong magnon-magnon coupling and low dissipation rate in an all-magnetic-insulator heterostructure

引用

Physical Review Applied 2024年第3期22卷 034017页

作者： Jiacheng Liu Yuzan Xiong Jingming Liang Xuezhao Wu Chen Liu Shun Kong Cheung Zheyu Ren Ruizi Liu Andrew Christy Zehan Chen Yifan Liu Ferris Prima Nugraha Xi-Xiang Zhang Dennis Chi Wah Leung Wei Zhang Qiming Shao Department of Electronic and Computer Engineering The IAS Center for Quantum Technologies The Department of Physics and Astronomy The Department of Applied Physics The Physical Science and Engineering Division (PSE) Department of Physics The

Magnetic insulators, such as yttrium iron garnets (YIGs), are important for spin-wave or magnonic devices as their low damping enables low-power dissipation. Magnetic insulator heterostructures can offer larger design space for realizing exotic magnonic quantum states, provided that individual layers have low damping and their exchange coupling is strong and engineerable. Here, we show that, in a high-quality all-insulator thulium iron garnet (TmIG)/YIG bilayer system, TmIG exhibits an ultralow dissipation rate thanks to its low-damping, low-saturation magnetization and strong orbital momentum. The low dissipation rates in both YIG and TmIG, along with their significant coupling strength due to interfacial exchange coupling, enable strong and coherent magnon-magnon coupling. The coupling strength can be tuned by varying the magnetic insulator layer thickness and magnon modes, which is consistent with analytical calculations and micromagnetic simulations. Our results demonstrate TmIG/YIG as a novel platform for investigating hybrid magnonic phenomena and open opportunities for magnon devices comprising all-insulator heterostructures.

关键词： Magnetic coupling Magnetic interactions Magnetization dynamics Magnons Spin waves Magnetic insulators Synthetic antiferromagnetic multilayers Transition metal oxides

来源：评论

学校读者我要写书评

暂无评论

Eddy covariance towers as sentinels of abnormal radioactive material releases

引用

environmental Science and Pollution Research 2025年第11期32卷 6761-6769页

作者： Stachelek, Jemma Dickman, Lee Turin Kraklow, Vachel A. Casleton, Emily Thompson, Elizabeth Christi Sevanto, Sanna Junghans, Ann High Performance Computing Division Los Alamos National Laboratory Los AlamosNM87544 United States Earth and Environmental Sciences Division Los Alamos National Laboratory Los AlamosNM87544 United States Computer Computational and Statistical Sciences Division Los Alamos National Laboratory Los AlamosNM87544 United States Nuclear and Engineering Nonproliferation Division Los Alamos National Laboratory Los AlamosNM87544 United States

Ensuring accurate detection and attribution of abnormal releases of radioactive material is critical for protecting human health and safety. Most commonly, such detection is accomplished via active monitoring approaches involving the collection of physical samples. This is labor intensive and limits the temporal and spatial resolution of any detected events to a relatively coarse level. As an alternative first step towards passive monitoring, we developed an approach using eddy flux tower data records to identify signals from a known abnormal release and quantify the extent to which that signal also occurs at other times in the data record. Through two case studies, one of which targeted the Fukushima nuclear disaster and the other targeting an abnormal release event at a radioisotope production facility in Fleurus, Belgium, we tested our approach and identified several potential heretofore unidentified abnormal events that were consistent with atmospheric circulation patterns and/or wind direction from known release sites. Because our approach is relatively simple and is resistant to systematic errors in the observational record, it has broad applicability beyond specific constituents and ecosystem types to identify a wide variety of limited-duration anomalies in flux tower data to ensure human health and industrial safety. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Nuclear reactor accidents

来源：评论

学校读者我要写书评

暂无评论

Simultaneous Reconstruction and Uncertainty Quantification for Tomography 48

Simultaneous Reconstruction and Uncertainty Quantification f...

引用

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

作者： Dasgupta, Agnimitra Graziani, Carlo Di, Zichao Wendy University of Southern California Sonny Astani Department of Civil & Environmental Engineering United States Argonne National Laboratory Mathematics and Computer Science Division United States

ISBN: (纸本)9781728163277

Tomographic reconstruction, despite its revolutionary impact on a wide range of applications, suffers from its ill-posed nature in that there is no unique solution because of limited and noisy measurements. Therefore, in the absence of ground truth, quantifying the solution quality is highly desirable but under-explored. In this work, we address this challenge through Gaussian process modeling to flexibly and explicitly incorporate prior knowledge of sample features and experimental noises through the choices of the kernels and noise models. Our proposed method yields not only comparable reconstruction to existing practical reconstruction methods (e.g., regularized iterative solver for inverse problem) but also an efficient way of quantifying solution uncertainties. We demonstrate the capabilities of the proposed approach on various images and show its unique capability of uncertainty quantification in the presence of various noises. © 2023 IEEE.

关键词： Gaussian processes statistical inference tomography uncertainty quantification

来源：评论

学校读者我要写书评

暂无评论

A Facile Approach for Fabricating Ordered Submicrometer-Wide Surface Patterns by Imprinting Polydimethylsiloxane Cracks 22

A Facile Approach for Fabricating Ordered Submicrometer-Wide...

引用

22nd International Conference on Solid-State Sensors, Actuators and Microsystems, Transducers 2023

作者： Bu, Yang Ni, Sheng Yobas, Levent The Hong Kong University Of Science And Technology Department Of Electronic And Computer Engineering Hong Kong The Hong Kong University Of Science And Technology Division Of Bioengineering Hong Kong

ISBN: (纸本)9784886864352

A novel and cost-effective method for creating ordered submicrometer-wide surface patterns using PDMS cracks is presented in this study. Cracks are first formed on a flat PDMS substrate by stretching an oxidized PDMS slab, and then the cracks are imprinted onto a target substrate to create uniform and ordered surface patterns. The resulting submicrometer-wide patterns are difficult to achieve using conventional fabrication methods limited by photolithography's resolution. Applications of the imprinted patterns, such as selective particle capture and DNA combing, are demonstrated. This approach offers a new way to utilize PDMS cracks and provides a simple and low-cost method for creating submicrometer-wide surface patterns with potential applications in various fields. © 2023 IEEJ.

关键词： cracks DNA combing imprinting microfabrication polydimethylsiloxane Surface patterns

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：