检索结果-南通市图书馆

Physics-informed deep learning for fringe pattern analysis

Opto-Electronic Advances 2024年第1期7卷 4-15页

作者： Wei Yin Yuxuan Che Xinsheng Li Mingyu Li Yan Hu Shijie Feng Edmund Y.lam Qian Chen Chao Zuo Smart Computational imaging Laboratory(SCiLab) School of Electronic and Optical EngineeringNanjing University of Science and TechnologyNanjing 210094China Smart Computational imaging Research institute(SCiRi)of Nanjing University of Science and Technology Nanjing 210019China Jiangsu Key Laboratory of Spectral imaging&intelligent Sense Nanjing 210094China Department of Electrical and Electronic Engineering The University of Hong KongPokfulamHong Kong SAR 999077China

Recently,deep learning has yielded transformative success across optics and photonics,especially in optical *** neural networks (DNNs) with a fully convolutional architecture (e.g.,U-Net and its derivatives) have been widely implemented in an end-to-end manner to accomplish various optical metrology tasks,such as fringe denoising,phase unwrapping,and fringe ***,the task of training a DNN to accurately identify an image-to-image transform from massive input and output data pairs seems at best naive,as the physical laws governing the image formation or other domain expertise pertaining to the measurement have not yet been fully exploited in current deep learning *** this end,we introduce a physics-informed deep learning method for fringe pattern analysis (Pi-FPA) to overcome this limit by integrating a lightweight DNN with a learning-enhanced Fourier transform profilometry (Le FTP) *** parameterizing conventional phase retrieval methods,the Le FTP module embeds the prior knowledge in the network structure and the loss function to directly provide reliable phase results for new types of samples,while circumventing the requirement of collecting a large amount of high-quality data in supervised learning *** by the initial phase from Le FTP,the phase recovery ability of the lightweight DNN is enhanced to further improve the phase accuracy at a low computational cost compared with existing end-to-end *** results demonstrate that Pi-FPA enables more accurate and computationally efficient single-shot phase retrieval,exhibiting its excellent generalization to various unseen objects during *** proposed Pi-FPA presents that challenging issues in optical metrology can be potentially overcome through the synergy of physics-priors-based traditional tools and data-driven learning approaches,opening new avenues to achieve fast and accurate single-shot 3D imaging.

关键词： optical metrology deep learning physics-informed neural networks fringe analysis phase retrieval

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

A review of image processing and quantification analysis for solid oxide fuel cell

引用

Energy and Ai 2024年第2期16卷 464-482页

作者： Kar Shen Tan Chee Kiang lam Wee Choon Tan Heap Sheng Ooi Zi Hao Lim Faculty of Electrical Engineering&Technology Universiti Malaysia PerlisPauh Putra CampusPauh02600PerlisMalaysia Faculty of Mechanical Engineering&Technology Universiti Malaysia PerlisPauh Putra CampusPauh02600PerlisMalaysia Faculty of information Science&Technology Universiti Kebangsaan MalaysiaBangi43600SelangorMalaysia

The purpose of this study is to investigate the approaches applied to analyze solid oxide fuel cell (SOFC) microstructural properties. Both manual and automated image processing approaches applied on SOFC microstructural images which are obtained from several types of tomography such as dual-beam focused ion beam with scanning electron microscopy (FiB-SEM), Electron Backscatter Diffraction (EBSD) and others are discussed. in fact, to achieve a realistic and accurate SOFC microstructural properties, such as average diameter, volume fraction, triple phase boundary (TPB), area interface density and tortuosity factor, the approaches of image processing and quantification are crucial for a reliable image generation for quantification purposes. The microstructural properties are optimized to improve SOFC electrode performance. Therefore, the image processing and quantification approaches are outlined and reviewed. Despite the automated image processing and quantification algorithms significantly outperform manual image processing and quantification approaches in terms of computing speed when evaluating and measuring microstructural properties, the efficiency and productivity are still extremely taken into concern. As a result, image processing and quantification approaches are concluded and presented respectively in this paper.

关键词： Digital image processing Deep learning Triple phase boundary Solid oxide fuel cell Microstructure

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Using Five Music instructional Methods to illustrate the Social Constructive Music Teaching Framework in Hong Kong Primary Level Music Education

引用

Sino-US English Teaching 2024年第6期21卷 247-269页

作者： lam Wing Yin The Hong Kong University of Science and Technology Hong Kong SAR

Music education under the frame name of arts education has been integrated into the primary and secondary education curriculums in Hong Kong for more than 20 years,starting from 2001,the year of launching the Learning to Learn curriculum for the reconstruction of the education system for the younger *** education,embedded into the arts education,was therefore regarded as one of the key subjects to cultivate and uplift student holistic development,focusing on aesthetic skill training and moral growth *** research was an exploration study of music teaching practices from two private international and two general public school music teachers at the primary school *** value of this study rested on borrowing the idea of Shulman’s pedagogical content knowledge(PCK)principle to create a social constructivist music teaching framework from five commonly-used instructional methods,namely,Orff,Kodaly,Dalcrozes,Suzuki,and Gordon’s *** on the evaluations of these four case studies,hypotheses on the differences in the PCK were tested with the types of schools and found to be no *** preliminary results suggested that music teachers in private international schools had similar pedagogical approaches to music instruction to teachers in aided-public ***,the modeling,guiding,and training approach was identified as a grounded teaching method for music education at the primary school level regardless of different types of *** implications like the further development of the framework were discussed.

关键词： pedagogy social constructivism music education primary school Hong Kong

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Porously Reduced 2-Dimensional Bi_(2)O_(2)CO_(3) Petals for Strain-Mediated Electrochemical CO_(2) Reduction to HCOOH

引用

Energy & Environmental Materials 2024年第1期7卷 215-221页

作者： Won Seok Cho Dae Myung Hong Wan Jae Dong Tae Hyung Lee Chul Jong Yoo Donghwa Lee Ho Won Jang Jong-lam Lee Department of Materials Science and Engineering Pohang University of Science and Technology(POSTECH)Pohang Gyungbuk 37673Korea Department of Materials Science and Engineering Research institute of Advanced Materials Seoul National UniversitySeoul 08826Korea

Here we introduce bismuth-based catalysts for the efficient electrochemical reduction of CO_(2)to formic acid(HCOOH),which are composed of petal-shaped Bi_(2)O_(2)CO_(3)(BOC)that spontaneously formed from Bi thin film in aqueous carbonate solution at room *** the electrochemical reduction process,the BOC petals transform to reduced BOC(R-BOC)consisting of individual BOC and Bi *** mismatch between both domains induces biaxial strain at the *** functional theory calculations suggest that the tensile strain on the Bi domain stabilizes the*OCHO intermediate,reducing the thermodynamic barrier toward CO_(2)conversion to *** with the thermodynamic benefit and the unique nanoporous petal-shaped morphology,R-BOC petals have a superior Faradaic efficiency of 95.9%at-0.8 V_(RHE)for the electrochemical conversion of CO_(2)to *** work demonstrates that the spontaneously formed binary phases with desirable lattice strain can increase the activity of bismuth catalysts to the CO_(2)reduction reaction;such a strategy can be applicable in design of various electrocatalysts.

关键词： bismuth carbon dioxide reduction formic acid heterointerfaces strain

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Recent advances in functional utilisation of environmentally friendly and recyclable high-performance green biocomposites: A review

引用

Chinese Chemical Letters 2024年第4期35卷 73-85页

作者： Guiyang Zheng Xuelian Kang Haoran Ye Wei Fan Christian Sonne Su Shiung lam Rock Keey Liew Changlei Xia Yang Shi Shengbo Ge Co-innovation Center of Efficient Processing and Utilization of Forest Resources College of Materials Science and EngineeringNanjing Forestry UniversityNanjing 210037China School of Textile Science and Engineering&Key Laboratory of Functional Textile Material and Product of Ministry of Education Xi'an Polytechnic UniversityXi'an 710048China Department of Bioscience Arctic Research Centre(ARC)Aarhus UniversityFrederiksborgvej 399PO Box 358DK-4000 RoskildeDenmark Sustainability Cluster School of EngineeringUniversity of Petroleum&Energy StudiesDehradunUttarakhand 248007India Higher institution Centre of Excellence(HiCoE) Institute of Tropical Aquaculture and Fisheries(AKUATROP)Universiti Malaysia Terengganu21030 Kuala NerusTerengganuMalaysia Center for Transdisciplinary Research Saveetha Institute of Medical and Technical SciencesSaveetha UniversityChennai 600072India NV Western PLT Georgetown 10400PenangMalaysia Aerospace Kaitian Environmental Technology Co. Ltd.Changsha 410000China Hunan Hongsen Novel Material Technology Co. Ltd.Yiyang 413407China

Humans have relied on biomass for survival and development since the Stone Age. All aspects of human needs for materials are covered by tools, fuel, and buildings. Nowadays, metals and petroleum-based materials are widely used in highly developed industries. Unfortunately, environmental contamination and the loss of natural resources have led to the reemergence of biomass resources as efficient and sustainable energy sources. Notably, simple and direct applications can no longer meet the demand for functionalization, high performance of materials and construction materials. Therefore, it is imperative to modify biomass and combine its utilisation to produce functionalization and high performance materials. For example, construction materials with superior mechanical properties and water resistance can be produced by reinforcing fibres to facilitate crosslinking. Water-oil separation or adsorption effects of hydrogels and aerogels are determined by the porosity and lightness of biomass, biocomposite conductor is prepared by chimaeric conductive material. Here, we review the approaches that have been taken to devise an environmentally friendly yet fully recyclable and sustainable functionalised biocomposites from biomass and its potential directions for future research.

关键词： Biocomposite Renewable Sustainability Advanced functional material Pollution mitigation

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

On the use of deep learning for phase recovery

引用

Light(Science & Applications) 2024年第2期13卷 190-235页

作者： Kaiqiang Wang Li Song Chutian Wang Zhenbo Ren Guangyuan Zhao Jiazhen Dou Jianglei Di George Barbastathis Renjie Zhou Jianlin Zhao Edmund Y.lam Department of Electrical and Electronic Engineering The University of Hong KongHong Kong SARChina School of Physical Science and Technology Northwestern Polytechnical UniversityXi’anChina Department of Biomedical Engineering The Chinese University of Hong KongHong Kong SARChina School of information Engineering Guangdong University of TechnologyGuangzhouChina Department of Mechanical Engineering Massachusetts Institute of TechnologyCambridgeMAUSA

Phase recovery(PR)refers to calculating the phase of the light field from its intensity *** exemplified from quantitative phase imaging and coherent diffraction imaging to adaptive optics,PR is essential for reconstructing the refractive index distribution or topography of an object and correcting the aberration of an imaging *** recent years,deep learning(DL),often implemented through deep neural networks,has provided unprecedented support for computational imaging,leading to more efficient solutions for various PR *** this review,we first briefly introduce conventional methods for ***,we review how DL provides support for PR from the following three stages,namely,pre-processing,in-processing,and *** also review how DL is used in phase image ***,we summarize the work in DL for PR and provide an outlook on how to better use DL to improve the reliability and efficiency of ***,we present a live-updating resource(https://***/kqwang/phase-recovery)for readers to learn more about PR.

关键词： networks phase optics

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Protect the oceans from Japan's radioisotope dumping

引用

Environmental Science and Ecotechnology 2024年第4期20卷 16-17页

作者： Chengjun Li Huan Zhong Lingyu Meng Mengjie Wu Wenjing Ning Su Shiung lam Jun Luo Christian Sonne institute of Environmental Research at Greater Bay Area Guangzhou UniversityGuangzhou 510006China School of Environment Nanjing UniversityNanjingChina Department of Civil Engineering Nagoya Institute of TechnologyJapan Key Laboratory of Soil Environment and Pollution Remediation Institute of Soil ScienceChinese Academy of SciencesNanjingChina Universiti Malaysia Terengganu TerengganuMalaysia Center for Global Health Research(CGHR) Saveetha Institute of Medical and Technical Sciences(SIMATS)Saveetha UniversityChennaiIndia Aarhus University RoskildeDenmark Sustainability Cluster School of EngineeringUniversity of Petroleum&Energy StudiesDehradunUttarakhandIndia

in August 2023,Japan started to dump its 1.3 million tons of radioactive wastewater into the oceans[1,2].Most radioisotopes are claimed to be removed from the wastewater except tritium,which needs further dilution before ***,this dilution does not effectively remove any tritium from the wastewater but serves as a measure to bring its abnormally high concentration down to meet emission *** most worrisome situation is that many more bioaccumulative long-lived radioisotopes(BLLRs),such as carbon-14 and cobalt-60,slip through the treatment *** are attempts to reduce the concentrations of BLLRs via repurification to meet the regulatory standards[3];however,even low levels of these BLLRs can undergo biomagnification of up to 50,000 folds in marine fish species[4].

关键词： wastewater Japan removed

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Nutritional Assessment Tools for Patients with Cancer:A Narrative Review

引用

Current Medical Science 2024年第1期44卷 71-80页

作者： Peng-peng WANG Kim lam Soh Huzwah binti Khazaai Chuan-yi NiNG Xue-ling HUANG Jia-xiang YU Jin-lian LiAO Faculty of Medicine and Health Sciences Universiti Putra MalaysiaSerdang 43400Malaysia NursingCollege of Guangxi Medical University Nanning 530021China Department of Biomedical Sciences Universiti Putra MalaysiaSerdang 43400Malaysia Department of Nursing The First Affiliated Hospital of Guangxi Medical UniversityNanning 530021China

Cancer patients are at high risk of malnutrition,which can lead to adverse health outcomes such as prolonged hospitalization,increased complications,and increased *** and timely nutritional assessment plays a critical role in effectively managing malnutrition in these ***,while many tools exist to assess malnutrition,there is no universally accepted *** different tools have their own strengths and limitations,there is a lack of narrative reviews on nutritional assessment tools for cancer *** address this knowledge gap,we conducted a non-systematic literature search using PubMed,Embase,Web of Science,and the Cochrane Library from their inception until May 2023.A total of 90 studies met our selection criteria and were included in our narrative *** evaluated the applications,strengths,and limitations of 4 commonly used nutritional assessment tools for cancer patients:the Subjective Global Assessment(SGA),Patient-Generated Subjective Global Assessment(PG-SGA),Mini Nutritional Assessment(MNA),and Global Leadership initiative on Malnutrition(GLiM).Our findings revealed that malnutrition was associated with adverse health *** of these 4 tools has its applications,strengths,and *** findings provide medical staff with a foundation for choosing the optimal tool to rapidly and accurately assess malnutrition in cancer *** is essential for medical staff to be familiar with these common tools to ensure effective nutritional management of cancer patients.

关键词： cancer malnutrition nutrition nutritional assessment tool

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Thrombotic Thrombocytopenic Purpura in Pregnancy Presented with Stroke at 29 Weeks: A Case Report

引用

Open Journal of Obstetrics and Gynecology 2024年第3期14卷 359-364页

作者： Shamsa Kassam Jodie lam Gabrielle Baptiste Department of Women’s Health Luton and Dunstable University Hospital Bedfordshire Hospitals NHS Foundation Trust Luton UK

Thrombotic thrombocytopenic purpura (TTP) is a rare but acute, life-threatening condition which may be precipitated by pregnancy. This disorder that presents with thrombocytopenia, haemolytic anemia, and clinical consequences of microvascular thrombosis such as stroke. The exact cause is not known but it is associated with a deficiency of ADAMTS13 enzymes. immune mediated TTP is more common and can present in pregnancy. The aim of this case is to bring awareness as many clinicians are unaware of this condition in pregnancy, its diagnosis may be missed or delayed, leading to fetal loss or serious maternal implications. in this case the patient presented at 29 weeks with stroke in Emergency department, referred to delivery suit for Obstetric review, with suspicion of Pre-eclampsia/HELLP. The diagnosis of TTP was achieved by a multidisciplinary team who worked tirelessly together. The patient was transferred to a Specialist Tertiary Care Centre for further management. The pregnancy continued until 33 weeks and 5 days. She underwent an emergency caesarean section for fetal distress. Steroids and Rituximab were continued postnatally. The outcome was favourable due to fast and efficient multidisciplinary care. Awareness of this rare but important condition can lead to recognition of clinical presentation, prompt diagnosis and appropriate management.

关键词： Thrombotic Thrombocytopenic Purpura Pregnancy ischemic Stroke Caesarean Section

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

ARGA-Unet:Advanced U-net segmentation model using residual grouped convolution and attention mechanism for brain tumor MRi image segmentation

引用

虚拟现实与智能硬件（中英文） 2024年第3期6卷 203-216页

作者： Siyi XUN Yan ZHANG Sixu DUAN Mingwei WANG Jiangang CHEN Tong TONG Qinquan GAO Chantong lam Menghan HU Tao TAN Faculty of Applied Sciences Macao Polytechnic UniversityMacao 999078China Jinan Branch of China Telecom Co.Ltd. Jinan 250000China School of Physics and Electronics Shandong Normal UniversityJinan 250000China Department of Dardiovascular Medicine Affiliated Hospital of Hangzhou Normal UniversityHangzhou 310000China Clinical School of Medicine Hangzhou Normal UniversityHangzhou 310000China Hangzhou institute of Cardiovascular Diseases Hangzhou 310000China Shanghai Key Laboratory of Multidimensional information Processing Shanghai 200000China School of Communication&Electronic Engineering East China Normal UniversityShanghai 200000China Engineering Research Center of Traditional Chinese Medicine intelligent Rehabilitation Ministry of EducationShanghai 200000China College of Physics and information Engineering Fuzhou UniversityFuzhou 350000China

Background Magnetic resonance imaging(MRi)has played an important role in the rapid growth of medical imaging diagnostic technology,especially in the diagnosis and treatment of brain tumors owing to its non invasive characteristics and superior soft tissue ***,brain tumors are characterized by high non uniformity and non-obvious boundaries in MRi images because of their invasive and highly heterogeneous *** addition,the labeling of tumor areas is time-consuming and *** To address these issues,this study uses a residual grouped convolution module,convolutional block attention module,and bilinear interpolation upsampling method to improve the classical segmentation network *** influence of network normalization,loss function,and network depth on segmentation performance is further *** in the experiments,the Dice score of the proposed segmentation model reached 97.581%,which is 12.438%higher than that of traditional U-net,demonstrating the effective segmentation of MRi brain tumor *** in conclusion,we use the improved U-net network to achieve a good segmentation effect of brain tumor MRi images.

关键词： Brain tumor MRi U-net Segmentation Attention mechanism Deep learning

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

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：