检索结果-南通市图书馆

Three-Stage Transfer Learning with AlexNet50 for MRI Image Multi-Class Classification with Optimal Learning Rate

Computer Modeling in Engineering & Sciences 2025年第1期142卷 155-183页

作者： Suganya Athisayamani A.Robert singh Gyanendra Prasad Joshi Woong Cho School of Computing Sastra Deemed to be UniversityThanjavur613401India Department of Computational Intelligence SRM Institute of Science and TechnologyKattankulathur603203India Department of AI and Software Engineering Kangwon National UniversitySamcheok25913Republic of Korea Department of Electronics Information and Communication EngineeringKangwon National UniversitySamcheok25913Republic of Korea

In radiology,magnetic resonance imaging(MRI)is an essential diagnostic tool that provides detailed images of a patient’s anatomical and physiological *** is particularly effective for detecting soft tissue ***,radiologists manually interpret these images,which can be labor-intensive and time-consuming due to the vast amount of *** address this challenge,machine learning,and deep learning approaches can be utilized to improve the accuracy and efficiency of anomaly detection in MRI *** manuscript presents the use of the Deep AlexNet50 model for MRI classification with discriminative learning *** are three stages for learning;in the first stage,the whole dataset is used to learn the *** the second stage,some layers of AlexNet50 are frozen with an augmented dataset,and in the third stage,AlexNet50 with an augmented dataset with the augmented *** method used three publicly available MRI classification datasets:Harvard whole brain atlas(HWBA-dataset),the School of Biomedical Engineering of Southern Medical University(SMU-dataset),and The National Institute of Neuroscience and Hospitals brain MRI dataset(NINS-dataset)for *** hyperparameter optimizers like Adam,stochastic gradient descent(SGD),Root mean square propagation(RMS prop),Adamax,and AdamW have been used to compare the performance of the learning ***-dataset registers maximum classification *** evaluated the performance of the proposed classification model using several quantitative metrics,achieving an average accuracy of 98%.

关键词： MRI tumors classification AlexNet50 transfer learning hyperparameter tuning optimizer

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

Multi-Scale Dilated Convolution Network for SPECT-MPI Cardiovascular Disease Classification with Adaptive Denoising and Attenuation Correction

引用

Computer Modeling in Engineering & Sciences 2025年第1期142卷 299-327页

作者： A.Robert singh Suganya Athisayamani Gyanendra Prasad Joshi Bhanu Shrestha Department of Computational Intelligence SRM Institute of Science and TechnologyKattankulathur603203Tamil NaduIndia School of Computing Sastra Deemed to be UniversityThanjavur613401Tamil NaduIndia Department of Artificial Intelligence&Software Kangwon National UniversitySamcheok25913Republic of Korea Department of Information Convergence System Graduate School of Smart ConvergenceKwangwoon UniversitySeoul01897Republic of Korea

Myocardial perfusion imaging(MPI),which uses single-photon emission computed tomography(SPECT),is a well-known estimating tool for medical diagnosis,employing the classification of images to show situations in coronary artery disease(CAD).The automatic classification of SPECT images for different techniques has achieved near-optimal accuracy when using convolutional neural networks(CNNs).This paper uses a SPECT classification framework with three steps:1)Image denoising,2)Attenuation correction,and 3)Image *** denoising is done by a U-Net architecture that ensures effective image *** correction is implemented by a convolution neural network model that can remove the attenuation that affects the feature extraction process of ***,a novel multi-scale diluted convolution(MSDC)network is *** merges the features extracted in different scales and makes the model learn the features more *** scales of filters with size 3×3 are used to extract *** three steps are compared with state-of-the-art *** proposed denoising architecture ensures a high-quality image with the highest peak signal-to-noise ratio(PSNR)value of *** proposed classification method is compared with the five different CNN models,and the proposed method ensures better classification with an accuracy of 96%,precision of 87%,sensitivity of 87%,specificity of 89%,and F1-score of 87%.To demonstrate the importance of preprocessing,the classification model was analyzed without denoising and attenuation correction.

关键词： SPECT-MPI CAD MSDC denoising attenuation correction classification

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

A comprehensive investigation on nonlinear vibration and bending characteristics of bio-inspired helicoidal laminated composite structures

引用

Applied Mathematics and Mechanics(English Edition) 2025年第1期46卷 81-100页

作者： S.SAURABH R.KIRAN D.singh R.VAISH V.S.CHAUHAN School of Mechanical and Materials Engineering Indian Institute of Technology Mandi

Bio-inspired helicoidal composite laminates, inspired by the intricate helical structures found in nature, present a promising frontier for enhancing the mechanical properties of structural designs. Hence, this study provides a comprehensive investigation into the nonlinear free vibration and nonlinear bending behavior of bio-inspired composite plates. The inverse hyperbolic shear deformation theory(IHSDT) of plates is employed to characterize the displacement field, with the incorporation of Green-Lagrange nonlinearity. The problem is modeled using the C0finite element method(FEM), and an in-house code is developed in the MATLAB environment to solve it numerically. Various helicoidal layup configurations including helicoidal recursive(HR), helicoidal exponential(HE), helicoidal semi-circular(HS), linear helicoidal(LH), and Fibonacci helicoidal(FH)with different layup sequences and quasi-isotropic configurations are studied. The model is validated, and parametric studies are conducted. These studies investigate the effects of layup configurations, side-to-thickness ratio, modulus ratios, boundary conditions, and loading conditions at different load amplitudes on the nonlinear vibration and nonlinear bending behaviors of bio-inspired composite plates. The results show that the laminate sequence exerts a substantial impact on both nonlinear natural frequencies and nonlinear bending behaviors. Moreover, this influence varies across different side-to-thickness ratios and boundary conditions of the bio-inspired composite plate.

关键词： Inverse problems

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Thermo-mechanical and tribological properties of SU-8/h-BN composite with SN150/perfluoropolyether filler

引用

Friction 2020年第1期8卷 151-163页

作者： Anand singh RATHAUR Jitendra KKATIYAR vinay Kumar PATEL Department of Mechanical Engineering Govind Ballabh Pant Institute of Engineering and Technology GhurdauriPauri GarhwalUttarakhand 246194India Department of Mechanical Engineering SRM Institute of Science and TechnologyKattankulathur CampusChennaiTamil Nadu 603203India

In this study, SU-8 and its composites are fabricated by blending 10 wt.% hexagonal boron nitride(h-BN) fillers with/without lubricants, such as 10 wt.% base oil(SN150) and 20 wt.% perfluoropolyether(PFPE). The thickness of SU-8 and its composites coating is fabricated in the range ~100–105 μm. Further, SU-8 and its composites are characterized by a 3D optical profilometer, atomic force microscopy, scanning electron microscopy, a thermal gravimetric analyzer, a goniometer, a hardness tester, and an optical microscope. Under a tribology test performed at different normal loads of 2, 4, and 6 N and at a constant sliding speed of 0.28 m/s, the reduction in the initial and steady-state coefficient of friction is obtained to be ~0.08 and ~0.098, respectively, in comparison to SU-8(~0.42 and ~0.75), and the wear resistance is enhanced by more than 103 times that of pure SU-8. Moreover, the thermal stability is improved by ~80–120 ℃, and the hardness and elastic modulus by ~3 and ~2 times that of pure SU-8, respectively. The SU-8 composite reinforced with 10 wt.% h-BN and 20 wt.% PFPE demonstrated the best thermo-mechanical and tribological properties with a nano-textured surface of high hydrophobicity.

关键词： SU‐8 boron nitride perfluoropolyether(PFPE) base oil(SN 150) in‐situ lubrication

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

An analysis of energy consumption and carbon footprints of cryptocurrencies and possible solutions

引用

Digital Communications and Networks 2023年第1期9卷 79-89页

作者： Varun Kohli Sombuddha Chakravarty vinay Chamola Kuldip singh Sangwan Sherali Zeadally Department of Electrical and Computer Engineering Engineering National University of SingaporeSingapore Department of Electrical and Electronics Engineering&APPCAIR BITS-PilaniPilani Campus333031India Department of Mechanical Engineering BITS-PilaniPilani Campus333031India College of Communication and Information University of KentuckyLexingtonKY40506-0224USA

There is an urgent need to control global warming caused by humans to achieve a sustainable ***_(2) levels are rising steadily,and while countries worldwide are actively moving toward the sustainability goals proposed during the Paris Agreement in 2015,we are still a long way to go from achieving a sustainable mode of global *** increased popularity of cryptocurrencies since the introduction of Bitcoin in 2009 has been accompanied by an increasing trend in greenhouse gas emissions and high electrical energy *** energy tracking studies(e.g.,Digiconomist and the Cambridge Bitcoin Energy Consumption Index(CBECI))have estimated energy consumption ranges from 29.96 TWh to 135.12 TWh and 26.41 TWh to 176.98 TWh,respectively for Bitcoin as of July 2021,which are equivalent to the energy consumption of countries such as Sweden and *** latest estimate by Digiconomist on carbon footprints shows a 64.18 MtCO_(2) emission by Bitcoin as of July 2021,close to the emissions by Greece and *** review compiles estimates made by various studies from 2018 to *** compare the energy consumption and carbon footprints of these cryptocurrencies with countries around the world and centralized transaction methods such as *** identify the problems associated with cryptocurrencies and propose solutions that can help reduce their energy consumption and carbon ***,we present case studies on cryptocurrency networks,namely,Ethereum 2.0 and Pi Network,with a discussion on how they can solve some of the challenges we have identified.

关键词： Blockchain Carbon footprint Climate change Cryptocurrency Sustainability

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 Comprehensive Survey on Federated Learning Applications in Computational Mental Healthcare

引用

Computer Modeling in Engineering & Sciences 2025年第1期142卷 49-90页

作者： Vajratiya Vajrobol Geetika Jain Saxena Amit Pundir Sanjeev singh Akshat Gaurav Savi Bansal Razaz Waheeb Attar Mosiur Rahman Brij B.Gupta Institute of Informatics and Communication University of DelhiDelhi110021India Maharaja Agrasen College University of DelhiDelhi110096India Computer Engineering Ronin InstituteMontclairNJ 07043USA Department of Research and Innovation Insights2TechinfoJaipur302001India University Centre for Research and Development(UCRD) Chandigarh UniversityChandigarh140413India Management Department College of Business AdministrationPrincess Nourah bint Abdulrahman UniversityRiyadh11671Saudi Arabia CCRI&Department of Computer Science and Information Engineering Asia UniversityTaichung413Taiwan Symbiosis Centre for Information Technology(SCIT) Symbiosis International UniversityPune411057India Center for Interdisciplinary Research University of Petroleum and Energy Studies(UPES)Dehradun248007India

Mental health is a significant issue worldwide,and the utilization of technology to assist mental health has seen a growing *** aims to alleviate the workload on healthcare professionals and aid *** applications have been developed to support the challenges in intelligent healthcare ***,because mental health data is sensitive,privacy concerns have *** learning has gotten some *** research reviews the studies on federated learning and mental health related to solving the issue of intelligent healthcare *** explores various dimensions of federated learning in mental health,such as datasets(their types and sources),applications categorized based on mental health symptoms,federated mental health frameworks,federated machine learning,federated deep learning,and the benefits of federated learning in mental health *** research conducts surveys to evaluate the current state of mental health applications,mainly focusing on the role of Federated Learning(FL)and related privacy and data security *** survey provides valuable insights into how these applications are emerging and evolving,specifically emphasizing FL’s impact.

关键词： Depression emotional recognition intelligent healthcare systems mental health federated learning stress detection sleep behaviour

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

Genome recoding strategies to improve cellular properties: mechanisms and advances

引用

aBIOTECH 2021年第1期2卷 79-95页

作者： Tanya singh Sudesh Kumar Yadav Alexander Vainstein vinay Kumar Department of Botany School of Basic SciencesCentral University of PunjabBathinda 151001India Center of Innovative and Applied Biotechnology Mohali 140306India Institute of Plant Sciences and Genetics in Agriculture The Hebrew University of JerusalemRehovotIsrael

The genetic code,once believed to be universal and immutable,is now known to contain many variations and is not quite *** basis for genome recoding strategy is genetic code variation that can be harnessed to improve cellular ***,genome recoding is a promising strategy for the enhancement of genome flexibility,allowing for novel functions that are not commonly documented in the organism in its natural ***,the basic concept of genetic code and associated mechanisms for the generation of genetic codon variants,including biased codon usage,codon reassignment,and ambiguous decoding,are extensively *** of the concept of natural genetic code expansion is also *** generation of recoded organisms and associated mechanisms with basic targeting components,including aminoacyl-tRNA synthetase–tRNA pairs,elongation factor EF-Tu and ribosomes,are highlighted for a comprehensive understanding of this *** research associated with the generation of diverse recoded organisms is also *** success of genome recoding in diverse multicellular organisms offers a platform for expanding protein chemistry at the biochemical level with non-canonical amino acids,genetically isolating the synthetic organisms from the natural ones,and fighting viruses,including SARS-CoV2,through the creation of attenuated *** conclusion,genome recoding can offer diverse applications for improving cellular properties in the genome-recoded organisms.

关键词： Genetic code Codon usage Protein engineering Attenuated virus

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

Synthetic data as an investigative tool in hypertension and renal diseases research

引用

World Journal of Methodology 2025年第1期15卷 9-13页

作者： Aleena Jamal Som singh Fawad Qureshi Sidney Kimmel Medical College Thomas Jefferson UniversityPhiladelphiaPA 19107United States School of Medicine University of Missouri Kansas CityKansasMO 64106United States Division of Nephrology and Hypertension Mayo ClinicRochesterMN 55905United States

There is a growing body of clinical research on the utility of synthetic data derivatives,an emerging research tool in *** nephrology,clinicians can use machine learning and artificial intelligence as powerful aids in their clinical decision-making while also preserving patient *** is especially important given the epidemiology of chronic kidney disease,renal oncology,and hypertension ***,there remains a need to create a framework for guidance regarding how to better utilize synthetic data as a practical application in this research.

关键词： Synthetic data Artificial intelligence Nephrology Blood pressure Research Editorial

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

System Identification of Heritage Structures Through AVT and OMA:A Review

引用

Structural Durability & Health Monitoring 2019年第1期13卷 1-40页

作者： vinay Shimpi Madappa V.R.Sivasubramanian S.B.singh Department of Civil Engineering National Institute of Technology PuducherryKaraikal609609India Department of Civil Engineering Birla Institute of Technology and Science PilaniPilani333031India

In this review article,the past investigations carried out on heritage structures using Ambient Vibration Test(AVT)and Operational Modal Analysis(OMA)for system identification(determination of dynamic properties like frequency,mode shape and damping ratios)and associated applications are summarized.A total of 68 major research studies on heritage structures around the world that are available in literature are surveyed for this *** first,field investigations carried out on heritage structures prior to conducting AVT are explained in ***,specifications of accelerometers,location of accelerometers and optimization of accelerometer networks have been elaborated with respect to the geometry of the heritage *** addition to this,ambient vibration loads and data acquisition procedures are also ***,the state of art of performing OMA techniques for heritage structures is explained ***,various applications of system identification for heritage structures are ***,conclusions are made towards errorless system identification of heritage structures through AVT and OMA.

关键词： Ambient Vibration Test(AVT) heritage structures Operational Modal Analysis(OMA) structural assessment system identification

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

Graphene derivatives as efficient hole transport materials for lead-free double perovskite（Cs2SnI6） solar cells: a numerical study

引用

Optoelectronics Letters 2025年第3期21卷 155-159页

作者： Sarita YADAV Saral K.GUPTA Chandra Mohan singh NEGI Department of Physical Science Banasthali Vidyapith

The double perovskite Cs2SnI6has notable optical and electrical characteristics, rendering it a highly prospective candidate for deployment as the absorber layer in perovskite solar cells （PSCs）. We simulated the performance of PSCs using lead-free Cs2SnI6double perovskite absorber layer and graphene derivatives, namely graphene oxide （GO） and reduced graphene oxide （rGO）, as hole transport layers （HTLs）. Our findings show that r GO offers an excellent hole extraction property with minimal interfacial recombination compared to GO.

关键词：

来源：

同方期刊数据库

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：