检索结果-南通市图书馆

semantic segmentation of Lumbar vertebrae Using Meijering U-Net(MU-Net)on spine Magnetic Resonance Images

在线全文

学校读者我要写书评

暂无评论

Computer Modeling in Engineering & sciences 2025年第1期142卷 733-757页

作者： Lakshmi s v v shiloah Elizabeth Darmanayagam sunil Retmin Raj Cyril Department of Computer science and Engineering College of Engineering GuindyAnna UniversityChennai600025India Department of Information technology Madras Institute of TechnologyAnna UniversityChrompetChennai600044India

Lower back pain is one of the most common medical problems in the world and it is experienced by a huge percentage of people *** to its ability to produce a detailed view of the soft tissues,including the spinal cord,nerves,intervertebral discs,and vertebrae,Magnetic Resonance Imaging is thought to be the most effective method for imaging the *** semantic segmentation of vertebrae plays a major role in the diagnostic process of lumbar *** is difficult to semantically partition the vertebrae in Magnetic Resonance Images from the surrounding variety of tissues,including muscles,ligaments,and intervertebral discs.U-Net is a powerful deep-learning architecture to handle the challenges of medical image analysis tasks and achieves high segmentation *** work proposes a modified U-Net architecture namely MU-Net,consisting of the Meijering convolutional layer that incorporates the Meijering filter to perform the semantic segmentation of lumbar vertebrae L1 to L5 and sacral vertebra ***-colour mask images were generated and used as ground truth for training the *** work has been carried out on 1312 images expanded from t1-weighted mid-sagittal MRI images of 515 patients in the Lumbar spine MRI Dataset publicly available from Mendeley *** proposed MU-Net model for the semantic segmentation of the lumbar vertebrae gives better performance with 98.79%of pixel accuracy(PA),98.66%of dice similarity coefficient(DsC),97.36%of Jaccard coefficient,and 92.55%mean Intersection over Union(mean IoU)metrics using the mentioned dataset.

关键词： Computer aided diagnosis(CAD) magnetic resonance imaging(MRI) semantic segmentation lumbar vertebrae deep learning U-Net model

Detection of Fuel Adulteration Using Wave Optical with Machine Learning Algorithms

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

Computer systems science & Engineering 2022年第4期41卷 19-33页

作者： s.Dilip Kumar t.v.sivasubramonia pillai Department of Instrumentation and Control Engineering Sri Krishna College of TechnologyCoimbatore641105TamilnaduIndia Department of Physics University College of EngineeringNagercoil629004TamilnaduIndia

Fuel is a very important factor and has considerable inﬂuence on the air quality in the environment,which is the heart of the *** increase of vehi-cles in lived-in areas results in greater emission of carbon particles in the *** fuel causes more contaminated particles to mix with breathing air and becomes the main source of dangerous *** is the mixing of foreign substances in fuel,which damages vehicles and causes more health problems in living beings such as humans,birds,aquatic life,and even water resources by emitting high levels of hydrocarbons,nitrogen oxides,and carbon *** frequent blending liquids are lubricants and kerosene in the petrol,and its adulteration is a considerable problem that adds to environ-mental *** study focuses on detecting the adulteration in petrol using sensors and machine learning algorithms.A modiﬁed evanescent wave opticalﬁber sensor with discrete wavelet transform is proposed for classiﬁcation of adult-erated data from the ***,support vector machine classiﬁer is used for accurate *** sensor isﬁrst tested with fuel and numerical data is classiﬁed based on machine learning ***,the result is eval-uated with less error and high accuracy of 99.9%,which is higher than all existing techniques.

关键词： Petrol adulteration discrete wavelet transform modiﬁed evanescent wave opticalﬁber svM classiﬁer

Drilling study on lightweight structural Mg/siC composite for defence applications

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

Defence technology（防务技术） 2019年第4期15卷 557-564页

作者： K. Balamurugan M. Uthayakumar s. thirumalai Kumaran G.s. samy U.t.s. pillai Department of Mechanical Engineering VFSTR (Deemed to be University) Guntur 522213 India Faculty of Mechanical Engineering Kalasalingam University Krishnankoil 626126 Tamil Nadu India CsIR-NIIst Material Science and Technology Division Thiruvananthapuram 695019 India

Heat energy generated during machining has been found to have a greater influence on determining the machinability of the *** this work,magnesium-based silicon carbide composite,which has been identified as a suitable lightweight application material,is prepared with the weight ratio of 90:10 by a stir casting *** available Hss drill tools with different diameters of 4,6 and 8 mm are used to perform the drilling operations with governing parameters of spindle speed,feed rate and constant depth of *** image camera of the FLIR E60 series is used to measure the temperature variation in the cutting zone at different operating *** influences of machining temperature on chip morphology,tool wear and surface profile of the machined samples are *** speed has been found to have a significant effect on machining *** spindle speed increases,the diameter of drill tool increases the tool wear and surface profile,*** abrasion and adhesive type of wears are observed in the drill ***,change from abrasion to adhesive wear is noticed with the increase of the diameter of the drill *** plots are drawn with respect to the interaction of governing parameters along with the working temperatures obtained under different machining conditions.

关键词： Magnesium siC Drilling thermal effect Chip morphology tool wear

Physical,Mechanical,and tribological Attributes of stir-Cast AZ91/siC_p Composite

在线全文

学校读者我要写书评

暂无评论

Acta Metallurgica sinica(English Letters) 2014年第2期27卷 295-305页

作者： K.K.Ajith Kumar Abhilash viswanath t.P.D.Rajan U.t.s.pillai B.C.Pai Material science and technology Division CSIR-National Institute for Interdisciplinary Science and Technology

In the present investigation, composites with silicon carbide particle （siCp） as reinforcement and AZ91 magnesium alloy as matrix have been synthesized using liquid metal stir-casting technique with optimized processing conditions. the composites with good particle distribution in the matrix, and better grain refinement and good interfacial bonding between the matrix and reinforcement have been obtained. the effect of siCp content on the physical, mechanical, and tribological properties of Mg-based metal matrix composite （MMC） is studied with respect to particle distribution, grain refinement, and particle/matrix interfacial reactions. the electrical conductivity, coefficient of thermal expansion, microas well as macro-hardness, tensile and compressive properties, and the fracture behavior of the composites along with dry sliding wear of the composites have been evaluated and compared with the base alloy.

关键词： Composite AZ91D alloy Casting alloy Mechanical properties Wear

Microstructural image based convolutional neural networks for efficient prediction of full-field stress maps in short fiber polymer composites

在线全文

学校读者我要写书评

暂无评论

Defence technology（防务技术） 2023年第6期24卷 58-82页

作者： s.Gupta t.Mukhopadhyay v.Kushvaha Department of Civil Engineering Indian Institute of Technology JammuJ&KIndia Department of Aerospace Engineering Indian Institute of Technology KanpurUPIndia

the increased demand for superior materials has highlighted the need of investigating the mechanical properties of composites to achieve enhanced constitutive ***-reinforced polymer composites have emerged as an integral part of materials development with tailored mechanical ***,the complexity and heterogeneity of such composites make it considerably more challenging to have precise quantification of properties and attain an optimal design of structures through experimental and computational *** order to avoid the complex,cumbersome,and labor-intensive experimental and numerical modeling approaches,a machine learning(ML)model is proposed here such that it takes the microstructural image as input with a different range of Young’s modulus of carbon fibers and neat epoxy,and obtains output as visualization of the stress component s11(principal stress in the x-direction).For obtaining the training data of the ML model,a short carbon fiberfilled specimen under quasi-static tension is modeled based on 2D Representative Area Element(RAE)using finite element *** composite is inclusive of short carbon fibers with an aspect ratio of 7.5that are infilled in the epoxy systems at various random orientations and positions generated using the simple sequential Inhibition(ssI)*** study reveals that the pix2pix deep learning Convolutional Neural Network(CNN)model is robust enough to predict the stress fields in the composite for a given arrangement of short fibers filled in epoxy over the specified range of Young’s modulus with high *** CNN model achieves a correlation score of about 0.999 and L2 norm of less than 0.005 for a majority of the samples in the design spectrum,indicating excellent prediction *** this paper,we have focused on the stage-wise chronological development of the CNN model with optimized performance for predicting the full-field stress maps of the fiber-reinforced composite ***

关键词： Micromechanics of fiber-reinforced composites Machine learning assisted stress prediction Microstructural image-based machine learning CNN based stress analysis

Biodiversity and seasonal variation of benthic macrofauna in Minicoy Island, Lakshadweep,India

在线全文

学校读者我要写书评

暂无评论

Acta Oceanologica sinica 2014年第10期33卷 58-73页

作者： Dalia susan v satheesh Kumar P. pillai N. G. K Central Marine Fisheries Research Institute Kochi Kerala 682018 India

From the Indian coast only limited data are available on the benthic fauna of the seagrass communities. In this study, seasonal variation in the distribution of macrobenthos and influence of environmental parameters was explored at four seagrass beds and two mangrove stations along the Minicoy Island, Lakshadweep, India, from september 1999 to August 2001. A total of 160 macrobenthic species from eight major groups represented the macrofauna of the Minicoy Island. Of the identified taxa, molluscs 70（gastropods 41.46%, bivalves 7.5%）, polychaetes 27（16.88%）, crustaceans 30（18.75%）, echinoderms 11（6.88%） and remaining others. Average seasonal abundance of benthic macrofauna ranged from 219 to 711 ind./m2, species diversity varied from 1.45 to 3.64 bits per individual, species richness index ranged from 4.01 to 26.17, evenness 0.69 to 1.66. In general, the higher abundance and species diversity was noticed in southern seagrass stations and northern seagrass stations, but in the mangrove stations comparatively low species diversity was observed. three-way analysis of variance indicated that all communities resulted as being significantly different between seagrass and mangrove station, mainly when the seasonal interaction was considered. Multivariate analyses were employed to help define benthic characteristic and the relationship between environmental parameters at the six monitoring stations. Results of cluster analyses and multidimensional scale plot suggest that for mangrove region, different physiographic provinces, lower salinity, dissolved oxygen and sediment biotic structure have a higher influence on the species composition and diversity than other oceanographic conditions.

关键词： abundance seagrass macrobenthos mangrove Minicoy Island Lakshadweep

Influence of alkali metal doping on surface properties and catalytic activity/selectivity of CaO catalysts in oxidative coupling of methane

在线全文

学校读者我要写书评

暂无评论

Journal of Natural Gas Chemistry 2008年第4期17卷 313-320页

作者： v.H.Rane s.t.Chaudhari v.R.Choudhary Chemical Engineering and Process Development Division National Chemical Laboratory

surface properties （viz. surface area, basicity/base strength distribution, and crystal phases） of alkali metal doped CaO （alkali metal/Ca= 0.1 and 0.4） catalysts and their catalytic activity/selectivity in oxidative coupling of methane （OCM） to higher hydrocarbons at different reaction conditions （viz. temperature, 700 and 750 ℃; CH4/O2 ratio, 4.0 and 8.0 and space velocity, 5140-20550 cm^3 ·g^-1·h^-1） have been investigated. the influence of catalyst calcination temperature on the activity/selectivity has also been investigated. the surface properties （viz. surface area, basicity/base strength distribution） and catalytic activity/selectivity of the alkali metal doped CaO catalysts are strongly influenced by the alkali metal promoter and its concentration in the alkali metal doped CaO catalysts. An addition of alkali metal promoter to CaO results in a large decrease in the surface area but a large increase in the surface basicity （strong basic sites） and the C2＋ selectivity and yield of the catalysts in the OCM process. the activity and selectivity are strongly influenced by the catalyst calcination temperature. No direct relationship between surface basicity and catalytic activity/selectivity has been observed. Among the alkali metal doped CaO catalysts, Na-CaO （Na/Ca = 0.1, before calcination） catalyst （calcined at 750 ℃）, showed best performance （C2＋ selectivity of 68.8% with 24.7% methane conversion）, whereas the poorest performance was shown by the Rb-CaO catalyst in the OCM process.

关键词： oxidative coupling of methane alkali metal doped CaO catalysts basicity/base strength distribution catalytic activity/selectivity

Facile In situ Fabrication of Nanostructured Graphene–CuO Hybrid with Hydrogen sulfide Removal Capacity

在线全文

学校读者我要写书评

暂无评论

Nano-Micro Letters 2016年第4期8卷 312-319页

作者： sunil P.Lonkar vishnu v.pillai samuel stephen Ahmed Abdala vikas Mittal Department of Chemical Engineering The Petroleum Institute

A simple and scalable synthetic approach for one-step synthesis of graphene–Cu O(tRGC) nanocomposite by an in situ thermo-annealing method has been *** graphene oxide(GO) and copper hydroxide as a precursors reagent,the reduction of GO and the uniform deposition of in situ formed Cu O nanoparticles on graphene was simultaneously *** method employed no solvents,toxic-reducing agents,or organic *** resulting nanostructured hybrid exhibited improved H2 s sorption capacity of 1.5 mmol H2s/g-sorbent(3 g s/100 g-sorbent).Due to its highly dispersed sub-20 nm Cu O nanoparticles and large specific surface area,tRGC nanocomposite exhibits tremendous potential for energy and environment applications.

关键词： CuO/graphene Adsorption Breakthrough capacity Hydrogen sulfide thermal stability In situ synthesis

Effect of chlorine doping on the structural, morphological, optical and electrical properties of spray deposited Cds thin films

在线全文

学校读者我要写书评

暂无评论

Progress in Natural science:Materials International 2015年第5期25卷 392-398页

作者： t.sivaraman v.Narasimman v.s.Nagarethinam A.R.Balu PG and Research Department of Physics A.V.V.M Sri Pushpam College

Cds and chlorine doped Cds(Cds:Cl) thin films with different Cl-doping levels(0,2,4,6 and 8 at%) have been deposited on glass substrates by a spray pyrolysis technique using a perfume *** effect of Cl doping on the structural,morphological,optical and electrical properties of the films was *** patterns revealed that all the films exhibit hexagonal crystal structure with a preferential orientation along the(0 0 2) plane irrespective of the Cl doping *** particle size value decreases from 22.03 nm to 18.12 nm with increase in Cl *** band gap is blue-shifted from 2.48 ev to 2.73 ev with increase in Cl doping *** the films have resistivity in the order of 10～4 Ω *** obtained results confirm that chlorine as an anionic dopant material can enhance the physical properties of Cds thin films to a large extent.

关键词： X-ray diffraction Crystal structure Preferential orientation thin films Optical band gap