检索结果-南通市图书馆

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Genes & Diseases 2024年第3期11卷 66-68页

作者： Aswathi N Jincy M.Jose Sreelata B.Nair prabha S.N pappachan S Department of Medical Genetics Lifeline Super Specialty HospitalPathanamthittaKerala 691523India Lifeline Super Specialty Hospital PathanamthittaKerala 691523India

Alagille syndrome(ALGS;OMIM#118450)is a highlyvariable,multi-systemic,autosomal dominant disorder,caused by mutations in the Jagged Canonical Notch Ligand 1(JAG1)gene(20p12.2)or in the Neurogenic locus notch homolog protein 2(NOTCH2)gene(1p13).^(1)It primarily affects the liver,heart,eyes,face,kidney,skin,vertebrae,and skeleton.^(1,2)The JAG1 gene has 26 exons and about 90%of the ALGS cases result from pathogenic variants in the JAG1 and around 7%of cases have deletions in chromosome 20 that include this gene.

关键词： JAG1 cases Notch

Cephalopods Classification Using Fine Tuned Lightweight Transfer Learning Models

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Intelligent Automation & Soft Computing 2023年第3期35卷 3065-3079页

作者： p.Anantha prabha G.Suchitra R.Saravanan Department of Computer Science&Engineering Sri Krishna College of TechnologyCoimbatore641042Tamil NaduIndia Department of Electronics and Communication Engineering Government College of TechnologyCoimbatore641013Tamil NaduIndia Department of Marine pharmacology Faculty of Allied Health SciencesChettinad Academy of Research and EducationKelambakkamChengalpattu603103Tamil NaduIndia

Cephalopods identiﬁcation is a formidable task that involves hand inspection and close observation by a *** observation and iden-tiﬁcation take time and are always contingent on the involvement of experts.A system is proposed to alleviate this challenge that uses transfer learning techni-ques to classify the cephalopods *** the proposed method,only the Lightweight pre-trained networks are chosen to enable IoT in the task of cephalopod ***,the efﬁciency of the chosen models is determined by evaluating their performance and comparing theﬁ***,the models areﬁne-tuned by adding dense layers and tweaking hyperparameters to improve the classiﬁcation of *** models also employ a well-tuned Rectiﬁed Adam optimizer to increase the accuracy ***,Adam with Gradient Cen-tralisation(RAdamGC)is proposed and used inﬁne-tuned models to reduce the training *** framework enables an Internet of Things(IoT)or embedded device to perform the classiﬁcation tasks by embedding a suitable lightweight pre-trained ***ﬁne-tuned models,MobileNetV2,InceptionV3,and NASNet Mobile have achieved a classiﬁcation accuracy of 89.74%,87.12%,and 89.74%,***ﬁndings have indicated that theﬁne-tuned models can classify different kinds of *** results have also demonstrated that there is a signiﬁcant reduction in the training time with RAdamGC.

关键词： Cephalopods transfer learning lightweight models classiﬁcation deep learning ﬁsh IoT

Understand Students Feedback Using Bi-Integrated CRF Model Based Target Extraction

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2期40卷 735-747页

作者： K.Sangeetha D.prabha Department of Computer Science and Engineering Panimalar Engineering CollegeChennai600123India Department of Computer Science and Engineering Sri Krishna College of Engineering and TechnologyCoimbatore641008India

Educational institutions showing interest to find the opinion of the students about their course and the instructors to enhance the teaching-learning *** this,most research uses sentiment analysis to track students’*** sentence-level sentiment analysis focuses on the whole sentence *** studies show that the sentiments alone are not enough to observe the feeling of the students because different words express different sentiments in a *** is a need to extract the targets in a given sentence which helps to find the sentiment towards those *** extraction is the subtask of targeted sentiment *** this paper,we proposed the innovative model to find the targets of the given sentence using Bi-Integrated Conditional Random Fields(CRF).A parallel fusion neural network model is designed to perform this *** evaluate the model using the Michigan dataset and we build a dataset for target extraction from student *** experimental results show that our proposed fusion model achieves better results compared to baseline models.

关键词： Feedback sentimental analysis deeplearning integrated CRF

Complement of the reduced non-zero component graph of free semimodules

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Applied Mathematics(A Journal of Chinese Universities) 2023年第1期38卷 1-15页

作者： T.Tamizh Chelvam K.prabha Ananthi Department of Mathematics Manonmaniam Sundaranar UniversityTirunelveli 627012Tamil NaduIndia

Let M be a finitely generated free semimodule over a semiring S with identity having invariant basis number property with a basisα={α1,...,αk}.The complement■of the reduced non-zero component graph■of M,is the simple undirected graph with■as the vertex set and such that there is an edge between two distinct vertices■and■if and only if there exists no i such that both ai,biare *** this paper,we show that the graph■is connected and find its domination number,clique number and chromatic *** the case of finite semirings,we determine the degree of each vertex,order,size,vertex connectivity and girth of■.Also,we give a necessary and sufficient condition for■to be Eulerian or Hamiltonian or planar.

关键词： semiring modules planar

Ensemble Variable Selection for Naive Bayes to Improve Customer Behaviour Analysis

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

Computer Systems Science & Engineering 2022年第4期41卷 339-355页

作者： R.Siva Subramanian D.prabha Anna University Chennai600025India Department of Computer Science and Engineering Sri Krishna College of Engineering and TechnologyCoimbatore641008India

Executing customer analysis in a systemic way is one of the possible solutions for each enterprise to understand the behavior of consumer patterns in an efﬁcient and in-depth *** investigation of customer patterns helps theﬁrm to develop efﬁcient decisions and in turn,helps to optimize the enter-prise’s business and maximizes consumer satisfaction *** con-duct an effective assessment about the customers,Naive Bayes(also called Simple Bayes),a machine learning model is ***,the efﬁcacious of the simple Bayes model is utterly relying on the consumer data used,and the existence of uncertain and redundant attributes in the consumer data enables the simple Bayes model to attain the worst prediction in consumer data because of its presumption regarding the attributes ***,in practice,the NB pre-mise is not true in consumer data,and the analysis of these redundant attributes enables simple Bayes model to get poor prediction *** this work,an ensem-ble attribute selection methodology is performed to overcome the problem with consumer data and to pick a steady uncorrelated attribute set to model with the NB classiﬁ*** ensemble variable selection,two different strategies are applied:one is based upon data perturbation(or homogeneous ensemble,same feature selector is applied to a different subsamples derived from the same learning set)and the other one is based upon function perturbation(or heterogeneous ensemble different feature selector is utilized to the same learning set).Further-more,the feature set captured from both ensemble strategies is applied to NB indi-vidually and the outcome obtained is ***,the experimental outcomes show that the proposed ensemble strategies perform efﬁciently in choosing a steady attribute set and increasing NB classiﬁcation performance efﬁciently.

关键词： Naive bayes or simple bayes variable selection homogeneous ensemble heterogeneous ensemble customer prediction

Experimental,analytical and numerical studies on concrete encased trapezoidally web profiled cold-formed steel beams by varying depth-thickness ratio

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Structural and Civil Engineering 2020年第4期14卷 930-946页

作者： Divahar RAVI Aravind Raj pONSUBBIAH Sangeetha Sreekuniar prabha Joanna philip SARATHA Department of Civil Engineering Aarupadai Veedu Institute of TechnologyChennai 603104India Department of Civil Engineering Hindustan Institute of Technology and ScienceChennai 603103India

Concrete encased with trapezoidally corrugated web profiled cold-formed steel beams are used worldwide to improve resistance toward fire and corrosion,higher load carrying capacity as well as significant increase in the bending stiffness by encasing concrete on the beam *** present work gives a detailed description on the experimental,analytical and numerical investigation on the flexural behavior of concrete encased trapezoidally corrugated web profiled cold-formed steel beams which were simply supported at both ends and subjected to two point symmetric *** flexural behavior of such structure has been experimentally tested to failure under pure *** find the effct of concrete encasement in the web,12 experiments were conducted by two different *** having three different web corrugation angles of 0°,30°,and 45°with two different web depth-thickness(dw/tw)ratios of 60 and 80 were *** results such as load-deflection relationship,ultimate capacity,load-strain relationship,moment-curvature curves,ductility and failure mode indices of the specimens are *** the static bending tests the concrete encased trapezoidally corugated web beam showed improved moment carrying capacity,ductility bchavior and the resistance to transverse deflections in comparison to concrete encased with plain web *** for the beams with concrete encased 30°trapezoidally corrugated web having(dw/tw)ratio 60 and 80,the loading capacity was improved about 54%and 67.3%and the ductility also increased about l.6 and 3.6 times,when compared to concrete encased beams with plain *** research should contribute to the future engineering applications on seismic resistant structures and efficient usage of concrete encased with cold-formed steel beams by exhibiting its super elasto-plastic *** analytical and numerical results showed good agreement with the experimental results at yield load,which indicates that the proposed analyti

关键词： concrete encased beam trapezoidally corrugated web loading capacity super elasto-plastic

Effective inventory management using postponement strategy with fuzzy cost

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Management Analytics 2022年第2期9卷 232-260页

作者： K.V.Geetha M.prabha Department of Mathematics Sri S.Ramasamy Naidu Memorial CollegeSattur 626203Tamil NaduIndia Department of Mathematics PSNA College of Engineering and TechnologyDindigul 624622Tamil NaduIndia Department of Mathematics Research and Development CentreBharathiar UniversityCoimbatore 641046Tamil NaduIndia

In this article, we consider a two level supply chain to evaluate the impact ofpostponement strategy on the retailer. Here the cost parameters are *** distance method is used to defuzzify and to obtain the estimation of thetotal cost in the fuzzy sense. The common variable production cost, commonfixed cost and the common unit holding cost per unit time are assumed to befuzzy in nature. Inventory models are formulated for postponement system andindependent system such that the total average inventory cost function per unittime is minimized. Algorithms are given to derive the optimal solutions of theproposed model. Theoretical analysis and the computational procedure helps tostudy the impact of deterioration rate on the optimal inventory policies. Acomparative study between the postponement system and independent systemconsidering fuzzy costs is also made.

关键词： postponement strategy perishable items trapezoidal fuzzy number triangular fuzzy number signed distance method inventory

An Efficient Stacked-LSTM Based User Clustering for 5G NOMA Systems

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2022年第9期72卷 6119-6140页

作者： S.prabha Kumaresan Chee Keong Tan Yin Hoe Ng Faculty of Engineering Multimedia UniversityCyberjaya63100Malaysia School of Information Technology Monash UniversitySubang Jaya47500Malaysia

Non-orthogonal multiple access(NOMA)has been a key enabling technology for the fifth generation(5G)cellular *** on the NOMA principle,a traditional neural network has been implemented for user clustering(UC)to maximize the NOMA system’s throughput performance by considering that each sample is independent of the prior and the subsequent ***,the prediction of UC for the future ones is based on the current clustering information,which is never used again due to the lack of memory of the ***,to relate the input features of NOMA users and capture the dependency in the clustering information,time-series methods can assist us in gaining a helpful insight into the *** its mathematical complexity,the essence of time series comes down to examining past behavior and extending that information into the ***,in this paper,we propose a novel and effective stacked long short term memory(S-LSTM)to predict the UC formation of NOMA users to enhance the throughput performance of the 5G-based NOMA *** the proposed strategy,the S-LSTM is modelled to handle the time-series input data to improve the predicting accuracy of UC of the NOMA users by implementing multiple LSTM layers with hidden *** implemented LSTM layers have feedback connections that help to capture the dependency in the clustering information as it propagates between the ***,we develop,train,validate and test the proposed model to predict the UC formation for the futures ones by capturing the dependency in the clustering information based on the time-series *** results demonstrate that the proposed scheme effectively predicts UC and thereby attaining near-optimal throughput performance of 98.94%compared to the exhaustive search method.

关键词： Non-orthogonal multiple access(NOMA) deep neural network(DNN) long short term memory(LSTM) temporal channel user clustering

SMO Algorithm to Unravel CEED problem using Wind and Solar

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Intelligent Automation & Soft Computing 2023年第2期35卷 1857-1872页

作者： A.prabha G.Themozhi Rama Reddy Sathi Faculty of Electrical Engineering Anna UniversityChennai600025India Department of Electrical and Electronics Engineering AMET Deemed UniversityChennai603112India Department of Electrical and Electronics Engineering Rajalakshmi Engineering CollegeChennai602105India

This research proposes a more advanced way to address Combined Economic Emission Dispatch(CEED)*** Load Dispatch(ELD)and Economic Emission Dispatch(EED)have been implemented to reduce generating unit fuel costs and *** both economics and emission tar-gets are taken into account,the dispatch of an aggregate cost-effective emission challenge *** research affords a mathematical modeling-based analyti-cal technique for solving economic,emission,and collaborative economic and emission dispatch problems with only one *** study takes into account both the fuel cost target and the environmental impact of *** bi-inten-tion CEED problem is converted to a solitary goal function using a price penalty factor *** this case,a metaheuristic and an environment-inspired,intel-ligent Spider Monkey Optimization technique(SMO)are used to address the CEED *** following the generator’s scheduling process,the SMO meth-od is used to regulate the output from the power generation system in terms of pollution and fuel *** Fission-Fusion social(FFS)structure of spider mon-keys promotes them to utilize a global optimization method known as SMO dur-ing foraging *** emphasis is mostly on lowering the cost of generation and pollution in order to improve the efﬁciency of the power system and han-dle dispatch problems with *** economic dispatch has been reme-died,and the improved result demonstrates that the system’s performance is stable andﬂexible in real ***,the system’s output demonstrates that the system has improved in resolving CEED difﬁ*** compared to ear-lier investigations,the proposed model’sﬁndings have *** the gener-ating units,wind and solar are used to explore the CEED crisis in the IEEE 30 bus system.

关键词： Cost of generation emission CEED thermal power system bi-intention SMO wind and solar IEEE 30 bus system