检索结果-南通市图书馆

Optimization algorithms and intelligent techniques on electrical discharge machining process

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

International Journal of Modeling, Simulation, and Scientific Computing 2021年第4期12卷 12-40页

作者： C.S.Shyn R.Rajesh noorul islam centre for higher education Tamil Nadu India

Electrical Discharge Machining (EDM) is considered as the much traditional, adaptableand unconventional machining process that is proficient in generating complicated structures. Further, it is self-sufficient over the mechanical properties of workpiece materialsonly if it is conductive. The viability of the EDM process regarding the application typesmight get considerably improved with the constant enhancement in the personificationof numerical control and the metal removal efficacy. This survey intends to make a reviewof 65 papers related to the optimization and modeling of EDM process machining. Theanalysis is thus made with regards to the following factors like Al alloy composite in DieShrinking EDM, Optimization and Al metal matrix composites. Particularly, the hybridoptimization models in various papers are analyzed concerning their logic. Further, thealgorithmic and parametric analysis is also made with the contributed papers. Finally,the research gaps and challenges in this EDM processing are discussed, which wouldpave the way for efficient research works in this area.

关键词： Electric discharge machining aluminium alloy metal matrix composite neural network optimization

Nature-inspired hybrid deep learning for race detection by face shape features

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

International Journal of Intelligent Computing and Cybernetics 2020年第3期13卷 365-388页

作者： Asha Sukumaran Thomas Brindha Department of Computer Science and Engineering Noorul Islam Centre for Higher EducationKumaracoilIndia Department of Information Technology Noorul Islam Centre for Higher EducationKumaracoilIndia

Purpose-The humans are gifted with the potential of recognizing others by their uniqueness,in addition with more other demographic characteristics such as ethnicity(or race),gender and age,*** the decades,a vast count of researchers had undergone in the field of psychological,biological and cognitive sciences to explore how the human brain characterizes,perceives and memorizes ***,certain computational advancements have been developed to accomplish several insights into this ***/methodology/approach-This paper intends to propose a new race detection model using face shape *** proposed model includes two key phases,namely.(a)feature extraction(b)*** feature extraction is the initial stage,where the face color and shape based features get ***,maximally stable extremal regions(MSER)and speeded-up robust transform(SURF)are extracted under shape features and dense color feature are extracted as color ***,the extracted features are huge in dimensions;they are alleviated under principle component analysis(PCA)approach,which is the strongest model for solving“curse of dimensionality”.Then,the dimensional reduced features are subjected to deep belief neural network(DBN),where the race gets ***,to make the proposed framework more effective with respect to prediction,the weight of DBNis fine tuned with a new hybrid algorithm referred as lion mutated and updated dragon algorithm(LMUDA),which is the conceptual hybridization of lion algorithm(LA)and dragonfly algorithm(DA).Findings-The performance of proposed work is compared over other state-of-the-art models in terms of accuracy and error ***,LMUDA attains high accuracy at 100th iteration with 90%of training,which is 11.1,8.8,5.5 and 3.3%better than the performance when learning percentage(LP)550%,60%,70%,and 80%,*** particularly,the performance of proposed DBNþLMUDAis 22.2,12.5 and 33.3%better than the trad

关键词： Facial race detection Color dense features DBN Optimization LMUDA

Investigation of Single and Multiple Mutations Prediction Using Binary Classification Approach

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4期36卷 1189-1203页

作者： T.Edwin Ponraj J.Charles Department of Computer Applications Noorul Islam Centre for Higher EducationKumaracoil629180India Department of Software Engineering Noorul Islam Centre for Higher EducationKumaracoil629180India

The mutation is a critical element in determining the proteins’stability,becoming a core element in portraying the effects of a drug in the pharmaceutical *** wet laboratory tests to provide a better perspective on protein mutations is expensive and time-intensive since there are so many potential muta-tions,computational approaches that can reliably anticipate the consequences of amino acid mutations are *** work presents a robust methodology to analyze and identify the effects of mutation on a single protein ***,the context in a collection of words is determined using a knowledge graph for feature selection *** proposed prediction is based on an easier and sim-pler logistic regression inferred binary classiﬁcation *** approach can able to obtain a classiﬁcation accuracy(AUC)Area Under the Curve of 87%when randomly validated against experimental energy ***,for each cross-fold validation,the precision,recall,and F-Score are *** results support the validity of our strategy since it performs the vast majority of prior studies in this domain.

关键词： Proteins data science mutation analysis random forest neighbor proteins single and double mutations

Improved Interleaved Single-Ended Primary Inductor-Converter forSingle-Phase Grid-Connected System

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 3459-3478页

作者： T.J.Thomas Thangam K.Muthu Vel noorul islam centre for higher education Nagarkovil629180TamilnaduIndia

The generation of electricity based on renewable energy sources,parti-cularly Photovoltaic(PV)system has been greatly increased and it is simply insti-gated for both domestic and commercial *** power generated from the PV system is erratic and hence there is a need for an efﬁcient converter to perform the extraction of maximum *** improved interleaved Single-ended Primary Inductor-Converter(SEPIC)converter is employed in proposed work to extricate most of power from renewable *** proposed converter minimizes ripples,reduces electromagnetic interference due toﬁlter elements and the contin-uous input current improves the power output of PV panel.A Crow Search Algo-rithm(CSA)based Proportional Integral(PI)controller is utilized for controlling the converter switches effectively by optimizing the parameters of PI *** optimized PI controller reduces ripples present in Direct Current(DC)vol-tage,maintains constant voltage at proposed converter output and reduces over-shoots with minimum settling and rise *** voltage is given to single phase grid via 1�Voltage Source Inverter(VSI).The command pulses of 1�VSI are produced by simple PI *** response of the proposed converter is thus improved with less input *** implementing CSA based PI the efﬁciency of proposed converter obtained is 96%and the Total Harmonic Distor-tion(THD)is found to be 2:4%.The dynamics and closed loop operation is designed and modeled using MATLAB Simulink tool and its behavior is performed.

关键词： Improved interleaved DC-DC SEPIC converter crow search algorithm PI controller voltage source inverter PV array single phase grid

Copy Move Forgery Detection Using Novel Quadsort Moth Flame Light Gradient Boosting Machine

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 2023年第5期45卷 1577-1593页

作者： R.Dhanya R.Kalaiselvi Department of Computer Applications Noorul Islam Centre for Higher EducationNagercoil629180India Department of Computer Science Engineering Noorul Islam Centre for Higher EducationNagercoil629180India

A severe problem in modern information systems is Digital media tampering along with fake *** though there is an enhancement in image development,image forgery,either by the photographer or via image manipulations,is also done in *** researches have been concentrated on how to identify such manipulated media or information manually along with automatically;thus conquering the complicated forgery methodologies with effortlessly obtainable technologically enhanced ***,high complexity affects the developed ***,it is complicated to resolve the issue of the speed-accuracy *** tackling these challenges,this article put forward a quick and effective Copy-Move Forgery Detection(CMFD)system utilizing a novel Quad-sort Moth Flame(QMF)Light Gradient Boosting Machine(QMF-Light GBM).Utilizing Borel Transform(BT)-based Wiener Filter(BWF)and resizing,the input images are initially pre-processed by eliminating the noise in the proposed *** that,by utilizing the Orientation Preserving Simple Linear Iterative Clustering(OPSLIC),the pre-processed images,partitioned into a number of grids,are ***,as of the segmented images,the significant features are extracted along with the feature’s distance is calculated and matched with the input ***,utilizing the Union Topological Measure of Pattern Diversity(UTMOPD)method,the false positive matches that took place throughout the matching process are *** that,utilizing the QMF-Light GBM visualization,the visualization of forged in conjunction with non-forged images is *** extensive experiments revealed that concerning detection accuracy,the proposed system could be extremely precise when contrasted to some top-notch approaches.

关键词： Borel transform based wiener filter(BWF) orientation preserving simple linear iterative clustering(OPSLIC) keypoint features block features outlier detection

Evolutionary Algorithm Based Feature Subset Selection for Students Academic Performance Analysis

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6期36卷 3621-3636页

作者： Ierin Babu R.MathuSoothana S.Kumar Department of Computer Science and Engineering Noorul Islam Centre for Higher EducationKanyakumari629180India Department of Information Technology Noorul Islam Centre for Higher EducationKanyakumari629180India

educational Data Mining(EDM)is an emergent discipline that concen-trates on the design of self-learning and adaptive *** education institutions have started to utilize analytical tools to improve students’grades and *** of students’performance is a difficult process owing to the massive quantity of educational ***,Artificial Intelligence(AI)techniques can be used for educational data mining in a big data *** the same time,in EDM,the feature selection process becomes necessary in creation of feature *** the feature selection performance affects the predictive performance of any model,it is important to elaborately investigate the outcome of students’performance model related to the feature selection *** this motivation,this paper presents a new Metaheuristic Optimiza-tion-based Feature Subset Selection with an Optimal Deep Learning model(MOFSS-ODL)for predicting students’*** addition,the proposed model uses an isolation forest-based outlier detection approach to eliminate the existence of ***,the Chaotic Monarch Butterfly Optimization Algo-rithm(CBOA)is used for the selection of highly related features with low com-plexity and high ***,a sailfish optimizer with stacked sparse autoencoder(SFO-SSAE)approach is utilized for the classification of educational *** MOFSS-ODL model is tested against a benchmark student’s perfor-mance data set from the UCI repository.A wide-ranging simulation analysis por-trayed the improved predictive performance of the MOFSS-ODL technique over recent approaches in terms of different *** to other methods,experimental results prove that the proposed(MOFSS-ODL)classification model does a great job of predicting students’academic progress,with an accuracy of 96.49%.

关键词： Students’performance analysis educational data mining feature selection deep learning metaheuristics outlier detection

Complete Cototal Roman Domination Number of a Graph for User Preference Identification in Social Media

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 2023年第6期45卷 2405-2415页

作者： J.Maria Regila Baby K.Uma Samundesvari Department of Mathematics Noorul Islam Centre for Higher EducationKumaracoil629175India

Many graph domination applications can be expanded to achieve complete cototal *** every node in a dominating set is regarded as a record server for a PC organization,then each PC affiliated with the organization has direct access to a document *** is occasionally reasonable to believe that this gateway will remain available even if one of the scrape servers *** every PC has direct access to at least two documents’servers,a complete cototal dominating set provides the required adaptability to non-critical failure in such *** this paper,we presented a method for calculating a graph’s complete cototal roman domination *** also examined the properties and determined the bounds for a graph’s complete cototal roman domination number,and its applications are *** has been observed that one’s interest fluctuate over time,therefore inferring them just from one’s own behaviour may be ***,it may be able to deduce a user’s constant interest to some level if a user’s networking is also watched for similar or related *** research proposes a method that considers a user’s and his channel’s activity,as well as common tags,persons,and organizations from their social media posts in order to establish a solid foundation for the required conclusion.

关键词： Social media network graph complete cototal roman domination

Small-World Networks with Unitary Cayley Graphs for Various Energy Generation

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 2023年第6期45卷 2773-2782页

作者： C.Thilag P.B.Sarasija Department of Mathematics Noorul Islam Centre for Higher EducationKumaracoil629180India

Complex networks have been a prominent topic of research for several years,spanning a wide range of fields from mathematics to computer science and also to social and biological *** eigenvalues of the Seidel matrix,Seidel Signless Laplacian matrix,Seidel energy,Seidel Signless Laplacian energy,Maximum and Minimum energy,Degree Sum energy and Distance Degree energy of the Unitary Cayley graphs[UCG]have been ***-power devices must be able to transfer data across long distances with low delay and *** overcome this drawback a small-world network depending on the unitary Cayley graph is proposed to decrease the delay and increase the reliability and is also used to create and analyze network ***-world networks based on the Cayley graph have a basic construction and are highly *** simulation result shows that the small-world network based on unitary Cayley graphs has a shorter delay and is more ***,the maximum delay is lowered by 40%.

关键词： Seidel energy Seidel Signless Laplacian eigenvalues Distance degree energy Unitary Cayley graphs

WOA-DNN for Intelligent Intrusion Detection and Classification in MANET Services

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 1737-1751页

作者： C.Edwin Singh S.Maria Celestin Vigila Department of Computer Science and Engineering Noorul Islam Centre for Higher EducationNagercoil629180India Department of Information Technology Associate ProfessorNoorul Islam Centre for Higher EducationNagercoil629180India

Mobile ad-hoc networks(MANET)are garnering a lot of attention because of their potential to provide low-cost solutions to real-world *** are more vulnerable to security *** in nodes,band-width limits,and centralized control and management are some of the ***(Intrusion Detection System)are the aid for detection,deter-mination,and identiﬁcation of illegal system activity such as use,copying,mod-iﬁcation,and destruction of *** address the identiﬁed issues,academics have begun to concentrate on building IDS-based machine learning *** learning is a type of machine learning that can produce exceptional *** study proposes that WOA-DNN be used to detect and classify incursions in MANET(Whale Optimized Deep Neural Network Model)WOA(Whale Opti-mization Algorithm)and DNN(Deep Neural Network)are used to optimize the preprocessed data to construct a system for classifying and predicting unantici-pated cyber-attacks that are both effective and efﬁ*** a result,secure data transport to other nodes is provided,preventing intruder *** invaders are found using the(Machine Learning)ML-IDS and WOA-DNN *** data is reduced in dimensionality using Principal Component Analysis(PCA),which improves the accuracy of the outputs.A classiﬁer is used in forward propagation to predict whether a result is normal or *** compare the traditional and proposed models’effectiveness,the accuracy of classiﬁcation,detection of the attack rate,precision rate,and F-Measure,Recall are *** proposed WOA-DNN model has higher assessment metrics and a 99.1%accuracy ***-DNN also has a greater assault detection rate than others,resulting in fewer false *** classiﬁcation accuracy of the proposed WOA-DNN model is 99.1%.

关键词： Intrusion detection system whale optimization algorithm deep neural network mobile ad-hoc networks forward and back propagation