检索结果-南通市图书馆

Deep Learning Enabled Social Media Recommendation Based on User Comments

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2期44卷 1691-1702页

作者： K.Saraswathi V.Mohanraj Y.Suresh j.senthilkumar Department of Computer Science and Engineering Government College of EngineeringSalem636011India Department of Information Technology Sona College of TechnologySalem636005India

Nowadays,review systems have been developed with social media Recommendation systems(RS).Although research on RS social media is increas-ing year by year,the comprehensive literature review and classiﬁcation of this RS research is limited and needs to be *** previous method did notﬁnd any user reviews within a time,so it gets poor accuracy and doesn’tﬁlter the irre-levant comments efﬁ*** Recursive Neural Network-based Trust Recom-mender System(RNN-TRS)is proposed to overcome this method’s *** it is efﬁcient to analyse the trust comment and remove the irrelevant sentence ***ﬁrst step is to collect the data based on the transactional reviews of social *** second step is pre-processing using Imbalanced Col-laborative Filtering(ICF)to remove the null values from the *** the features from the pre-processing step using the Maximum Support Grade Scale(MSGS)to extract the maximum number of scaling features in the dataset and grade the weights(length,count,etc.).In the Extracting features for Training and testing method before that in the feature weights evaluating the softmax acti-vation function for calculating the average weights of the ***,In the classiﬁcation method,the Recursive Neural Network-based Trust Recommender System(RNN-TRS)for User reviews based on the Positive and negative scores is analysed by the *** simulation results improve the predicting accuracy and reduce time complexity better than previous methods.

关键词： Recommendation systems(RS) social media recursive neural network-based trust recommender system(RNN-TRS) user reviews

Intrusion Detection Using Ensemble Wrapper Filter Based Feature Selection with Stacking Model

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1期35卷 645-659页

作者： D.Karthikeyan V.Mohan Raj j.senthilkumar Y.Suresh Department of ECE KongunaduCollege of Engineering and TechnologyTrichy621215India Department of IT Sona College of TechnologySalem636005India

The number of attacks is growing tremendously in tandem with the growth of internet *** a result,protecting the private data from prying eyes has become a critical and tough *** intrusion detection solutions have been offered by researchers in order to decrease the effect of these *** attack detection,the prior system has created an SMSRPF(Stacking Model Significant Rule Power Factor)*** provide creative instance detection,the SMSRPF combines the detection of trained classifiers such as DT(Decision Tree)and RF(Random Forest).Nevertheless,it does not generate any accuratefindings that are *** suggested system has built an EWF(Ensemble Wrapper Filter)feature selection with SMSRPF classifier for attack detection so as to overcome this *** UNSW-NB15 dataset is used as an input in this proposed research ***,min–max normalization approach is used to pre-process the incoming *** feature selection is then carried out using *** on the selected features,SMSRPF classifiers are utilized to detect the *** SMSRPF is integrated with the trained classi-fiers such as DT and RF to create creative instance *** that,the testing data is classified using MCAR(Multi-Class Classification based on Association Rules).The SRPF judges the rules correctly even when the confidence and the lift measures *** accuracy,precision,recall,f-measure,computation time,and error,the experimental findings suggest that the new system outperforms the prior systems.

关键词： Intrusion detection system(IDS) ensemble wrapperfilter(EWF) stacking model with significant rule power factor(SMSRPF) classifier

BFS-SVM Classifier for QoS and Resource Allocation in Cloud Environment

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10期47卷 777-790页

作者： A.Richard William j.senthilkumar Y.Suresh V.Mohanraj Er Perumal Manimekalai College of Engineering Hosur636352Tamil NaduIndia Sona College of Technology Salem636005Tamil NaduIndia

In cloud computing Resource allocation is a very complex *** the customer demand makes the challenges of on-demand resource *** challenges are faced by conventional methods for resource allocation in order tomeet the Quality of Service(QoS)requirements of *** solving the about said problems a new method was implemented with the utility of machine learning framework of resource allocation by utilizing the cloud computing technique was taken in to an account in this research *** accuracy in the machine learning algorithm can be improved by introducing Bat Algorithm with feature selection(BFS)in the proposed work,this further reduces the inappropriate features from the *** similarities that were hidden can be demoralized by the Support Vector Machine(SVM)classifier which is also determine the subspace vector and then a new feature vector can be predicted by using *** an unexpected circumstance SVM model can make a resource allocation *** efficiency of proposed SVM classifier of resource allocation can be highlighted by using a singlecell multiuser massive Multiple-Input Multiple Output(MIMO)system,with beam allocation problem as an *** proposed resource allocation based on SVM performs efficiently than the existing conventional methods;this has been proven by analysing its results.

关键词： Bat algorithm with feature selection(BFS) support vector machine(SVM) multiple-input multiple output(MIMO) quality of service(QoS) classifier cloud computing

Influence of Shallow and Deep Cryogenic Treatment on Tribological Behavior of En 19 Steel

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 Iron and Steel Research International 2011年第9期18卷 53-59页

作者： D senthilkumar I Rajendran Department of Mechanical Engineering Dr Mahalingam College of Engineering and Technology

The influence of cryogenic treatment on the wear resistance of En 19 steel was studied. Furthermore, a comparative analysis on the effect of Deep Cryogenic Treatment （DCT, 196℃× 24 h）, Shallow Cryogenic Treatment （SCT -80℃ × 5 h） and Conventional Heat Treatment （CHT） was done through dry sliding wear testing. The microstructures of CHT, SCT and DCT samples were also examined through scanning electron microscopy. The results indicated that the wear resistance of shallow and deep cryogenically treated samples is higher when compared to that of conventionally treated samples. X-ray diffraction pattern revealed that the transformation of retained austenite into martensite is responsible for the wear resistance improvement.

关键词： steel wear cryogenic treatment automotive

Mapping allosteric pathway in NIa-Pro using computational approach

在线全文

学校读者我要写书评

暂无评论

Quantitative Biology 2023年第1期11卷 82-93页

作者： Rashmi Panigrahi senthilkumar Kailasam Department of Biochemistry University of AlbertaEdmontonT6G 2H7Canada Canadian Centre for Computational Genomics McGill UniversityMontréalH3A 0G1Canada

Background:Computer simulation studies complement in vitro experiments and provide avenue to understand allosteric regulation in the absence of other molecular viewing *** dynamics captures internal motion within the protein and enables tracing the communication path between a catalytic site and a distal allosteric *** this article,we have identified the communication pathway between the viral protein genome linked(VPg)binding region and catalytic active site in nuclear inclusion protein-a protease(NIa-Pro).Methods:Molecular dynamics followed by in silico analyses have been used to map the allosteric ***:This study delineates the residue interaction network involved in allosteric regulation of NIa-Pro activity by *** studies indicate that point mutations in the VPg interaction interface of NIa-Pro lead to disruption in these networks and change the orientation of catalytic ***142Ala and His167Ala mutations do not show a substantial change in the overall protease structure,but rather in the residue interaction network and catalytic site ***:Our mutagenic study delineates the allosteric pathway and facilitates the understanding of the modulation of NIa-Pro activity on a molecular level in the absence of the structure of its complex with the known regulator ***,our in silico analysis explains the molecular concepts and highlights the dynamics behind the previously reported wet lab study findings.

关键词： NIa-Pro VPg simulation residue interaction network allostery

Pulsed current and dual pulse gas metal arc welding of grade AISI: 310S austenitic stainless steel

在线全文

学校读者我要写书评

暂无评论

Defence Technology（防务技术） 2015年第3期11卷 269-274页

作者： A.MATHIVANAN A.senthilkumar K.DEVAKUMARAN Mechanical Engineering Department SRM University School of Mechanical and Building Sciences (SMBS) VIT University Welding Research Institute Bharath Heavy Electricals Limited (BHEL)

The transverse shrinkage, mechanical and metallurgical properties of AISI: 310 S ASS weld joints prepared by P-GMAW and DP-GMAW processes were investigated. It was observed that the use of the DP-GMAW process improves the aforementioned characteristics in comparison to that of the P-GMAW process. The enhanced quality of weld joints obtained with DP-GMAW process is primarily due to the combined effect of pulsed current and thermal pulsation(low frequency pulse). During the thermal pulsation period, there is a fluctuation of wire feed rate,which results in the further increase in welding current and the decrease in arc voltage. Because of this synchronization between welding current and arc voltage during the period of low frequency pulse, the DP-GMAW deposit introduces comparatively more thermal shock compared to the P-GMAW deposit, thereby reducing the heat input and improves the properties of weld joints.

关键词： AISI 电弧焊接奥氏体不锈钢脉冲气体电流脉冲品位金属力学性能

Rechargeable Na-MnO_(2) battery with modified cell chemistry

在线全文

学校读者我要写书评

暂无评论

journal of Energy Chemistry 2023年第9期84卷 414-423页

作者： Sirugaloor Thangavel senthilkumar Rebeca Marcilla Youngsik Kim jesus Palma Mani Ulaganathan jeong-Sun Park School of Energy&Chemical Engineering Ulsan National Institute of Science and Technology(UNIST)Ulsan 689-798Republic of Korea Electrochemical Processes Unit IMDEA Energy InstituteAvda.Ramón de La Sagra 328935MóstolesSpain Center for Advanced Materials Research Research Institute of Science and TechnologyUniversity of SharjahP.O.Box 27272SharjahUnited Arab Emirates Energy Materials and Devices Lab 4TOONE CorporationUNIST-gil 50Ulsan 689-798Republic of Korea Department of Sciences Amrita School of Physical SciencesAmrita Vishwa VidyapeethamCoimbatore 641112India

High voltage,high energy density,nominal cycle life,and low cost are the most critical requirements of rechargeable batteries for their widespread energy storage applications in electric vehicles and renewable energy ***-MnO_(2) battery could be a low-cost contender,but it suffers extensively from its low cell voltage and poor *** this study,we modified the conventional cell structure of Na-MnO_(2) battery and established altered cell chemistry through a hybrid electrochemical process consisting of Na striping/plating at the anode and Zn^(2+) insertion/de-insertion along with MnO_(2) dissolution/deposition at the *** the modification,Na-MnO_(2) battery exhibits a discharge capacity of 267.10 mA h/g and a cell voltage of 3.30 V(***/Na^(+)),resulting in a high specific energy density of 881.43 Wh/*** 300 cycles,the battery retains 98% of its first-cycle discharge capacity with100% coulombic ***,Na metal-free battery assembled using sodium biphenyl as a safer anode also delivers an excellent energy density of 810.0 Wh/*** work could provide a feasible method to develop an advanced Na-MnO_(2) battery for real-time energy storage applications.

关键词： Hybrid battery Sodium metal Sodium biphenyl High cell voltage Manganese dioxide battery Modified cell chemistry

Effect of Low Feed Rate FSP on Microstructure and Mechanical Properties of Extruded Cast 2285 Aluminum Alloy

在线全文

学校读者我要写书评

暂无评论

journal of Materials Science & Technology 2007年第5期23卷 614-618页

作者： L.Karthikeyan V.S.senthilkumar D.Viswanathan S.Natarajan Department of Mechanical Engineering Panimalar Engineering CollegeChennai-103TamilNaduIndia Department of Mechanical Engineering College of EngineeringAnna UniversityChennai-025TamilNaduIndia

Friction stir processing （FSP）, a variation of FSW （friction stir welding） is an emerging surface engineering technology that can locally eliminate casting defects and refine microstructures, thereby improving the mechanical properties of material. FSP can also produce fine grained microstructures through the thickness to impart superplasticity. The technology involves plunging a rapidly rotating, non consumable tool, comprising a profiled pin and larger diameter shoulder, into the surface and then traversing the tool across the surface. The pin and the shoulder friction heat the surface which alters the grain structure in the processed area thereby improving the mechanical properties. This paper presents the effects of FSP on microstructure and mechanical properties of extruded cast 2285 aluminum alloy at three different feed rates viz. 10, 12 and 15 mm/min. With the increase in the feed speed the material was observed to have increased impact strength. FSP also increased the tensile and yield strengths with increases in hardness and ductility values also. The observation has been listed in detail and pictorially represented.

关键词： Friction stir processing Feed rate Fine grain microstructure

K＋ Transporter AtCHX17 with Its Hydrophilic C Tail Localizes to Membranes of the Secretory/Endocytic System： Role in Reproduction and Seed Set

在线全文

学校读者我要写书评

暂无评论

Molecular Plant 2013年第4期6卷 1226-1246页

作者： Salil Chanroj.senthilkumar Padmanaban Daniel D. Czerny Guang-Yuh jauh Heven Sze Department of Cell Biology and Molecular Genetics and Maryland Agricultural Experiment Station University of Maryland College Park MD USA Department of Plant Science and Landscape Architecture University of Maryland College Park MD USA Present address: Department of Biotechnology Faculty of Science Burapha University Chon-Buri 20131 Thailand Institute of Plant and Microbial Biology Academia Sinica 128 Academia Road Section 2 Nankang Taipei

The importance of sorting proteins and wall materials to their destination is critical for plant growth and development, though the machinery orchestrating membrane trafficking is poorly understood. Transporters that alter the environment across endomembrane compartments are thought to be important players. Using Escherichia coli and yeast, we previously showed that several Arabidopsis Cation/H＋ eXchanger （AtCHX） members were K＋ transporters with a role in pH homeostasis, though their subcellular location and biological roles in plants are unclear. Co-expression of markers with CHX16, CHX17, CHX18, or CHX19 tagged with a fluorescent protein indicated these transporters associated with plasma membrane （PM） and post-Golgi compartments. Under its native promoter, AtCHX17（l_820）-GFP localized to prevacuolar compartment （PVC） and to PM in roots. Brefeldin A diminished AtCHX17- GFP fluorescence at PM, whereas wortmannin caused formation of GFP-labeled ring-like structures, suggesting AtCHX17 trafficked among PVC, vacuole and PM. AtCHX17（1-472） lacking its carboxylic tail did not associate with PVC or PM in plant cells. Single chx17 mutant or higher-order mutants showed normal root growth and vegetative devel- opment. However, quadruple （chx16chx17chxlSchx19） mutants were reduced in frequency and produced 50%-70% fewer seeds, indicating overlapping roles of several AtCHX17-related transporters in reproduction and/or seed devel- opment. Together, our results suggest that successful reproduction and seed development depend on the ability to regulate cation and pH homeostasis by AtCHX17-1ike transporters on membranes that traffic in the endocytic and/or secretory pathways.

关键词： membrane trafficking pH homeostasis cation/proton antiporter prevacuolar compartment.