检索结果-南通市图书馆

Implementation of Hybrid Deep reinforcement Learning Technique for Speech Signal Classification

Computer Systems Science & Engineering 2023年第7期46卷 43-56页

作者： r.gayathri K.Sheela Sobana rani Department of Electronics and Communication Engineering Sri Ramakrishna Institute of TechnologyCoimbatore641020India Department of Electrical and Electronics Engineering Sri Ramakrishna Institute of TechnologyCoimbatore641020India

Classification of speech signals is a vital part of speech signal processing *** the advent of speech coding and synthesis,the classification of the speech signal is made accurate and *** methods are considered inaccurate due to the uncertainty and diversity of speech signals in the case of real speech signal *** this paper,we use efficient speech signal classification using a series of neural network classifiers with reinforcement learning *** classification of speech signals,the study extracts the essential features from the speech signal using Cepstral *** features are extracted by converting the speech waveform to a parametric representation to obtain a relatively minimized data *** to improve the precision of classification,Generative Adversarial Networks are used and it tends to classify the speech signal after the extraction of features from the speech signal using the cepstral *** classifiers are trained with these features initially and the best classifier is chosen to perform the task of classification on new *** validation of testing sets is evaluated using rL that provides feedback to ***,at the user interface,the signals are played by decoding the signal after being retrieved from the classifier back based on the input *** results are evaluated in the form of accuracy,recall,precision,f-measure,and error rate,where generative adversarial network attains an increased accuracy rate than other methods:Multi-Layer Perceptron,recurrent Neural Networks,Deep belief Networks,and Convolutional Neural Networks.

关键词： Neural network(NN) reinforcement learning(rL) cepstral coefficient speech signal 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

On the Selection of a Composite Material for Two-Wheeler Foot Bracket Failure Prevention through Simulation and Mathematical Modeling

引用

Fluid Dynamics & Materials Processing 2022年第3期18卷 521-536页

作者： S.M.Sivagami A.Bovas Herbert Bejaxhin r.gayathri T.raja Vijay K.Punitharani P.Keerthi Vasan M.Meignanamoorthy Department of Mechanical Engineering Alagappa Chettiar Government College of Engineering and TechnologyKaraikudiTamilnadu630003India Department of Mechanical Engineering Saveetha School of EngineeringSIMATSThandalamChennaiTamilnadu602105India Department of Mechanical Engineering PSG College of TechnologyCoimbatoreTamilnadu641004India Department of Mechanical Engineering K.Ramakrishnan College of EngineeringTiruchirappalliTamilnadu621112India

A foot bracket is a metal panel bracket used to mount and support the footrest in two-wheeler *** holds the footrest in place while rigidly supporting *** working conditions,this element has often been observed to fail when specific load-fluctuation conditions are established at its rear *** materials therefore need to be identified to overcome such a recurring *** address these issues,the present study has been implemented with the specific objective to determine the response of selected Al6061-T6 and Al7075-T6 Hybrid Metal Matrix Composites(HMMC).The results,obtained using the ANSYS Software,show that the selected composites can withstand 636,962 N/m^(2)of maximum stress and 8.88×10^(−6)m of minimum *** results are also compared with relevant mathematical models and it is concluded that the identified material combination provides the required improvement of structural stability that can withstand the load fluctuation on the foot bracket.

关键词： Foot bracket Al6061-T6 alloy CrEO ANSYS stress displacement

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

Medicinal Plant Using Ground State Stabilization of Natural Antioxidant Curcumin by Keto-Enol Tautomerisation

引用

Natural Products and Bioprospecting 2018年第5期8卷 369-390页

作者： S.Manimaran K.Sambath Kumar r.gayathri K.raja N.rajkamal M.Venkatachalapathy G.ravichandran C.Lourdu Edisonraj P.G&research Department of Physics Thanthai Hans Roever College(Autonomous)PerambalurTamil Nadu 621220India Post Graduate and research Department of Physics (NANO Science Divisions)A.A.Govt.Arts CollegeVillupuramTamil Nadu 605602India Post Graduate and research Department of Physics Cauvery College for WomenTiruchirappalliTamil NaduIndia Post Graduate and research Department of Physics Dr.R.K.Shanmugam College of Arts&ScienceKallakurichiTamil Nadu 606213India Post Graduate and research Department of Physics Thiru.A.Govindasamy Govt Arts CollegeTindivanamTamil Nadu 604002India Post Graduate and research Department of Chemistry A.A.Govt.Arts CollegeVillupuramTamil Nadu 605602India

Curcumin is a medicinal agent that exhibits anti-cancer properties and bioactive pigment in Turmeric has a huge thera-peutic *** has a keto-enol moiety that gives rise to many of its chemical properties.A recent study has shown thatketo-enol tautomerisation at this moiety is implicated the effect of *** tautomerisation of curcumin in *** and acetonitrile are used in nuclear magnetic resonance(^(1)H,^(13)C)*** was characterized using UV,Irand raman spectral *** molecular electrostatic potential surface of the Curcumin has been visualized in elec-tropositive potential in the region of the CH^(3+) group and most electronegative potential in the two oxygen atom has verystrong binding *** the following,the modality of structural and thermo dynamical parameters,electrophilicity(ω).chemical potential(μ),chemical hardness(η) and electronic charge transfer confirms the local *** rate constantof tautomerisation of curcumin shows strong temperature *** electrostatic potential and Temperature dependence of various thermodynamic properties like(C^(0)_(p,m),S^(0)_(m),and H^(0)_(m))is increase with increase in temperature formonomer and dimer of various electrical fields.

关键词： Curcumin NMr.Uv HOMO-LUMO.MEP

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

Performance Evaluation of Compressed Air Energy Storage Using TrNSYS

引用

Journal of Electronic Science and Technology 2015年第4期13卷 361-366页

作者： r.Velraj V.gayathri A.Thenmozhi the Institute for Energy Studies Anna University

The appreciable economic growth in some of the developing countries like India in the recent years, towards providing energy security causes large environmental impact. renewable Energy （rE） is being seen as one of the important means to meet the growing power needs of the economy while enhancing energy security and providing opportunities for mitigating greenhouse gas emissions. However, rE sources are highly intermittent in nature. The variability of these sources has led to concerns regarding the reliability of an electric grid that derives a large fraction of its energy from these sources as well as the cost of reliably integrating large amounts of variable generation into the electric grid. Hence at this juncture, it is necessary to explore the benefits of suitable Energy storage technologies. Compressed air energy storage （CAES） is a commercial, utility-scale technology that provides long-duration energy storage with fast ramp rates and good part-load operation. It is a promising storage technology for balancing the large-scale penetration of renewable energies, such as wind and solar power, into electric grids. Considering the potential of CAES storage, the present work, a thermodynamic model is developed with suitable assumptions and the simulation analysis is performed using transient system simulation （TrNSYS） v17 software. The system performanee is compared by considering the recovery during the heat of compression using a thermal storage system and without considering the heat recovery. The overall turnaround efficiency of the system without considering the thermal energy storage （TES） system is 57 % and with TES system the efficiency is increased to 70%.

关键词： Compressed air energy storage solarcollector thermal energy storage.

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 Study of Ethical Implications of AI Tools Enhancing User Conveniences in the Indian Digital Landscape

引用

Journal of Social Computing 2024年第3期5卷 206-231页

作者： Biju P.r.gayathri O. the Department of Political Science at Government Brennen College Kerala 670106India the Department of Political Science at Government College Madappally Kerala 673102India

Structural oppression is a pervasive characteristic of Indian society,disproportionately affecting underprivileged groups such as Dalits,women,religious minorities,and geographically segregated *** developments in the economy and technology therefore affect the lives of these marginalized groups *** previous studies have explored the societal implications of intelligent systems,particularly prediction technologies such as recommender systems,ratings and reviews,there remains a significant gap in the literature concerning their impacts on these vulnerable social ***,there is a lack of insights into the unique challenges faced by marginalized communities within the context of predictive *** paper examines how the intelligent algorithms affect personal freedoms of weaker sections,particularly the right to choice,and whether they reinforce existing social biases within Indian *** doing so,it seeks to inform policymakers and predict the implications of prediction technologies on liberty;thereby proposing insights on the similar other issues likely to affect underprivileged communities due to the widespread adoption of AI technologies.

关键词： liberty social structure algorithm artificial intelligence Indian digital landscape

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

Pulsatile blood flow in large arteries:comparative study of Burton's and McDonald's models

引用

Applied Mathematics and Mechanics(English Edition) 2014年第5期35卷 575-590页

作者： K.gayathri K.SHAILENDHrA Department of Mathematics Amrita School of Engineering Amrita Vishwa Vidyapeetham

To get a clear picture of the pulsatile nature of blood flow and its role in the pathogenesis of atherosclerosis, a comparative study of blood flow in large arteries is carried out using the two widely used models, McDonald＇s and Burton＇s models, for the pressure gradient. For both models, the blood velocity in the lumen is obtained analytically. Elaborate investigations on the wall shear stress （WSS） and oscillatory shear index （OSI） are carried out. The results are in good agreement with the available data in the literature. The superiority of McDonald＇s model in capturing the pulsatile nature of blood flow, especially the OSI, is highlighted. The present investigation supports the hypothesis that not only WSS but also OSI are the essential features determining the pathogenesis of atherosclerosis. Finally, by reviewing the limitations of the present investigation, the possibility of improvement is explored.

关键词： hemodynamics wall shear stressrealistic pressure gradient Beavers and Josephpulmonary artery(WSS) oscillatory(B J) slip conditionshear index (OSI) femoral brachial

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

Performance Improvement of Multiband Triangular Microstrip Patch Antenna Using Frequency Selective Surface

引用

Journal of Shanghai Jiaotong university(Science) 2024年第2期29卷 316-321页

作者： MAHENDrAN Krishnakumar.gayathri rajaraman Department of Electronics and Communication Engineering Annamalai UniversityChidambaram 608002India

Today's antennas have to operate in multiple resonant frequencies to satisfy the need of recent advances in communication *** paper presents split ring resonator based triangular multiband antenna whose antenna performance is enhanced with the help of frequency selective surfaces(FSSs).The antenna has multiple resonances at S,C,and X *** array of 4×3 crisscross-shaped unit cells are arranged to form the FSS *** antenna is fed with a microstrip line feeding *** proposed antenna operates at 3.5 GHz,4.1 GHz,5.5GHz,9.4GHz,and 9.8 GHz with a better return loss and *** and measured results yield a good match.

关键词： triangular microstrip antenna split ring resonator frequency selective surface(FSS) metamaterial

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

Detection and defending the XSS attack using novel hybrid stacking ensemble learning-based DNN approach

引用

Digital Communications and Networks 2024年第3期10卷 716-727页

作者： Muralitharan Krishnan Yongdo Lim Seethalakshmi Perumal gayathri Palanisamy IMS Sungkyunkwan UniversitySuwon16419South Korea Department of Mathematics Sungkyunkwan UniversitySuwon16419South Korea Department of Information Technology Madras Institute of TechnologyChennaiIndia Department of Mathematics PSG College of Arts and ScienceTamilnaduIndia

Existing web-based security applications have failed in many situations due to the great intelligence of *** web applications,Cross-Site Scripting(XSS)is one of the dangerous assaults experienced while modifying an organization's or user's *** avoid these security challenges,this article proposes a novel,all-encompassing combination of machine learning(NB,SVM,k-NN)and deep learning(rNN,CNN,LSTM)frameworks for detecting and defending against XSS attacks with high accuracy and *** on the representation,a novel idea for merging stacking ensemble with web applications,termed“hybrid stacking”,is *** order to implement the aforementioned methods,four distinct datasets,each of which contains both safe and unsafe content,are *** hybrid detection method can adaptively identify the attacks from the UrL,and the defense mechanism inherits the advantages of UrL encoding with dictionary-based mapping to improve prediction accuracy,accelerate the training process,and effectively remove the unsafe JScript/JavaScript keywords from the *** simulation results show that the proposed hybrid model is more efficient than the existing detection *** produces more than 99.5%accurate XSS attack classification results(accuracy,precision,recall,f1_score,and receiver Operating Characteristic(rOC))and is highly resistant to XSS *** order to ensure the security of the server's information,the proposed hybrid approach is demonstrated in a real-time environment.

关键词： Machine learning Deep neural networks Classification Stacking ensemble XSS attack UrL encoding JScript/JavaScript Web security

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

Emission colour tuning in KLnF_(4):Yb^(3+),Er^(3+)/Ho^(3+)phosphor

引用

Journal of rare Earths 2024年第1期42卷 57-65,I0002页

作者： Janani K gayathri E Vijayatha V ramasubramanian S Thiyagarajan P Department of Science and Humanities Nehru Institute of TechnologyKaliapuramThirumalayampalayamCoimbatoreIndia Department of Sciences Amrita School of Physical SciencesAmrita Vishwa VidyapeethamCoimbatoreIndia Department of Physics Anna UniversityChennaiIndia

KLnF_(4):Yb^(3+),Er^(3+)/Ho^(3+)(Ln=Y,Yb,Gd)phosphors were prepared by solid-state reaction *** each of the Yb^(3+)/Er^(3+)and Yb^(3+)/Ho^(3+)co-doped phosphors independently,phase confirmation and morphological examination were accomplished using the X-ray diffraction technique and scanning electron microscope analysis.X-ray photoelectron spectroscopy analysis shows the charge state and existence of lanthanides and *** luminescence emissions of green and red colour were detected for the synthesized *** changes in the upconverted emission intensities and colour output pertaining to the change of the lanthanide host matrix along with dopants were investigated for the prepared *** the upconversion luminescence,erbium-doped samples exhibit a predominance of red emission while holmium-doped samples display a prevalence of green *** rare-earth Er/Ho doped KYbF4shows strong red emission compared to other ***_(4):Yb,Er/Ho exhibits relatively significant green upconve rsion emissions,while Yb,Er-doped KGdF_(4)host displays a 10-fold increase in green/red emission ratio with an increase in the input power of 20-780 *** photoluminescence studies and decay curve analysis were carried out using UV light excitation for the developed phosphors.A higher lifetime of 2.2 ms was measured for the downshifting red emission in the Ho doped KYbF_(4)*** study suggests a potential for colour tunability in the upconversion and downshifting emissions through host modifications to the fluoride phosphor.

关键词： rare earths Energy transfer upconversion Downshifting Colour coordinates

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

Detection and Classification of Diabetic retinopathy Using DCNN and BSN Models

引用

Computers, Materials & Continua 2022年第7期72卷 597-609页

作者： S.Sudha A.Srinivasan T.gayathri Devi Department of ECE SRCSASTRA Deemed UniversityKumbakonamIndia

Diabetes is associated with many complications that could lead to *** retinopathy,a complication of diabetes,is difficult to diagnose and may lead to vision *** identification of micro features in fundus images for the diagnosis of Dr is a complex and challenging task for *** clinical testing involves complex procedures and is timeconsuming,an automated system would help ophthalmologists to detect Dr and administer treatment in a timelymanner so that blindness can be *** research works have focused on image processing algorithms,or neural networks,or signal processing techniques alone to detect diabetic ***,we aimed to develop a novel integrated approach to increase the accuracy of *** approach utilized both convolutional neural networks and signal processing *** this proposed method,the biological electro retinogram(ErG)sensor network(BSN)and deep convolution neural network(DCNN)were developed to detect and classify *** the BSN system,electrodes were used to record ErGsignal,which was preprocessed to be *** was performed in the frequency domain by the application of fast Fourier transform(FFT)and mel frequency cepstral coefficients(MFCCs)were *** neural network(ANN)classifier was used to classify the signals of eyes with Dr and normal ***,fundus images were captured using a fundus camera,and these were used as the input for DCNN-based *** DCNN consisted of many layers to facilitate the extraction of features and classification of fundus images into normal images,non-proliferative Dr(NPDr)or earlystage Dr images,and proliferative Dr(PDr)or advanced-stage Dr ***,it classifiedNPDraccording tomicroaneurysms,hemorrhages,cotton wool spots,and exudates,and the presence of new blood vessels indicated *** accuracy,sensitivity,and specificity of the ANNclassifier were found to be 94%,95%,and 93%,***

关键词： Deep convolution neural network artificial neural network nonproliferative diabetic retinopathy biological ErG sensor network

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

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：