检索结果-南通市图书馆

Deep Residual Network Based on Image Priors for Single Image Super Resolution in FFA Images

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 Modeling in Engineering & Sciences 2020年第10期125卷 125-143页

作者： G.R.Hemalakshmi D.Santhi V.R.S.Mani a.geetha N.B.Prakash National Engineering College Kovilpatti628503India

Diabetic retinopathy,aged macular degeneration,glaucoma *** widely prevalent ocular pathologies which are irreversible at advanced *** learning based automated detection of these pathologies facilitate timely clinical interventions,preventing adverse *** screen these pathologies with fundus Fluorescein Angiography Images(FFA)which capture retinal components featuring diverse morphologies such as retinal vasculature,macula,optical disk ***,these images have low resolutions,hindering the accurate detection of ocular *** of high resolution images from these images,by super resolution approaches expedites the diagnosis of pathologies with better *** paper presents a deep learning network for Single Image Super Resolution(SISR)of fundus fluorescein angiography images,modeled on residual learning,gridded interpolation and Swish activation *** image prior for this network is constructed by gridded interpolation which provides better image fidelity compared to other *** of the performance of this network and comparative analysis with benchmark architectures,on a standard dataset shows that the proposed network is superior with respect to performance metrics and computational time.

关键词： SISR FFA residual network gridded interpolation swish function

Performance Analysis of a Heterogeneous Network Employing DAPSK Based OFDMA-PON

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

China Communications 2023年第3期20卷 128-145页

作者： Priyadharshini Rajasekaran geetha Ganesan Department of Electronics and Communication Engineering Sri Venkateswara College of EngineeringSriperumbudur 602117Tamil NaduIndia Department of Electronics and Communication Engineering College of Engineering GuindyAnna UniversityChennai 600025Tamil NaduIndia

Recent mobile broadband networks require heterogeneous networks supporting high capacity on demand.A hybrid Fiber-Wireless(Fi-Wi)access network integrating Differential Amplitude and Phase Shift Keying(DAPSK)based-Orthogonal Frequency Division Multiple Access(OFDMA)Passive Optical Network(PON)and 4G wireless network using Radio over Fiber(Ro F)technique is *** proposed heterogeneous network is simulated,and the performance is analyzed in terms of Bit Error Rate(BER),Error Vector Magnitude(EVM),Capacity,and Spectral *** proposed network is simulated considering a higher data rate of 10 and 25 Gbps,and the effect of system parameters like Laser Power,Fiber Length,and Number of users is *** results show that a higher network capacity of 720 Gbps with an average capacity of about 45 Gbps and a higher spectral efficiency of 4.85 bps/Hz is achieved for the multi-user heterogeneous network link with sixteen *** minimum value of optical power sufficient to achieve the desired BER is found to be-6 *** suitability of the proposed integrated architecture in supporting multiple services is analyzed by considering different services at each *** spectral efficiency of the multi-service link varies from 3 to 4 bps/Hz.

关键词： DAPSK OFDMA PON RoF Spectral ef-ficiency

Multi-Objective Modified Particle Swarm Optimization for Test Suite Reduction(MOMPSO)

在线全文

学校读者我要写书评

暂无评论

Computer Systems Science & Engineering 2022年第9期42卷 899-917页

作者： U.geetha Sharmila Sankar Department of Information Technology B.S.Abdur Rahman Crescent Institute of Science and TechnologyChennai600048India Department of Computer Science and Engineering B.S.Abdur Rahman Crescent Institute of Science and TechnologyChennai600048India

Software testing plays a pivotal role in entire software development *** provides researchers with extensive opportunities to develop novel methods for the optimized and cost-effective test suite Although implementation of such a cost-effective test suite with regression testing is being under exploration still it contains lot of challenges and flaws while incorporating with any of the new regression testing algorithm due to irrelevant test cases in the test suite which are not *** kinds of irrelevant test cases might create certain challenges such as code-coverage in the test suite,fault-tolerance,defects due to uncovered-statements and overall-performance at the time of *** this objective,the proposed a new Modified Particle Swarm optimization used for multi-objective test suite *** experiment results involving six subject programs show that MOMPSO method can outer perform with respect to both reduction rate(90.78%to 100%)and failure detection rate(44.56%to 55.01%).Results proved MOMPSO outperformed the other stated algorithms.

关键词： Regression testing test suite reduction test case generation

Outlier detection in neutrosophic sets by using rough entropy based weighted density method

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

CAAI Transactions on Intelligence Technology 2020年第2期5卷 121-127页

作者： Tamilarasu Sa.geetha geetha Mary Amalanathan SCOPE Vellore Institute of TechnologyVelloreIndia

Neutrosophy is the study of neutralities,which is an extension of discussing the truth of *** logic can be applied to any field,to provide the solution for indeterminacy *** of the real-world data have a problem of inconsistency,indeterminacy and *** sets provide a solution for uncertainties,and intuitionistic fuzzy sets handle incomplete information,but both concepts failed to handle indeterminate *** handle this complicated situation,researchers require a powerful mathematical tool,naming,neutrosophic sets,which is a generalised concept of fuzzy and intuitionistic fuzzy *** sets provide a solution for both incomplete and indeterminate *** has mainly three degrees of membership such as truth,indeterminacy and *** values are obtained from the three degrees of membership by cut relation *** items which contrast from other objects by their qualities are *** weighted density outlier detection method based on rough entropy calculates weights of each object and *** the obtained weighted values,the threshold value is fixed to determine *** analysis of the proposed method has been carried out with neutrosophic movie dataset to detect outliers and also compared with existing methods to prove its performance.

关键词： method. entropy incomplete

Role of Ag microalloying on glass forming ability and crystallization kinetics of ZrCoAgAlNi amorphous alloy

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Physics B 2021年第1期30卷 471-476页

作者： A Surendar K geetha C Rajan M Alaazim Department of Pharmacology Saveetha Dental College and HospitalSaveetha Institute of Medical and Technical SciencesChennaiIndia CSE Excel Engineering CollegePallakapalayamKomarapalayam637303India IT K S Rangasamy College of Technology TiruchengodeNamakkalTamil Nadu 637215India Faculty of Engineering Universitas Muhammadiyah Surakarta(UMS)Indonesia

Bulk metallic glasses(BMGs) with new chemical compositions(ZrCoAgAlNi) were fabricated and the effects of Ag minor addition on the glass forming ability(GFA) and crystallization kinetics were studied. The x-ray diffraction(XRD) test was applied to identify the amorphousness of BMGs or possible crystalline phases. Using differential scanning calorimeter(DSC), the thermal stability and crystallization kinetics under a non-isothermal condition at the different heating rates were studied. Considering the heating rate dependency of glass transition and crystallization kinetics, the activation energy was evaluated and measured for the mentioned processes. It was revealed that the rise in Ag content led to the decrease in activation energy for glass transition, while the activation energy for crystallization increased. The thermal stability and GFA were also studied and it was found that the Ag addition strongly affected the inherent features of BMGs. With the increase in Ag content, the atomic mobility and structural rearrangement changed in the material and consequently, the GFA and thermal stability were significantly improved.

关键词： bulk metallic glass materials design crystallization kinetics glass forming ability

Chemical composition and anti-inflammatory activity of Boswellia ovalifoliolata essential oils from leaf and bark

在线全文

学校读者我要写书评

暂无评论

Journal of Forestry Research 2018年第2期29卷 370-378页

作者： Venkatesan geetha Sarada Nallani Chakravarthula Department of Chemistry School of Advanced SciencesVIT University

We isolated the essential oils from Boswellia ovalifoliolata *** and *** using hydrodistillation,identified the obtained compounds using gas chromatography–mass spectrometry(GC–MS) and Fourier transform-infrared spectroscopy(FT-IR),and studied the photophysical and electrochemical properties using UV–visible and fluorescence spectroscopy and cyclic *** the basis of GC–MS spectra,38 compounds were identified in the essential oil from leaves and 26 in the oil from *** bark oil contained 13.44% b-Farnesene(sesquiterpene),10.45% caryophyllene oxide(sesquiterpene) and 6.6% spathulenol,(2 Z,6 E)-(sesquiterpene alcohol); the leaf oil contained 11.1% spathulenol(sesquiterpene alcohol),9.0% caryophyllene oxide(sesquiterpenoids) and 6.3% decyl acetate(ester).FT-IR spectra confirmed the presence of aliphatic aldehydes and ketones,carboxylic acid,alcohols,esters and ethers in both oil ***–visible absorption spectra showed maximum absorbance at 245,290 and 402 nm for bark oil,and 250,285 and 325 nm for *** oil showed strong emission with maximum emission wavelength at 456 nm was higher than that of leaf oil at 414 *** essential oil had significant anti-inflammatory activity,and the reduction potential of the leaf oil was-0.44 and-0.56 e V for bark.

关键词： Essential oil Boswellia ovalifoliolata Gas chromatography–mass spectrometry Fourier transforminfrared spectroscopy Cyclic voltammetry fluorescence spectroscopy

Comparative analysis of entanglement measures based on monogamy inequality

在线全文

学校读者我要写书评

暂无评论

Chinese Physics B 2017年第5期26卷 52-59页

作者： P J geetha Sudha K S Mallesh Department of Physics Kuvempu University Shankaraghatta Shimoga-577 451 India Inspire Institute Inc. Alexandria Virginia 22303 USA Department of Studies in Physics University of Mysore Mysore-570 006 India

We evaluate the monogamy inequality for symmetric, non-symmetric pure states of importance in terms of squared concurrence, squared entanglement of formation, squared negativity of partial transpose and compare the corresponding tangles. We show that though concurrence and concurrence tangle are zero for two special classes of mixed entangled states, both negativity tangle and entanglement of formation（EOF） tangle turn out to be non-zero. A comparison of different tangles is carried out in each case and it is shown that while the concurrence tangle captures the genuine multiqubit entanglement in N-qubit pure states with N distinct spinors（containing GHZ and superposition of W-, obverse W states）either negativity tangle or EOF tangle is to be used as a better measure of entanglement in the W-class of states with two distinct spinors and in the special classes of mixed multiqubit states.

关键词： entanglement tangle negativity superposition inequality entangled symmetric vanishing squared arbitrary

Hydroalcoholic extract of licorice(Glycyrrhiza glabra L.) root attenuates ethanol and cerulein induced pancreatitis in rats

在线全文

学校读者我要写书评

暂无评论

Asian Pacific Journal of Tropical Biomedicine 2019年第10期9卷 424-433页

作者： Sarmishta Srikantam geetha Arumugam Department of Biochemistry Bharathi Women’s CollegeBroadwayChennaiIndia Dr.Ambedkar Government Arts College VyasarpadiChennaiIndia

Objective:To evaluate the therapeutic potential of hydroalcoholic extract of licorice root against ethanol and cerulein induced chronic pancreatitis in ***:The phytochemical profile of hydroalcoholic extract of licorice root was determined by high performance liquid chromatography(HPLC)and gas chromatography coupled to mass spectrometry(GC-MS).Chronic pancreatitis was induced in male albino Wistar rats by feeding them a diet containing ethanol(0%-36%of total calories)for 4 weeks and cerulein(20μg/kg ***,i.p.)thrice a week for 3 *** and amylase in serum,lipid peroxides and antioxidants including reduced glutathione,glutathione peroxidase,superoxide dismutase and catalase in pancreas were *** response was measured by myeloperoxidase in the pancreas,caspase-1 and the concentrations of IL-1 as and liver was carried oαand IL-18 in ***,histological evaluation of the ***:Different flavonoids and saponins were identified in the hydroalcoholic extract of licorice root through HPLC and GC-MS.A marked increase in the levels of serum lipase,amylase,lipid peroxides,caspase-1,myeloperoxidase,IL-1 in the levels of antioxidants were observed after ethanoα,and IL-18 and a marked decrease l and cerulein *** with hydroalcoholic extract of licorice root attenuated these *** addition,histological observation confirmed the protective effect of the extract in the pancreas and liver against inflammatory changes induced by ethanol and ***:The licorice root extract attenuates ethanol and cerulein induced pancreatitis in rats probably due to its antioxidant phytonutrients since ethanol and cerulein-induced production of reactive oxygen species contributes to severe inflammation in the pancreas.

关键词： Pancreatitis ROS Inflammation Glycyrrhiza glabra HPLC GC-MS

FG-SMOTE:Fuzzy-based Gaussian synthetic minority oversampling with deep belief networks classifier for skewed class distribution

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 2021年第2期14卷 269-286页

作者： Putta Hemalatha.geetha Mary Amalanathan SCOPE Vellore Institute of TechnologyVelloreIndia

Purpose-Adequate resources for learning and training the data are an important constraint to develop an efficient classifier with outstanding *** data usually follows a biased distribution of classes that reflects an unequal distribution of classes within a *** issue is known as the imbalance problem,which is one of the most common issues occurring in real-time *** of imbalanced datasets is a ubiquitous challenge in the field of data *** data degrades the performance of the classifier by producing inaccurate ***/methodology/approach-In the proposed work,a novel fuzzy-based Gaussian synthetic minority oversampling(FG-SMOTE)algorithm is proposed to process the imbalanced *** mechanism of the Gaussian SMOTE technique is based on finding the nearest neighbour concept to balance the ratio between minority and majority class *** ratio of the datasets belonging to the minority and majority class is balanced using a fuzzy-based Levenshtein distance measure ***-The performance and the accuracy of the proposed algorithm is evaluated using the deep belief networks classifier and the results showed the efficiency of the fuzzy-based Gaussian SMOTE technique achieved an AUC:93.7%.F1 Score Prediction:94.2%,Geometric Mean Score:93.6%predicted from confusion *** limitations/implications-The proposed research still retains some of the challenges that need to be focused such as application FG-SMOTE to multiclass imbalanced dataset and to evaluate dataset imbalance problem in a distributed ***/value-The proposed algorithm fundamentally solves the data imbalance issues and challenges involved in handling the imbalanced ***-SMOTE has aided in balancing minority and majority class datasets.

关键词： Imbalanced data Gaussian SMOTE Levenshtein distance measure technique Skewed class distribution Fuzzy based Gaussian SMOTE Deep learning Deep belief network classifie