检索结果-南通市图书馆

EfficientNetV2 Model for Plant Disease Classification and Pest recognition

Computer systems science & Engineering 2023年第5期45卷 2249-2263页

作者： r.s.sandhya devi V.rVijay Kumar P.sivakumar Department of EEE Kumaraguru College of TechnologyCoimbatore641049India Department of Electronics and Communication Engineering Anna University Regional CampusCoimbatore641046India Department of EEE PSG College of TechnologyCoimbatore641004India

Plant disease classification and prevention of spreading of the disease at earlier stages based on visual leaves symptoms and Pest recognition through deep learning-based image classification is in the forefront of *** perform the investigation on Plant and pest classification,Transfer Learning(TL)approach is used on *** requires limited labelled data and shorter training ***,the limitation of TL is the pre-trained model network’s topology is static and the knowledge acquired is detrimentally overwriting the old ***-V2 is a Convolutional Neural Network(CNN)model with significant high speed learning rates across variable sized *** model employs a form of progressive learning mechanism which expands the network topology gradually over the course of training process improving the model’s learning *** provides a better interpretability of the model’s understanding on the test *** these insights,our work investigates the effectiveness of EfficienetV2 model trained on a class imbalanced dataset for plant disease classification and pest recognition by means of combining TL and progressive learning *** Progressive Learning for TL(PL-TL)is used in our work consisting of 38 classes of PlantVillage dataset of crops and fruit species,5 classes of cassava leaf diseases and another dataset with around 102 classes of crop pest images downloaded from popular dataset platforms,though it is not a benchmark *** test the predictability rate of the model in classifying leaf diseases with similar visual symptoms,Mix-up data augmentation technique is used at the ratio of 1:4 on corn and tomato classes which has high probability of misinterpretation of disease ***,the paper compares the TL approach performed on the above mentioned three types of data set using well established CNN based Inceptionv3,and Vision Transformer a non-CNN *** clearly depicts that EfficientNetV2 has an out

关键词： Image classification transfer learning efficientNetV2 mix-up data augmentation inception V3

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

An Efficient Modelling of Oversampling with Optimal Deep Learning Enabled Anomaly Detection in streaming Data

引用

China Communications 2024年第5期21卷 249-260页

作者： r.rajakumar s.sathiya devi srinivasa ramanujan Centre SASTRA Deemed UniversityKumbakonamTamil Nadu 612001India University College of Engineering BIT CampusAnna UniversityTiruchirappalli 620024India

recently,anomaly detection(AD)in streaming data gained significant attention among research communities due to its applicability in finance,business,healthcare,education,*** recent developments of deep learning(DL)models find helpful in the detection and classification of *** article designs an oversampling with an optimal deep learning-based streaming data classification(Os-ODLsDC)*** aim of the OsODLsDC model is to recognize and classify the presence of anomalies in the streaming *** proposed Os-ODLsDC model initially undergoes preprocessing *** streaming data is unbalanced,support vector machine(sVM)-synthetic Minority Over-sampling Technique(sVM-sMOTE)is applied for oversampling ***,the Os-ODLsDC model employs bidirectional long short-term memory(Bi LsTM)for AD and ***,the root means square propagation(rMsProp)optimizer is applied for optimal hyperparameter tuning of the Bi LsTM *** ensuring the promising performance of the Os-ODLsDC model,a wide-ranging experimental analysis is performed using three benchmark datasets such as CICIDs 2018,KDD-Cup 1999,and NsL-KDD datasets.

关键词： anomaly detection deep learning hyperparameter optimization oversampling sMOTE streaming data

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

Visual Enhancement of Underwater Images Using Transmission Estimation and Multi-scale Fusion

引用

Computer systems science & Engineering 2023年第3期44卷 1897-1910页

作者： r.Vijay Anandh s.rukmani devi Department of Electronics and Communication Engineering RMK College of Engineering and TechnologyTiruvallurTamilnadu601206India Department of Electronics and Communication Engineering RMD Engineering CollegeGummidipundiTamilnadu601206India

The demand for the exploration of ocean resources is increasing *** image data plays a significant role in many research *** this,the visual quality of underwater images is degraded because of two main factors namely,backscattering and ***,visual enhancement has become an essential process to recover the required data from the *** algorithms had been proposed in a decade for improving the quality of *** paper aims to propose a single image enhancement technique without the use of any external *** that,the degraded images are subjected to two main processes namely,color correction and image ***,veiling light and transmission light is estimated tofind the color required for *** light refers to unwanted light,whereas transmission light refers to the required light for color *** estimated outputs are applied in the scene recovery *** image obtained from color correction is subjected to a fusion process where the image is categorized into two versions and applied to white balance and contrast enhancement *** resultants are divided into three weight maps namely,luminance,saliency,chromaticity and fused using the Laplacian *** results obtained are graphically compared with their input data using rGB Histogram ***,image quality is measured and tabulated using underwater image quality measures.

关键词： Underwater image backscattering attenuation image fusion veiling light white balance laplacian pyramid

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

A Novel Outlier Detection with Feature selection Enabled streaming Data Classification

引用

Intelligent Automation & soft Computing 2023年第2期35卷 2101-2116页

作者： r.rajakumar s.sathiya devi Anna University Chennai600025India University College of Engineering BIT CampusAnna UniversityTiruchirappalli620024India

Due to the advancements in information technologies,massive quantity of data is being produced by social media,smartphones,and sensor *** investigation of data stream by the use of machine learning(ML)approaches to address regression,prediction,and classiﬁcation problems have received consid-erable *** the same time,the detection of anomalies or outliers and feature selection(Fs)processes becomes *** study develops an outlier detec-tion with feature selection technique for streaming data classiﬁcation,named ODFsT-sDC ***,streaming data is pre-processed in two ways namely categorical encoding and null value *** addition,Local Correla-tion Integral(LOCI)is used which is signiﬁcant in the detection and removal of ***,red deer algorithm(rDA)based Fs approach is employed to derive an optimal subset of ***,kernel extreme learning machine(KELM)classiﬁer is used for streaming data classiﬁ*** design of LOCI based outlier detection and rDA based Fs shows the novelty of the *** order to assess the classiﬁcation outcomes of the ODFsT-sDC technique,a series of simulations were performed using three benchmark *** experimental results reported the promising outcomes of the ODFsT-sDC technique over the recent approaches.

关键词： streaming data classiﬁcation outlier removal feature selection machine learning metaheuristics

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

A Novel radial Basis Function Neural Network Approach for ECG signal Classification

引用

Intelligent Automation & soft Computing 2023年第1期35卷 129-148页

作者： s.sathishkumar r.devi Priya Department of Information Technology Adhiyamaan College of EngineeringHosur621004India Department of Information Technology Kongu Engineering CollegeErode638060India

ions in the ECG *** cardiologist and medical specialistfind numerous difficulties in the process of traditional *** specified restrictions are eliminated in the proposed *** fundamental aim of this work is tofind the r-r *** analyze the blockage,different approaches are implemented,which make the computation as facile with high *** information are recovered from the MIT-BIH *** retrieved data contain normal and pathological ECG *** obtain a noiseless signal,Gaborfilter is employed and to compute the amplitude of the signal,DCT-DOsT(Discrete cosine based Discrete orthogonal stock well transform)is *** amplitude is computed to detect the cardiac *** r peak of the underlying ECG signal is noted and the segment length of the ECG cycle is *** Genetic algorithm(GA)retrieves the primary highlights and the classifier integrates the data with the chosen attributes to optimize the *** addition,the GA helps in performing hereditary calculations to reduce the problem of multi-target ***,the rBFNN(radial basis function neural network)is applied,which diminishes the local minima present in the *** shows enhancement in characterizing the ordinary and anomalous ECG signals.

关键词： Electrocardiogram signal gaborfilter discrete cosine based discrete orthogonal stock well transform genetic algorithm radial basis function neural 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

ENTrOPY TOLErANT FUZZY C-MEANs IN MEDICAL IMAGEs

引用

Journal of Innovative Optical Health sciences 2011年第4期4卷 447-462页

作者： s.r.KANNAN s.rAMATHILAGAM r.devi YUEH-MIN HUANG Department of Mathematics ramanujan school of Mathematical sciences Pondicherry University India Department of Mathematics Periyar Government College CuddaloreIndia Department of Engineering science National Cheng Kung University TainanTaiwan

segmenting the Dynamic Contrast-Enhanced Breast Magnetic resonance Images(DCE-BMrI)is an extremely important task to diagnose the disease because it has the highest specificity when acquired with high temporal and spatial resolution and is also corrupted by heavy noise,outliers,and other imaging *** this paper,we intend to develop efficient robust segmentation algorithms based on fuzzy clustering approach for segmenting the *** proposed segmentation algorithms have been amalgamated with effective kernel-induced distance measure on standard fuzzy c-means algorithm along with the spatial neighborhood information,entropy term,and tolerance vector into a fuzzy clustering structure for segmenting the *** significant feature of our proposed algorithms is its capability tofind the optimal membership grades and obtain effective cluster centers automatically by minimizing the proposed robust objective ***,this article demonstrates the superiority of the proposed algorithms for segmenting DCE-BMrI in comparison with other recent kernel-based fuzzy c-means *** the clustering accuracies of the proposed algorithms are validated by using silhouette method in comparison with existed fuzzy clustering algorithms.

关键词： Fuzzy clustering algorithms entropy method segmentation medical images

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

An Optimized Transfer Learning Model Based Kidney stone Classification

引用

Computer systems science & Engineering 2023年第2期44卷 1387-1395页

作者： s.devi Mahalakshmi Department of Computer science and Engineering Mepco Schlenk Engineering CollegeSivakasi626005TamilnaduIndia

The kidney is an important organ of humans to purify the *** healthy function of the kidney is always essential to balance the salt,potassium and pH levels in the ***,the failure of kidneys happens easily to human beings due to their lifestyle,eating habits and diabetes *** pre-diction of kidney stones is compulsory for timely *** processing-based diagnosis approaches provide a greater success rate than other detection *** this work,proposed a kidney stone classiﬁcation method based on optimized Transfer Learning(TL).The Deep Convolutional Neural Network(DCNN)models of DenseNet169,MobileNetv2 and GoogleNet applied for clas-siﬁ*** combined classiﬁcation results are processed by ensemble learning to increase classiﬁcation *** hyperparameters of the DCNN model are adjusted by the metaheuristic algorithm of Gorilla Troops Optimizer(GTO).The proposed TL model outperforms in terms of all the parameters compared to other DCNN models.

关键词： DCNN GTO kidney stone transfer learning

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

A review on Efficient routing Mechanisms in Urban scenario of Vehicular Ad⁃Hoc Networks

引用

Journal of Harbin Institute of Technology(New series) 2023年第6期30卷 83-94页

作者： Kalpana devi s Thenmozhi r Department of Computing Technologies SRM Institute of Science and TechnologyKattankulathurChennai 603203India

Efficient routing protocols are crucial for enabling secure communication among the highly mobile and self-configurable nodes in Vehicular Ad-Hoc Networks(VANETs). In this work, we present a performance evaluation of different routing protocols in VANETs based on the currently available research. Our study focuses on analyzing the strength and weaknesses of the routing protocols, namely, Ad-Hoc On-demand Distance Vector(AODV), Dynamic source routing(Dsr), and Destination-sequenced Distance-Vector(DsDV), under varying network conditions. We examine the protocols’ performance based on key metrics such as throughput, delay, and energy consumption. We also highlight the advantages and limitations of each protocol in different scenarios, such as varying vehicular densities and mobility patterns. Our results show that AODV outperforms Dsr and DsDV in terms of throughput and delay, while Dsr consumes the least energy. We also observe that the performance of the routing protocols varies with the density of vehicles and the mobility patterns of the nodes. Our study highlights the importance of conducting real-world experiments to evaluate the performance of routing protocols in VANETs, as they provide more realistic and accurate results than simulation-based studies. Our findings can help in the selection and design of efficient and secure routing protocols for VANETs.

关键词： routing metrics VANET mobile nodes simulation

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 Novel Fuzzy Inference system-Based Endmember Extraction in Hyperspectral Images

引用

Intelligent Automation & soft Computing 2023年第8期37卷 2459-2476页

作者： M.r.Vimala devi s.Kalaivani school of Electronics Engineering Vellore Institute of TechnologyVellore632051India

spectral unmixing helps to identify different components present in the spectral mixtures which occur in the uppermost layer of the area owing to the low spatial resolution of hyperspectral *** spectral unmixing methods are globally based and do not consider the spectral variability among its endmembers that occur due to illumination,atmospheric,and environmental ***,endmember bundle extraction plays a major role in overcoming the above-mentioned limitations leading to more accurate abundance ***,a two-stage approach is proposed to extract endmembers through endmember bundles in hyperspectral *** divide and conquer method is applied as the first step in subset images with only the non-redundant bands to extract endmembers using the Vertex Component Analysis(VCA)and N-FINDr algorithms.A fuzzy rule-based inference system utilizing spectral matching parameters is proposed in the second step to categorize *** endmember with the minimum error is chosen as the final endmember in each specific *** proposed method is simple and automatically considers endmember variability in hyperspectral *** efficiency of the proposed method is evaluated using two real hyperspectral *** average spectral angle and abundance angle are used to analyze the performance measures.

关键词： Hyperspectral image spectral unmixing spectral matching endmember bundles fuzzy inference system

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

FUZZY.C-MEANs IN FINDING sUBTYPEs OF CANCErs IN CANCEr DATABAsE

引用

Journal of Innovative Optical Health sciences 2014年第1期7卷 109-128页

作者： s.r.KANNAN s.rAMTHILAGAM r.devi T.P.HONG Department of Mathematics Pondicherry Central University India Department of Mathematics Periyar Government College Tamil Nadu Department of Computer science and Information Engineering National University of Kaohsiung Taiwan

Finding subtypes of cancer in breast cancer database is an extremely dificult task because ofheavy noise by measurement *** of the recent clustering techniques for breast cancerdatabase to achieve cancerous and noncancerous often weigh down the interpretability of ***,this paper tries to find effective Fuzzy C-Means-based clustering techniques toidentify the proper subtypes of cancer in breast cancer database,This paper obtains the objectivefunction of ffective Fuzzy C-Means clustering techriques by incorporating the kermel induceddist ance function,renyi's entropy function,weighted dist ance measure and neighborhood ternsbased spatial *** efectiveness of the proposed methods are proved through the ex-perimental works on Lung cancer database,IrIs dataset,Wine dat aset,Checkerboard dataset,Time series dataset and Yeast ***,the proposed methods are implemented suc-cesfully to cluster the breast cancer dat abase into cancerous and *** clusteringaccuracy has been validat ed through error matrix and silhouette method.

关键词： Fuzzy C-Means kenel induced distance entropy terms cancer database

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：