检索结果-南通市图书馆

A novel Optimizer in Deep neural network for Diabetic Retinopathy Classification

Computer Systems Science & Engineering 2022年第12期43卷 1099-1110页

作者： Pranamita nanda n.duraipandian Department of Computer Science and Engineering Velammal Institute of TechnologyChennai601204TamilnaduIndia Department of Computer Science and Engineering Saveetha Engineering CollegeChennai602105TamilnaduIndia

In severe cases, diabetic retinopathy can lead to blindness. For decades,automatic classification of diabetic retinopathy images has been a challenge. Medical image processing has benefited from advances in deep learning systems. Toenhance the accuracy of image classification driven by Convolutional neural network (Cnn), balanced dataset is generated by data augmentation method followed by an optimized algorithm. Deep neural networks (Dnn) are frequentlyoptimized using gradient (GD) based techniques. Vanishing gradient is the maindrawback of GD algorithms. In this paper, we suggest an innovative algorithm, tosolve the above problem, Hypergradient Descent learning rate based Quasi hyperbolic (HDQH) gradient descent to optimize the weights and biases. The algorithms only use first order gradients, which reduces computation time andstorage space requirements. The algorithms do not require more tuning of thelearning rates as the learning rate tunes itself by means of gradients. We presentempirical evaluation of our algorithm on two public retinal image datasets such asMessidor and DDR by using Resnet18 and Inception V3 architectures. The findings of the experiment show that the efficiency and accuracy of our algorithm outperforms the other cutting-edge algorithms. HDQHAdam shows the highestaccuracy of 97.5 on Resnet18 and 95.7 on Inception V3 models respectively.

关键词： Cnn diabetic retinopathy data augmentation gradient descent deep learning optimization

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

Secured Data Storage Using Deduplication in Cloud Computing Based on Elliptic Curve Cryptography

引用

Computer Systems Science & Engineering 2022年第4期41卷 83-94页

作者： n.niyaz Ahamed n.duraipandian Department of Computer Science and Engineering Velammal Engineering CollegeChennai600066India

The tremendous development of cloud computing with related technol-ogies is an unexpected ***,centralized cloud storage faces few chal-lenges such as latency,storage,and packet drop in the *** storage gets more attention due to its huge data storage and ensures the security of secret *** of the developments in cloud storage have been positive except better cost model and effectiveness,but still data leakage in security are billion-dollar questions to *** data security techniques are usually based on cryptographic methods,but these approaches may not be able to with-stand an attack from the cloud server's ***,we suggest a model called multi-layer storage(MLS)based on security using elliptical curve cryptography(ECC).The suggested model focuses on the signiﬁcance of cloud storage along with data protection and removing duplicates at the initial *** on divide and combine methodologies,the data are divided into three ***,theﬁrst two portions of data are stored in the local system and fog nodes to secure the data using the encoding and decoding *** other part of the encrypted data is saved in the *** viability of our model has been tested by research in terms of safety measures and test evaluation,and it is truly a powerful comple-ment to existing methods in cloud storage.

关键词： Cloud storage deduplication fog computing and elliptic curve cryptography

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

Modeling of Optimal Deep Learning Based Flood Forecasting Model Using Twitter Data

引用

Intelligent Automation & Soft Computing 2023年第2期35卷 1455-1470页

作者： G.Indra n.duraipandian Department of Computer Science and Engineering RMK College of Engineering and TechnologyChennai601206India Department of Computer Science and Engineering Saveetha Engineering CollegeChennai602106India

Aﬂood is a signiﬁcant damaging natural calamity that causes loss of life and *** work on the construction ofﬂood prediction models intended to reduce risks,suggest policies,reduce mortality,and limit property damage caused byﬂ*** massive amount of data generated by social media platforms such as Twitter opens the door toﬂood *** of the real-time nature of Twitter data,some government agencies and authorities have used it to track natural catastrophe events in order to build a more rapid rescue ***,due to the shorter duration of Tweets,it is difﬁcult to construct a perfect prediction model for determiningﬂ*** learning(ML)and deep learning(DL)approaches can be used to statistically developﬂood prediction *** the same time,the vast amount of Tweets necessitates the use of a big data analytics(BDA)tool forﬂood *** this regard,this work provides an optimal deep learning-basedﬂood forecasting model with big data analytics(ODLFF-BDA)based on Twitter *** suggested ODLFF-BDA technique intends to anticipate the existence ofﬂoods using tweets in a big data *** ODLFF-BDA technique comprises data pre-processing to convert the input tweets into a usable *** addition,a Bidirectional Encoder Representations from Transformers(BERT)model is used to generate emotive contextual embed-ding from ***,a gated recurrent unit(GRU)with a Multilayer Convolutional neural network(MLCnn)is used to extract local data and predict theﬂ***,an Equilibrium Optimizer(EO)is used toﬁne-tune the hyper-parameters of the GRU and MLCnn models in order to increase prediction *** memory usage is pull down lesser than 3.5 MB,if its compared with the other algorithm *** ODLFF-BDA technique’s performance was validated using a benchmark Kaggle dataset,and theﬁndings showed that it outperformed other recent approaches signiﬁcantly.

关键词： Big data analytics predictive models deep learning ﬂood prediction twitter data hyperparameter tuning

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

Optimal Adaptive Genetic Algorithm Based Hybrid Signcryption Algorithm for Information Security

引用

Computer Modeling in Engineering & Sciences 2015年第5期105卷 47-68页

作者： R.Sujatha M.Ramakrishnan n.duraipandian B.Ramakrishnan Velammal Engineering College Anna UniversityIndia School of Computer Applications Madurai Kamarajar UniversityIndia Department of Computer Science and Research Centre S.T.Hindu CollegeMadurai Kamarajar UniversityIndia

The functions of digital signature and public key encryption are simultaneously fulfilled by signcryption,which is a cryptographic *** securely communicate very large messages,the cryptographic primitive called signcryption efficiently implements the same and while most of the public key based systems are suitable for small messages,hybrid encryption(KEM-DEM)provides a competent and practical *** this paper,we develop a hybrid signcryption *** hybrid signcryption is based on the KEM and DEM *** KEM algorithm utilizes the KDF technique to encapsulate the symmetric *** DEM algorithm utilizes the Adaptive Genetic Algorithm based Elliptic curve cryptography algorithm to encrypt the original ***,for the security purpose,we introduce the three games and we proved the attackers fail to find the security attributes of our proposed signcryption *** proposed algorithm is analyzed with Daniel of Service(DOS),Brute Force attack and Man In Middle(MIM)attacks to ensure the secure data transaction.

关键词： Hybrid Signcryption KEM DEM Adaptive Genetic Algorithm EllipticCurve Cryptography

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

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

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：