Evolving Systems最新文献_第9页

Generic image application using GANs (Generative Adversarial Networks): A Review. 基于生成对抗网络的通用图像应用综述。

IF 2.7 4区计算机科学

Evolving Systems Pub Date : 2022-09-30 DOI: 10.1007/s12530-022-09464-y

S P Porkodi, V Sarada, Vivek Maik, K Gurushankar

{"title":"Generic image application using GANs (Generative Adversarial Networks): A Review.","authors":"S P Porkodi, V Sarada, Vivek Maik, K Gurushankar","doi":"10.1007/s12530-022-09464-y","DOIUrl":"10.1007/s12530-022-09464-y","url":null,"abstract":"The generative adversarial network (GAN), which has received considerable notice for its outstanding data generating abilities, is one of the most intriguing fields of artificial intelligence study. Large volumes of data are required to develop generalizable deep learning models. GANs are a highly strong class of networks capable of producing believable new pictures from unlabeled source prints and labeled medical imaging data is scarce and costly to produce. Despite GAN's remarkable outcomes, steady training remains a challenge. The goal of this study is to perform a complete evaluation of the GAN-related literature and to present a succinct summary of existing knowledge on GAN, including the theory following it, its intended purpose, potential base model alterations, and latest breakthroughs in the area. This article will aid you in gaining a comprehensive grasp of GAN and provide an overview of GAN and its many model types, as well as common implementations, measurement parameter suggestions, and GAN applications in image processing. It will also go over the several applications of GANs in image processing, as well as their benefits and limitations, as well as its prospective reach.","PeriodicalId":12174,"journal":{"name":"Evolving Systems","volume":"84 1","pages":"1-15"},"PeriodicalIF":2.7,"publicationDate":"2022-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9523650/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83845029","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

An advance computational intelligent approach to solve the third kind of nonlinear pantograph Lane–Emden differential system 一种求解第三类非线性受电弓Lane-Emden微分系统的先进计算智能方法

IF 3.2 4区计算机科学

Evolving Systems Pub Date : 2022-09-28 DOI: 10.1007/s12530-022-09469-7

Z. Sabir, R. Zahoor, Mohamed R. Ali, R. Sadat

引用次数: 1

A trust region based local Bayesian optimization without exhausted optimization of acquisition function 一种基于信任域的局部贝叶斯优化算法

IF 3.2 4区计算机科学

Evolving Systems Pub Date : 2022-09-26 DOI: 10.1007/s12530-022-09470-0

Qingxia Li, Anbing Fu, Wenhong Wei, Yuhui Zhang

引用次数: 0

An effective shunt active power filter based on novel binary multilevel inverter and optimal type-2 fuzzy system to accurately mitigate harmonic currents 一种基于新型二值多电平逆变器和最优2型模糊系统的有效并联有源电力滤波器，能准确地缓解谐波电流

IF 3.2 4区计算机科学

Evolving Systems Pub Date : 2022-09-26 DOI: 10.1007/s12530-022-09465-x

Hossein Toopchizadeh, Mostafa Zallaghi, Mosayeb Moradi, Saeid Shahmoradi

引用次数: 1

Application of feature extraction using nonlinear dynamic system in face recognition 非线性动态系统特征提取在人脸识别中的应用

IF 3.2 4区计算机科学

Evolving Systems Pub Date : 2022-09-24 DOI: 10.1007/s12530-022-09468-8

Lianglei Sun, Hong-Yang Lin, Wanbo Yu, Yan Zhang

引用次数: 0

XECryptoGA: a metaheuristic algorithm-based block cipher to enhance the security goals XECryptoGA:基于元启发式算法的分组密码，以提高安全性目标

IF 3.2 4区计算机科学

Evolving Systems Pub Date : 2022-09-21 DOI: 10.1007/s12530-022-09462-0

Md Saquib Jawed, Mohammad Sajid

引用次数: 12

A novel multilevel color image segmentation technique based on an improved firefly algorithm and energy curve 基于改进的萤火虫算法和能量曲线的多级彩色图像分割技术

IF 3.2 4区计算机科学

Evolving Systems Pub Date : 2022-09-18 DOI: 10.1007/s12530-022-09460-2

Q. Guo, Hao Peng

引用次数: 1

Improved equilibrium optimization based on Levy flight approach for feature selection 基于Levy飞行方法的特征选择改进平衡优化

IF 3.2 4区计算机科学

Evolving Systems Pub Date : 2022-09-15 DOI: 10.1007/s12530-022-09461-1

K. Balakrishnan, R. Dhanalakshmi, M. Akila, B. B. Sinha

引用次数: 2

Tackling over-smoothing in multi-label image classification using graphical convolution neural network. 利用图形卷积神经网络解决多标签图像分类中的过度平滑问题。

IF 2.7 4区计算机科学

Evolving Systems Pub Date : 2022-09-07 DOI: 10.1007/s12530-022-09463-z

Vikas Chauhan, Aruna Tiwari, Boppudi Venkata, Vislavath Naik

{"title":"Tackling over-smoothing in multi-label image classification using graphical convolution neural network.","authors":"Vikas Chauhan, Aruna Tiwari, Boppudi Venkata, Vislavath Naik","doi":"10.1007/s12530-022-09463-z","DOIUrl":"10.1007/s12530-022-09463-z","url":null,"abstract":"The importance of the graphical convolution network in multi-label classification has grown in recent years due to its label embedding representation capabilities. The graphical convolution network is able to capture the label dependencies using the correlation between labels. However, the graphical convolution network suffers from an over-smoothing problem when the layers are increased in the network. Over-smoothing makes the nodes indistinguishable in the deep graphical convolution network. This paper proposes a normalization technique to tackle the over-smoothing problem in the graphical convolution network for multi-label classification. The proposed approach is an efficient multi-label object classifier based on a graphical convolution neural network that tackles the over-smoothing problem. The proposed approach normalizes the output of the graph such that the total pairwise squared distance between nodes remains the same after performing the convolution operation. The proposed approach outperforms the existing state-of-the-art approaches based on the results obtained from the experiments performed on MS-COCO and VOC2007 datasets. The experimentation results show that pairnorm mitigates the effect of over-smoothing in the case of using a deep graphical convolution network.","PeriodicalId":12174,"journal":{"name":"Evolving Systems","volume":"44 1","pages":"1-11"},"PeriodicalIF":2.7,"publicationDate":"2022-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9451128/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79445647","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A player unknown's battlegrounds ranking based optimization technique for power system optimization problem 基于玩家未知战场排名的电力系统优化技术

IF 3.2 4区计算机科学

Evolving Systems Pub Date : 2022-08-14 DOI: 10.1007/s12530-022-09458-w

K. Bodha, V. Mukherjee, V. Yadav

引用次数: 54