Pub Date : 2022-09-30DOI: 10.1007/s12530-022-09464-y
S P Porkodi, V Sarada, Vivek Maik, K Gurushankar
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.
{"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":"<p><p>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.</p>","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}
Pub Date : 2022-09-28DOI: 10.1007/s12530-022-09469-7
Z. Sabir, R. Zahoor, Mohamed R. Ali, R. Sadat
{"title":"An advance computational intelligent approach to solve the third kind of nonlinear pantograph Lane–Emden differential system","authors":"Z. Sabir, R. Zahoor, Mohamed R. Ali, R. Sadat","doi":"10.1007/s12530-022-09469-7","DOIUrl":"https://doi.org/10.1007/s12530-022-09469-7","url":null,"abstract":"","PeriodicalId":12174,"journal":{"name":"Evolving Systems","volume":"29 6 1","pages":"393-412"},"PeriodicalIF":3.2,"publicationDate":"2022-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88347246","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"An effective shunt active power filter based on novel binary multilevel inverter and optimal type-2 fuzzy system to accurately mitigate harmonic currents","authors":"Hossein Toopchizadeh, Mostafa Zallaghi, Mosayeb Moradi, Saeid Shahmoradi","doi":"10.1007/s12530-022-09465-x","DOIUrl":"https://doi.org/10.1007/s12530-022-09465-x","url":null,"abstract":"","PeriodicalId":12174,"journal":{"name":"Evolving Systems","volume":"97 1","pages":"783 - 800"},"PeriodicalIF":3.2,"publicationDate":"2022-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73596647","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-09-26DOI: 10.1007/s12530-022-09470-0
Qingxia Li, Anbing Fu, Wenhong Wei, Yuhui Zhang
{"title":"A trust region based local Bayesian optimization without exhausted optimization of acquisition function","authors":"Qingxia Li, Anbing Fu, Wenhong Wei, Yuhui Zhang","doi":"10.1007/s12530-022-09470-0","DOIUrl":"https://doi.org/10.1007/s12530-022-09470-0","url":null,"abstract":"","PeriodicalId":12174,"journal":{"name":"Evolving Systems","volume":"6 1","pages":"839 - 858"},"PeriodicalIF":3.2,"publicationDate":"2022-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79862561","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-09-24DOI: 10.1007/s12530-022-09468-8
Lianglei Sun, Hong-Yang Lin, Wanbo Yu, Yan Zhang
{"title":"Application of feature extraction using nonlinear dynamic system in face recognition","authors":"Lianglei Sun, Hong-Yang Lin, Wanbo Yu, Yan Zhang","doi":"10.1007/s12530-022-09468-8","DOIUrl":"https://doi.org/10.1007/s12530-022-09468-8","url":null,"abstract":"","PeriodicalId":12174,"journal":{"name":"Evolving Systems","volume":"38 1","pages":"825 - 838"},"PeriodicalIF":3.2,"publicationDate":"2022-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77643539","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-09-21DOI: 10.1007/s12530-022-09462-0
Md Saquib Jawed, Mohammad Sajid
{"title":"XECryptoGA: a metaheuristic algorithm-based block cipher to enhance the security goals","authors":"Md Saquib Jawed, Mohammad Sajid","doi":"10.1007/s12530-022-09462-0","DOIUrl":"https://doi.org/10.1007/s12530-022-09462-0","url":null,"abstract":"","PeriodicalId":12174,"journal":{"name":"Evolving Systems","volume":"51 1","pages":"749 - 770"},"PeriodicalIF":3.2,"publicationDate":"2022-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73512774","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-09-18DOI: 10.1007/s12530-022-09460-2
Q. Guo, Hao Peng
{"title":"A novel multilevel color image segmentation technique based on an improved firefly algorithm and energy curve","authors":"Q. Guo, Hao Peng","doi":"10.1007/s12530-022-09460-2","DOIUrl":"https://doi.org/10.1007/s12530-022-09460-2","url":null,"abstract":"","PeriodicalId":12174,"journal":{"name":"Evolving Systems","volume":"9 1","pages":"685 - 733"},"PeriodicalIF":3.2,"publicationDate":"2022-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85260285","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-09-15DOI: 10.1007/s12530-022-09461-1
K. Balakrishnan, R. Dhanalakshmi, M. Akila, B. B. Sinha
{"title":"Improved equilibrium optimization based on Levy flight approach for feature selection","authors":"K. Balakrishnan, R. Dhanalakshmi, M. Akila, B. B. Sinha","doi":"10.1007/s12530-022-09461-1","DOIUrl":"https://doi.org/10.1007/s12530-022-09461-1","url":null,"abstract":"","PeriodicalId":12174,"journal":{"name":"Evolving Systems","volume":"138 1","pages":"735 - 746"},"PeriodicalIF":3.2,"publicationDate":"2022-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81207239","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
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.
{"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":"<p><p>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.</p>","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}
Pub Date : 2022-08-14DOI: 10.1007/s12530-022-09458-w
K. Bodha, V. Mukherjee, V. Yadav
{"title":"A player unknown's battlegrounds ranking based optimization technique for power system optimization problem","authors":"K. Bodha, V. Mukherjee, V. Yadav","doi":"10.1007/s12530-022-09458-w","DOIUrl":"https://doi.org/10.1007/s12530-022-09458-w","url":null,"abstract":"","PeriodicalId":12174,"journal":{"name":"Evolving Systems","volume":"13 1","pages":"295-317"},"PeriodicalIF":3.2,"publicationDate":"2022-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87557260","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号