{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T06:48:52Z","timestamp":1777704532711,"version":"3.51.4"},"reference-count":27,"publisher":"SAGE Publications","issue":"5","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IFS"],"published-print":{"date-parts":[[2020,11,19]]},"abstract":"<jats:p>Pulsars are highly magnetized, rotating neutron stars with small volume and high density. The discovery of pulsars is of great significance in the fields of physics and astronomy. With the development of artificial intelligent, image recognition models based on deep learning are increasingly utilized for pulsar candidate identification. However, pulsar candidate datasets are characterized by unbalance and lack of positive samples, which has contributed the traditional methods to fall into poor performance and model bias. To this end, a general image recognition model based on adversarial training is proposed. A generator, a classifier, and two discriminators are included in the model. Theoretical analysis demonstrates that the model has a unique optimal solution, and the classifier happens to be the inference network of the generator. Therefore, the samples produced by the generator significantly augment the diversity of training data. When the model reaches equilibrium, it can not only predict labels for unseen data, but also generate controllable samples. In experiments, we split part of data from MNIST for training. The results reveal that the model not only behaves better classification performance than CNN, but also has better controllability than CGAN and ACGAN. Then, the model is applied to pulsar candidate dataset HTRU and FAST. The results exhibit that, compared with CNN model, the F-score has increased by 1.99% and 3.67%, and the Recall has also increased by 6.28% and 8.59% respectively.<\/jats:p>","DOI":"10.3233\/jifs-200925","type":"journal-article","created":{"date-parts":[[2020,10,13]],"date-time":"2020-10-13T12:51:34Z","timestamp":1602593494000},"page":"7657-7669","source":"Crossref","is-referenced-by-count":2,"title":["A novel image classification model based on adversarial training for pulsar candidate identification"],"prefix":"10.1177","volume":"39","author":[{"given":"Linyong","family":"Zhou","sequence":"first","affiliation":[{"name":"School of Mathematics and Statistics, Guizhou University of Finance and Economics, Huaxi University Town, Guiyang, China"},{"name":"Key Laboratory of Information and Computing Science, Guizhou Normal University, Guiyang, China"}]},{"given":"Shanping","family":"You","sequence":"additional","affiliation":[{"name":"Key Laboratory of Information and Computing Science, Guizhou Normal University, Guiyang, China"}]},{"given":"Bimo","family":"Ren","sequence":"additional","affiliation":[{"name":"School of Mathematics and Statistics, Guizhou University of Finance and Economics, Huaxi University Town, Guiyang, China"}]},{"given":"Xuhong","family":"Yu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Information and Computing Science, Guizhou Normal University, Guiyang, China"}]},{"given":"Xiaoyao","family":"Xie","sequence":"additional","affiliation":[{"name":"Key Laboratory of Information and Computing Science, Guizhou Normal University, Guiyang, China"}]}],"member":"179","reference":[{"key":"10.3233\/JIFS-200925_ref1","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks[C]\/\/","volume":"2012","author":"Krizhevsky","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.3233\/JIFS-200925_ref2","first-page":"818","article-title":"Visualizing and understanding convolutional networks[C]\/\/","volume":"2014","author":"Zeiler","journal-title":"European Conference on Computer Vision. Springer, Cham"},{"issue":"1","key":"10.3233\/JIFS-200925_ref4","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1613\/jair.953","article-title":"SMOTE: synthetic minority over-sampling technique[J]","volume":"16","author":"Chawla","year":"2002","journal-title":"Journal of Artificial Intelligence Research"},{"key":"10.3233\/JIFS-200925_ref5","first-page":"2672","article-title":"Generative adversarial nets[C]\/\/","volume":"2014","author":"Goodfellow","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.3233\/JIFS-200925_ref6","first-page":"448","article-title":"Using generative adversarial networks for improving classification effectiveness in credit card fraud detection[J]","volume":"2017","author":"Fiore","journal-title":"Information Sciences"},{"key":"10.3233\/JIFS-200925_ref7","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1016\/j.procs.2018.08.150","article-title":"Deep Learning for Imbalance Data Classification using Class Expert Generative Adversarial Network[J]","volume":"135","author":"Fanny","year":"2018","journal-title":"Procedia Computer Science"},{"key":"10.3233\/JIFS-200925_ref8","first-page":"1695","article-title":"Generative adversarial minority oversampling[C]\/\/","volume":"2019","author":"Mullick","journal-title":"Proceedings of the IEEE International Conference on Computer Vision"},{"key":"10.3233\/JIFS-200925_ref10","first-page":"2642","article-title":"Conditional image synthesis with auxiliary classifier gans[C]\/\/","volume":"2017","author":"Odena","journal-title":"Proceedings of the 34th International Conference on Machine Learning"},{"key":"10.3233\/JIFS-200925_ref11","first-page":"2234","article-title":"Improved techniques for training gans[C]\/\/","volume":"2016","author":"Salimans","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.3233\/JIFS-200925_ref12","first-page":"4088","article-title":"Triple generative adversarial nets[C]\/\/","volume":"2017","author":"Chongxuan","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.3233\/JIFS-200925_ref13","first-page":"5247","article-title":"Triangle generative adversarial networks[C]\/\/","volume":"2017","author":"Gan","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.3233\/JIFS-200925_ref14","doi-asserted-by":"crossref","first-page":"464","DOI":"10.1016\/j.eswa.2017.09.030","article-title":"Effective data generation for imbalanced learning using conditional generative adversarial networks[J]","volume":"91","author":"Douzas","year":"2018","journal-title":"Expert Systems with Applications"},{"key":"10.3233\/JIFS-200925_ref15","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1016\/j.neucom.2018.09.013","article-title":"GAN-based synthetic medical image augmentation for increased CNN performance in liver lesion classification[J]","volume":"321","author":"Frid-Adar","year":"2018","journal-title":"Neurocomputing"},{"issue":"3","key":"10.3233\/JIFS-200925_ref16","doi-asserted-by":"crossref","first-page":"401","DOI":"10.1093\/mnras\/255.3.401","article-title":"A highfrequency survey of the southern galactic plane for pulsars[J]","volume":"255","author":"Johnston","year":"1992","journal-title":"Monthly Notices of the Royal Astronomical Society"},{"issue":"1","key":"10.3233\/JIFS-200925_ref17","doi-asserted-by":"crossref","first-page":"688","DOI":"10.1093\/mnras\/stt758","article-title":"PEACE: pulsar evaluation algorithm for candidate extraction\u2013a software package for post-analysis processing of pulsar survey candidates[J]","volume":"433","author":"Lee","year":"2013","journal-title":"Monthly Notices of the Royal Astronomical Society"},{"issue":"1","key":"10.3233\/JIFS-200925_ref18","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1111\/j.1365-2966.2004.08310.x","article-title":"The Parkes Multibeam Pulsar Survey -V. Finding binary and millisecond pulsars[J]","volume":"355","author":"Faulkner","year":"2004","journal-title":"Monthly Notices of the Royal Astronomical Society"},{"issue":"4","key":"10.3233\/JIFS-200925_ref19","doi-asserted-by":"crossref","first-page":"2443","DOI":"10.1111\/j.1365-2966.2010.17082.x","article-title":"Selection of radio pulsar candidates using artificial neural networks[J]","volume":"407","author":"Eatough","year":"2010","journal-title":"Monthly Notices of the Royal Astronomical Society"},{"issue":"2","key":"10.3233\/JIFS-200925_ref20","doi-asserted-by":"crossref","first-page":"1052","DOI":"10.1111\/j.1365-2966.2012.22042.x","article-title":"The High Time Resolution Universe Pulsar Survey -VI: An artificial neural network and timing of 75 pulsars[J]","volume":"427","author":"Bates","year":"2012","journal-title":"Monthly Notices of the Royal Astronomical Society"},{"issue":"2","key":"10.3233\/JIFS-200925_ref21","doi-asserted-by":"crossref","first-page":"1651","DOI":"10.1093\/mnras\/stu1188","article-title":"SPINN: a straightforward machine learning solution to the pulsar candidate selection problem[J]","volume":"443","author":"Morello","year":"2014","journal-title":"Monthly Notices of the Royal Astronomical Society"},{"issue":"2","key":"10.3233\/JIFS-200925_ref22","first-page":"109","article-title":"Searching for pulsars using image pattern recognition[J]","volume":"781","author":"Zhu","year":"2014","journal-title":"Physics"},{"issue":"5","key":"10.3233\/JIFS-200925_ref23","first-page":"65","article-title":"Pulsar candidate selection using ensemble networks for FAST drift-scan survey[J]","volume":"62","author":"Wang","year":"2019","journal-title":"Science China(Physics, Mechanics & Astronomy)"},{"key":"10.3233\/JIFS-200925_ref24","first-page":"770","article-title":"Deep residual learning for image recognition[C]\/\/","volume":"2016","author":"He","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"10.3233\/JIFS-200925_ref26","first-page":"1","article-title":"Pulsar candidate recognition with deep learning[J]","volume":"2019","author":"Zhang","journal-title":"Computers & Electrical Engineering"},{"key":"10.3233\/JIFS-200925_ref28","first-page":"1","article-title":"Medical image synthesis for data augmentation and anonymization using generative adversarial networks[C]\/\/","volume":"2018","author":"Shin","journal-title":"International Workshop on Simulation and Synthesis in Medical Imaging"},{"key":"10.3233\/JIFS-200925_ref29","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1016\/j.neucom.2015.10.042","article-title":"A profit-driven artifificial neural network (ANN) with applications to fraud detection and direct marketing[J]","volume":"175","author":"Zakaryazad","year":"2016","journal-title":"Neurocomputing"},{"issue":"2","key":"10.3233\/JIFS-200925_ref30","doi-asserted-by":"crossref","first-page":"434","DOI":"10.1109\/TR.2013.2259203","article-title":"Using Class Imbalance Learning for Software Defect Prediction[J]","volume":"62","author":"Wang","year":"2013","journal-title":"IEEE Transactions on Reliability"},{"issue":"11","key":"10.3233\/JIFS-200925_ref31","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition[J]","volume":"86","author":"LeCun","year":"1998","journal-title":"Proceedings of the IEEE"}],"container-title":["Journal of Intelligent &amp; Fuzzy Systems"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/JIFS-200925","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T09:41:25Z","timestamp":1777455685000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/JIFS-200925"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,11,19]]},"references-count":27,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.3233\/jifs-200925","relation":{},"ISSN":["1064-1246","1875-8967"],"issn-type":[{"value":"1064-1246","type":"print"},{"value":"1875-8967","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,11,19]]}}}