Fuzzy and SVM Based Classification Model to Classify Spectral Objects in Sloan Digital Sky

被引:2
作者
Karn, Arodh Lal [1 ]
Tavera Romero, Carlos Andres [2 ]
Sengan, Sudhakar [3 ]
Mehbodniya, Abolfazl [4 ]
Webber, Julian L. [4 ]
Pustokhin, Denis A. [5 ]
Wende, Frank-Detlef [6 ]
机构
[1] Xian Jiaotong Liverpool Univ, Sch Math & Phys, Dept Financial & Actuarial Math, Suzhou 215123, Peoples R China
[2] Univ Santiago Cali, Fac Engn, COMBA R&D Lab, Cali 76001, Colombia
[3] PSN Coll Engn & Technol, Dept Comp Sci & Engn, Tirunelveli 627152, India
[4] Kuwait Coll Sci & Technol, Dept Elect & Commun Engn, Kuwait, Kuwait
[5] State Univ Management, Dept Logist, Moscow 109542, Russia
[6] Financial Univ Govt Russian Federat, Fac Econ & Business, Dept Logist & Mkt, Moscow 125993, Russia
关键词
Support vector machines; Machine learning; Feature extraction; Telescopes; Principal component analysis; Fuzzy logic; Fuzzy sets; Astronomy; Sloan digital sky; fuzzy logic; fuzzy control; support vector machine; nearest neighbor; machine learning; astronomical; kernel principal component analysis; SUPPORT VECTOR MACHINES; AUTOMATED CLASSIFICATION; DATA SETS; GALAXIES; SMOTE;
D O I
10.1109/ACCESS.2022.3207480
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
The Sloan Digital Sky Survey (SDSS) comprises about one billion objects classified spectrometrically. Because astronomical datasets are so enormous, manually classifying them is nearly impossible-a huge dataset results in class imbalance and overfitting. We recommend a framework in this research study that overcomes these constraints. The framework uses a hybrid Synthetic Minority Oversampling Technique + Edited Nearest Neighbor (SMOTE + ENN) balancer. The balanced dataset is then used to extract features via a non-linear algorithm using Kernel Principal Component Analysis (KPCA). The features are then passed into the proposed Int-T2-Fuzzy Support Vector Machine classifier, which uses a modified type reducer and inference engine to achieve more precise categorization. Using the Sloan Digital Sky Survey dataset and a number of evaluation metrics, the SMOTE+ENN model's performance is measured. The research shows that the model does a good job.
引用
收藏
页码:101276 / 101291
页数:16
相关论文
共 55 条
[1]   Applying support vector machines to imbalanced datasets [J].
Akbani, R ;
Kwek, S ;
Japkowicz, N .
MACHINE LEARNING: ECML 2004, PROCEEDINGS, 2004, 3201 :39-50
[2]   THE ELEVENTH AND TWELFTH DATA RELEASES OF THE SLOAN DIGITAL SKY SURVEY: FINAL DATA FROM SDSS-III [J].
Alam, Shadab ;
Albareti, Franco D. ;
Allende Prieto, Carlos ;
Anders, F. ;
Anderson, Scott F. ;
Anderton, Timothy ;
Andrews, Brett H. ;
Armengaud, Eric ;
Aubourg, Eric ;
Bailey, Stephen ;
Basu, Sarbani ;
Bautista, Julian E. ;
Beaton, Rachael L. ;
Beers, Timothy C. ;
Bender, Chad F. ;
Berlind, Andreas A. ;
Beutler, Florian ;
Bhardwaj, Vaishali ;
Bird, Jonathan C. ;
Bizyaev, Dmitry ;
Blake, Cullen H. ;
Blanton, Michael R. ;
Blomqvist, Michael ;
Bochanski, John J. ;
Bolton, Adam S. ;
Bovy, Jo ;
Bradley, A. Shelden ;
Brandt, W. N. ;
Brauer, D. E. ;
Brinkmann, J. ;
Brown, Peter J. ;
Brownstein, Joel R. ;
Burden, Angela ;
Burtin, Etienne ;
Busca, Nicolas G. ;
Cai, Zheng ;
Capozzi, Diego ;
Rosell, Aurelio Carnero ;
Carr, Michael A. ;
Carrera, Ricardo ;
Chambers, K. C. ;
Chaplin, William James ;
Chen, Yen-Chi ;
Chiappini, Cristina ;
Chojnowski, S. Drew ;
Chuang, Chia-Hsun ;
Clerc, Nicolas ;
Comparat, Johan ;
Covey, Kevin ;
Croft, Rupert A. C. .
ASTROPHYSICAL JOURNAL SUPPLEMENT SERIES, 2015, 219 (01)
[3]  
Astro, 2020, ASTRON ASTROPHYS
[4]   Robust machine learning applied to astronomical data sets. I. Star-galaxy classification of the Sloan Digital Sky Survey DR3 using decision trees [J].
Ball, Nicholas M. ;
Brunner, Robert J. ;
Myers, Adam D. ;
Tcheng, David .
ASTROPHYSICAL JOURNAL, 2006, 650 (01) :497-509
[5]   Automated classification of sloan digital sky survey (SDSS) stellar spectra using artificial neural networks [J].
Bazarghan, Mahdi ;
Gupta, Ranjan .
ASTROPHYSICS AND SPACE SCIENCE, 2008, 315 (1-4) :201-210
[6]   Photometric redshifts for the Kilo-Degree Survey Machine-learning analysis with artificial neural networks [J].
Bilicki, M. ;
Hoekstra, H. ;
Brown, M. J. I. ;
Amaro, V. ;
Blake, C. ;
Cavuoti, S. ;
de Jong, J. T. A. ;
Georgiou, C. ;
Hildebrandt, H. ;
Wolf, C. ;
Amon, A. ;
Brescia, M. ;
Brough, S. ;
Costa-Duarte, M. V. ;
Erben, T. ;
Glazebrook, K. ;
Grado, A. ;
Heymans, C. ;
Jarrett, T. ;
Joudaki, S. ;
Kuijken, K. ;
Longo, G. ;
Napolitano, N. ;
Parkinson, D. ;
Vellucci, C. ;
Kleijn, G. A. Verdoes ;
Wang, L. .
ASTRONOMY & ASTROPHYSICS, 2018, 616
[7]   Sloan Digital Sky Survey IV: Mapping the Milky Way, Nearby Galaxies, and the Distant Universe [J].
Blanton, Michael R. ;
Bershady, Matthew A. ;
Abolfathi, Bela ;
Albareti, Franco D. ;
Allende Prieto, Carlos ;
Almeida, Andres ;
Alonso-Garcia, Javier ;
Anders, Friedrich ;
Anderson, Scott F. ;
Andrews, Brett ;
Aquino-Ortiz, Erik ;
Aragon-Salamanca, Alfonso ;
Argudo-Fernandez, Maria ;
Armengaud, Eric ;
Aubourg, Eric ;
Avila-Reese, Vladimir ;
Badenes, Carles ;
Bailey, Stephen ;
Barger, Kathleen A. ;
Barrera-Ballesteros, Jorge ;
Bartosz, Curtis ;
Bates, Dominic ;
Baumgarten, Falk ;
Bautista, Julian ;
Beaton, Rachael ;
Beers, Timothy C. ;
Belfiore, Francesco ;
Bender, Chad F. ;
Berlind, Andreas A. ;
Bernardi, Mariangela ;
Beutler, Florian ;
Bird, Jonathan C. ;
Bizyaev, Dmitry ;
Blanc, Guillermo A. ;
Blomqvist, Michael ;
Bolton, Adam S. ;
Boquien, Mederic ;
Borissova, Jura ;
Van den Bosch, Remco ;
Bovy, Jo ;
Brandt, William N. ;
Brinkmann, Jonathan ;
Brownstein, Joel R. ;
Bundy, Kevin ;
Burgasser, Adam J. ;
Burtin, Etienne ;
Busca, Nicolas G. ;
Cappellari, Michele ;
Delgado Carigi, Maria Leticia ;
Carlberg, Joleen K. .
ASTRONOMICAL JOURNAL, 2017, 154 (01)
[8]   Automated star-galaxy segregation using spectral and integrated band data for TAUVEX/ASTROSAT satellite data pipeline [J].
Bora, Archana ;
Gupta, Ranjan ;
Singh, Harinder P. ;
Duorah, K. .
NEW ASTRONOMY, 2009, 14 (08) :649-653
[9]  
Brunner R. J, 2001, HDB MASSIVE DATA SET
[10]   Stellar spectral subclasses classification based on Isomap and SVM [J].
Bu, Yude ;
Chen, Fuqiang ;
Pan, Jingchang .
NEW ASTRONOMY, 2014, 28 :35-43