Hybridization of the SGTM Neural-like Structure through Inputs Polynomial Extension
dc.authorid | Kutucu, Hakan/0000-0001-7144-7246 | |
dc.authorid | Tkachenko, Roman/0000-0002-9802-6799 | |
dc.authorid | Izonin, Ivan/0000-0002-9761-0096 | |
dc.contributor.author | Vitynskyi, Pavlo | |
dc.contributor.author | Tkachenko, Roman | |
dc.contributor.author | Izonin, Ivan | |
dc.contributor.author | Kutucu, Hakan | |
dc.date.accessioned | 2024-09-29T16:11:36Z | |
dc.date.available | 2024-09-29T16:11:36Z | |
dc.date.issued | 2018 | |
dc.department | Karabük Üniversitesi | en_US |
dc.description | 2nd IEEE International Conference on Data Stream Mining and Processing (DSMP) -- AUG 21-25, 2018 -- Lviv, UKRAINE | en_US |
dc.description.abstract | In this paper, a new approach for increasing the approximation accuracy with the use of computational intelligence tools is described. It is based on the compatible use of the neural-like structure of the Successive Geometric Transformations Model and the inputs polynomial extension. To implement such an extension, second degree Wiener polynomial is used. This combination improves the method accuracy for solving various tasks, such as classification and regression, including short-term and long-term prediction, dynamic pricing, as well as image recognition and image scaling, e-commerce. Due to the use of SGTM neural-like structure, the high speed of the system is maintained in both training and using modes. The simulation of the described approach is carried out on real data, the time results of the neural-like structure work and the accuracy results (MAPE, RMSE, R) are given. A comparison of the operation of the method with existing ones, such as Support vector regression, Classic linear SGTM neural-like structure, Linear regression (using Stochastic Gradient Descent), Random Forest, Multilayer Perceptron, AdaBoost are made. The advantages of the developed approach, in particular with regard to the highest accuracy among existing ones were experimentally established. | en_US |
dc.description.sponsorship | IEEE,IT Step Univ,Lviv Polytechn Natl Univ,Ukrainian Cathol Univ,IEEE Ukraine Sect,IEEE Ukraine Sect Kharkiv SP AP C EMC COM Soc Joint Chapter,IEEE Ukraine Sect W AP ED MTT CPMT SSC Soc Joint Chapter,softserve,GlobalLogic,Perfectial,Lviv Convent Bur,Altexsoft,IT JIM,LMX,Hey Machine Learning,Teragence,Univ J E Purkyne USTI NAD LABEM,Univ Social Sci, Spoleczna Akademia Nauk,BENI SUEF UNIV,ISI Res Lab,Banking Univ,SEVERENITY,XHTY,LVIV IT CLUSTER,IT B E A N S Student Community,PM Business Solut,Game & Design,Lviv Data Sci Club,AI Ukraine,UAevent,ISDMCI,AI & Big Data Day,ODSC,Lviv City Council,LVIV,Kharkiv Natl Univ Radio Elect | en_US |
dc.identifier.endpage | 391 | en_US |
dc.identifier.isbn | 978-1-5386-2874-4 | |
dc.identifier.startpage | 386 | en_US |
dc.identifier.uri | https://hdl.handle.net/20.500.14619/8567 | |
dc.identifier.wos | WOS:000448930300070 | en_US |
dc.identifier.wosquality | N/A | en_US |
dc.indekslendigikaynak | Web of Science | en_US |
dc.language.iso | en | en_US |
dc.publisher | Ieee | en_US |
dc.relation.ispartof | 2018 Ieee Second International Conference On Data Stream Mining & Processing (Dsmp) | en_US |
dc.relation.publicationcategory | Konferans Öğesi - Uluslararası - Kurum Öğretim Elemanı | en_US |
dc.rights | info:eu-repo/semantics/closedAccess | en_US |
dc.subject | approximation | en_US |
dc.subject | Wiener polynomial | en_US |
dc.subject | neural-like structures | en_US |
dc.subject | Successive Geometric Transformation Model | en_US |
dc.subject | input's extension | en_US |
dc.title | Hybridization of the SGTM Neural-like Structure through Inputs Polynomial Extension | en_US |
dc.type | Conference Object | en_US |