Prediction of Properties of Unknotted Spliced Ends of Yarns Using Multiple Regression and Artificial Neural Networks. Part II: Verification of Regression Models
Research and development
Authors:
- Lewandowski Stanisław
Poland, Bielsko-Biała, University of Bielsko-Biala, Institute of Textile Engineering and Polymer Materials - Drobina Robert (j/w)
 Full text | Abstract: A verification of regressive models based on artificial neural networks and multiple regression analysis was carried out. The analysis of the results obtained showed that artificial neural networks realizing regressive operations are useful for identifying the character of changes of additive quantities, in particular geometric dimensions and strength parameters. However, they are not suitable for identifying non-additive features, represented by tangling as well as teaseling. In this case, better predictive possibilities are provided by models based on multiple regression. |
Tags: layer diagrams, surface diagrams, learning quality, validation quality, testing quality, learning error, validation error, testing error, correlation..
Contact form
"Fibres & Textiles in Eastern Europe" is inserted on the "ISI Master Journal List" of the Institute for Scientific Information, Philadelphia, USA (for the year 2010 has an Impact Factor of 0.629) and is indexed in Research Alert, SCI Expanded (Sci Search and Web of Science), the Materials Science Citation Index, Current Contents/Engineering, Computing & Technology; as well as by the Textile Institute, Manchester, in the Information Service; and in Toga FIZ Technik; Rapra Technology Ltd.; Elsevier Geo Abstracts; Textiles Eastern Europe - World Textile Publications; Applied Mechanics Review; Chemical Abstracts Service; Referativny hurnal; and by the European Textile Network.
The content of "Fibres & Textiles in Eastern Europe" is available by free open access on the website http://www.fibtex.lodz.pl, starting from issue No 3/2002.