Home | Repositories | Statistics | About





Year: 2014





Title: Optimization of supervised self-organizing maps with genetic algorithms for classification electrophoretic profiles


Author: Tomovska, Natalia
Author: Kuzmanovski, Igor
Author: Stojanoski, Kiro



Abstract:

Standard electrophoresis methods were used in the classification of analyzed proteins in cerebrospinal fluid from patients with multiple sclerosis. Disc electrophoresis was carried out for detection of oligoclonal IgG bands in cerebrospinal fluid on polyacrylamide gel, mainly with multiple sclerosis and other central nervous system dysfunctions. ImageMaster 1D Elite and GelPro specialized software packages were used for fast accurate image and gel analysis. The classification model was based on supervised self-organizing maps. In order to perform the modeling in automated manner genetic algorithms were used. Using this approach and a data set composed of 69 samples we were able to develop models based on supervised self-organizing maps which were able to correctly classify 83 % of the samples in the data set used for external validation.




Publisher: Society of Chemists and Technologists of Macedonia


Relation: Macedonian Journal of Chemistry and Chemical Engineering



Identifier: oai:repository.ukim.mk:20.500.12188/15940
Identifier: http://hdl.handle.net/20.500.12188/15940
Identifier: 10.20450/mjcce.2014.436
Identifier: http://www.mjcce.org.mk/index.php/MJCCE/article/viewFile/436/299
Identifier: http://www.mjcce.org.mk/index.php/MJCCE/article/viewFile/436/299
Identifier: 33
Identifier: 1



TitleDateViews
Optimization of supervised self-organizing maps with genetic algorithms for classification electrophoretic profiles201425