Please use this identifier to cite or link to this item:
Full metadata record
DC FieldValueLanguage
dc.thesis.supervisorPremaratne, H.L. (Dr.)-
dc.contributor.authorGalappaththi, C.H.K.en_US
dc.description.abstractThe tea industry is one of the major foreign trading industries in Sri Lanka. Therefore their quality is the most important factors to be considered. In order to determine the tea quality, Tea tasters mainly consider about 4 parameters called Leaf, Infusion, Color and Liqueur of the tea sample. These quality factors are traditionally measured through the use of a combination of conventional analytical instrumentation and human organoleptic profiling panels. I have studied current existing tea quality measuring system at Bogawanthalawa Plantation Ltd and observed some significant problems there. In the ever increasing competitive market, traditional tea tasting method is becoming ineffective and as a solution I have developed a neural network based solution. By using the data gathered (Leaf, Infusion, and Color) from Bogawanthalawa Plantation; I have trained three different neural networks to obtain the tea quality. The results obtained from this method have been compared with the same results obtained from the same samples by Bogawanthalawa Tea Tasters.en_US
dc.subjectResearch Subject Categories::TECHNOLOGY::Information technology::Computer scienceen_US
dc.titleComputational Sense Towards Tea Quality Rankingen_US
Appears in Collections:SCS Individual Project - Final Thesis (2008)

Files in This Item:
File Description SizeFormat 
  Restricted Access
807.32 kBAdobe PDFView/Open Request a copy

Items in UCSC Digital Library are protected by copyright, with all rights reserved, unless otherwise indicated.