Odour-Profile Classification of Gelam, Acacia and Tualang Honey based on K-Nearest Neighbors Technique
Recently, there has been growing interest in using agriculture food such as honey in food, beverage, pharmaceutical and medical industries. Specific honey type has their own usage and benefit. However, it is quite challenging task to classify different types of honey by simply using our naked eye.Th...
| Main Authors: | , , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | English |
| Published: |
Universiti Malaysia Pahang
2016
|
| Subjects: | |
| Online Access: | http://umpir.ump.edu.my/id/eprint/14769/ http://umpir.ump.edu.my/id/eprint/14769/ http://umpir.ump.edu.my/id/eprint/14769/1/Odour-Profile%20Classification%20of%20Gelam%2C%20Acacia.pdf |
| Summary: | Recently, there has been growing interest in using agriculture food such as honey in food, beverage, pharmaceutical and medical industries. Specific honey type has their own usage and benefit. However, it is quite challenging task to classify different types of honey by simply using our naked eye.The purpose of this study is to apply an electronic nose (E-nose) as an instrument to produce odor profile pattern for Gelam, Acacia and Tualang honey which are the common honey in Malaysia. Enose can produce signal for odor measurement in form of numeric resistance. Its measurement can pre-processed using
normalization for standardized scale of unique features. Mean features is one of the unique features which extracted from the pre-processed data and statistical tool using boxplot representing the data pattern according to three types of honey (Gelam, Acacia and Tualang). Mean features that have been extracted were employed into K-Nearest Neighbors classifier as an input features. KNN performance have been evaluated using several splitting ratio. The results have shown that 100% rate of accuracy, sensitivity and specificity of classification from KNN using weigh (k=1), ratio 90:10 and Euclidean distance. It has been proven that the ability of KNN classifier as intelligent classification can be employed to classify different honey types from E-nose measured data. |
|---|