Odour-Profile Classification of Gelam, Acacia and Tualang Honey based on K-Nearest Neighbors Technique

Nurdiyana, Zahed and M. S., Najib and Saiful Nizam, Tajuddin (2016) Odour-Profile Classification of Gelam, Acacia and Tualang Honey based on K-Nearest Neighbors Technique. In: Proceedings of The National Conference for Postgraduate Research (NCON-PGR 2016) , 24-25 September 2016 , Universiti Malaysia Pahang (UMP), Pekan, Pahang. pp. 404-412..

[img]
Preview
PDF
Odour-Profile Classification of Gelam, Acacia.pdf

Download (343kB) | Preview

Abstract

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.

Item Type: Conference or Workshop Item (Lecture)
Uncontrolled Keywords: Honey; Electronic Nose; Mean feature; Intelligent classification; K-Nearest Neighbors
Subjects: Q Science > Q Science (General)
T Technology > TK Electrical engineering. Electronics Nuclear engineering
Faculty/Division: Faculty of Electrical & Electronic Engineering
Faculty of Industrial Sciences And Technology
Institute of Postgraduate Studies
Depositing User: Mrs. Neng Sury Sulaiman
Date Deposited: 02 Nov 2016 02:46
Last Modified: 30 Oct 2019 03:43
URI: http://umpir.ump.edu.my/id/eprint/14769
Download Statistic: View Download Statistics

Actions (login required)

View Item View Item