Categorization of Gelam, Acacia and Tualang Honey odor-profile using k-nearest neighbors

Nurdiyana, Zahed and M. S., Najib and Saiful Nizam, Tajuddin (2018) Categorization of Gelam, Acacia and Tualang Honey odor-profile using k-nearest neighbors. International Journal of Software Engineering & Computer Sciences (IJSECS), 4 (1). pp. 15-28. ISSN 2289-8522. (Published)

[img]
Preview
Text
Categorization of gelam, acacia and tualang honey odor-profile using k-nearest neighbors.pdf

Download (504kB) | Preview

Abstract

Honey authenticity refer to honey types is of great importance issue and interest in agriculture. In current research, several documents of specific types of honey have their own usage in medical field. However, it is quite challenging task to classify different types of honey by simply using our naked eye. This work demostrated a successful an electronic nose (E-nose) application as an instrument for identifying odor profile pattern of three common honey in Malaysia (Gelam, Acacia and Tualang honey). The applied E-nose has produced signal for odor measurement in form of numeric resistance (Ω). The data reading have been pre-processed using normalization technique for standardized scale of unique features. Mean features is extracted and boxplot used as the statistical tool to present the data pattern according to three types of honey. Mean features that have been extracted were employed into K-Nearest Neighbors classifier as an input features and evaluated using several splitting ratio. Excellent results were obtained by showing 100% rate of accuracy, sensitivity and specificity of classification from KNN using weigh (k=1), ratio 90:10 and Euclidean distance. The findings confirmed the ability of KNN classifier as intelligent classification to classify different honey types from E-nose calibration. Outperform of other classifier, KNN required less parameter optimization and achieved promising result.

Item Type: Article
Uncontrolled Keywords: Honey; Electronic Nose; Mean feature; Intelligent classification; K-Nearest Neighbors
Subjects: Q Science > QA Mathematics > QA76 Computer software
T Technology > TK Electrical engineering. Electronics Nuclear engineering
Faculty/Division: Faculty of Computer System And Software Engineering
Faculty of Electrical & Electronic Engineering
Institute of Postgraduate Studies
Depositing User: Mrs. Neng Sury Sulaiman
Date Deposited: 26 Jun 2018 03:56
Last Modified: 30 Oct 2019 03:42
URI: http://umpir.ump.edu.my/id/eprint/20870
Download Statistic: View Download Statistics

Actions (login required)

View Item View Item