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

• Main Authors: Nurdiyana, Zahed, M. S., Najib, Saiful Nizam, Tajuddin
• Format: Article
• Language: English
• Published: Penerbit UMP 2018
• Subjects: QA76 Computer software; TK Electrical engineering. Electronics Nuclear engineering
• Online Access: http://umpir.ump.edu.my/id/eprint/20870/1/Categorization%20of%20gelam%2C%20acacia%20and%20tualang%20honey%20odor-profile%20using%20k-nearest%20neighbors.pdf; http://umpir.ump.edu.my/id/eprint/20870/; http://ijsecs.ump.edu.my/index.php/archive/17-v4/35-ijsecs-04-002

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.