CATEGORIZATION OF GELAM, ACACIA AND TUALANG HONEY ODORPROFILE USING K-NEAREST NEIGHBORS
Journal Title: International Journal of Software Engineering and Computer Systems - Year 2018, Vol 4, Issue 1
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.
Authors and Affiliations
Nurdiyana Zahed, Muhammad Sharfi Najib, Saıful Nizam Tajuddin
Keywords
Related Articles
- EP ID EP597358
- DOI 10.15282/ijsecs.4.1.2018.2.0035
- Views 102
- Downloads 0
A GLOBAL AFRICAN BUFFALO OPTIMIZATION
In this paper, a modified version of the African Buffalo Optimization algorithm with emphasis on global search is proposed. Two different equations with the values of their upper and lower boundaries are selected to be t...
INFORMATION SYSTEMS REENGINEERING APPROACH BASED ON THE MODEL OF INFORMATION SYSTEMS DOMAINS
The paper considers current problems of integration of Information Systems (IS), limitations of current methods of IS Reengineering and limitations of existing approaches for Data Integration in Relational Databases. The...
PREDICTING THE EFFECTIVENESS OF WEB INFORMATION SYSTEMS USING NEURAL NETWORKS MODELING: FRAMEWORK & EMPIRICAL TESTING
The information systems (IS) assessment studies have still used the commonly traditional tools such as questionnaires in evaluating the dependent variables and specially effectiveness of systems. Artificial neural network...
METAMODELLING APPROACH AND SOFTWARE TOOLS FOR PHYSICAL MODELLING AND SIMULATION
In computer science, metamodelling approach becomes more and more popular for the purpose of software systems development. In this paper, we discuss applicability of the metamodelling approach for development of software...
SOFTWARE AGENT AND CLOUD COMPUTING: A BRIEF REVIEW
The merging of interests between Cloud applications which necessary require an intelligent software agent with elastic, dynamic, with independent behavior ability and multi-agent systems that need consistent distributed...