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 122
- Downloads 0
USABILITY EVALUATION METHOD FOR AGILE SOFTWARE DEVELOPMENT
Agile methods are the best fit for tremendously growing software industry due to its flexible and dynamic nature. But the software developed using agile methods do meet the usability standards? To answer this question we...
EVALUATING THE EFFECT OF DATASET SIZE ON PREDICTIVE MODEL USING SUPERVISED LEARNING TECHNIQUE
Learning models used for prediction purposes are mostly developed without paying much cognizance to the size of datasets that can produce models of high accuracy and better generalization. Although, the general believe i...
INVESTIGATION MODEL FOR DDOS ATTACK DETECTION IN REAL-TIME
Investigating traffic of distributed denial of services (DDoS) attack requires extra overhead which mostly results in network performance degradation. This study proposes an investigation model for detecting DDoS attack...
A SURVEY OF MEDICAL IMAGE PROCESSING TOOLS
A precise analysis of medical image is an important stage in the contouring phase throughout radiotherapy preparation. Medical images are mostly used as radiographic techniques in diagnosis, clinical studies and treatmen...
FINGERPRINT WATERMARKING WITH TAMPER LOCALIZATION AND EXACT RECOVERY USING MULTI-LEVEL AUTHENTICATION
This paper presents the tamper localization and exact recovery using multi-level authentication in fingerprint watermarking. The proposed scheme will be detecting the tampered sector of fingerprint images when the waterm...