Main Article Content

Yulia Resti Firmansyah Burlian Irsyadi Yani Des Alwine Zayanti Indah Meiliana Sari
DOI: https://doi.org/10.26554/sti.2020.5.3.75-78 Published Jul 22, 2020

Abstract

Cans is one type of inorganic waste that can take up to hundreds of years to be decomposed on the ground so that recycling is the right solution for managing cans waste. In the recycling industry, can classification systems are needed for the sorting system automation. This paper discusses the cans classification system based on the digital images using the Naive Bayes method, where the input variables are the pixel values of red, green, and blue (RGB) color, and the image of the can is captured by placing it on a conveyor belt which runs at a certain speed. The average accuracy rate of the k-fold cross-validation which is less satisfactory from the classification system obtained using the original Naive Bayes model is corrected using the fuzzy approach. This approach succeeded in improving the average accuracy of the can classification system which was originally from 52.99% to 88.02% or an increase of 60.2%, where the standard deviation decreased from 15.72% to only 3%.


Cans is one type of inorganic waste that can take up to hundreds of years to be decomposed on the ground so that recycling is the right solution for managing cans waste. In the recycling industry, can classification systems are needed for the sorting system automation. This paper discusses the cans classification system based on the digital images using the Naive Bayes method, where the input variables are the pixel values of red, green, and blue (RGB) color, and the image of the can is captured by placing it on a conveyor belt which runs at a certain speed. The average accuracy rate of the k-fold cross-validation which is less satisfactory from the classification system obtained using the original Naive Bayes model is corrected using the fuzzy approach. This approach succeeded in improving the average accuracy of the can classification system which was originally from 52.99% to 88.02% or an increase of 60.2%, where the standard deviation decreased from 15.72% to only 3%.

Abstract 171 times PDF 90 times

Article Details

How to Cite
RESTI, Yulia et al. Improved the Cans Waste Classification Rate of Naïve Bayes using Fuzzy Approach. Science and Technology Indonesia, [S.l.], v. 5, n. 3, p. 75-78, july 2020. ISSN 2580-4391. Available at: <http://sciencetechindonesia.com/index.php/jsti/article/view/231>. Date accessed: 01 dec. 2020. doi: https://doi.org/10.26554/sti.2020.5.3.75-78.
Section
Articles