Improved the Cans Waste Classification Rate of Naïve Bayes using Fuzzy Approach

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%.

Fuzzy Discretization on the Multinomial Naïve Bayes Method for Modeling Multiclass Classification of Corn Plant Diseases and Pests

“…Using a combination of linear and triangular fuzzy membership functions in discretizing the predictor variable also succeeded in increasing the performance of the naïve Bayes model in predicting the type of cans based on digital images [11]. Each predictor variable is discretized into three categories.…”

“…The selection of fuzzy membership functions representing linguistic terms in fuzzy discretization is subjective [6,9,11]. Several fuzzy membership functions used in this work are defined in Equations ( 7)-( 12) [9,39].…”

“…As a result, the number of antecedents in the classification rules is few. Implementing fuzzy discretization in several classification methods has increased the classification method's performance [4,5,8,9], including naïve Bayes [10][11][12].…”

“…The RGB represents the red, green, and blue color space model. This technique can also improve object classification performance, [9,11]. However, no less important is the combination of the fuzzy membership functions used in the discretization process [9,11,13].…”

“…This technique can also improve object classification performance, [9,11]. However, no less important is the combination of the fuzzy membership functions used in the discretization process [9,11,13]. The combination related to the number of linguistic terms is determined based on prior knowledge or experience and the used fuzzy membership functions.…”