Study in Development of Cans Waste Classification System Based on Statistical Approaches

Resti, Yulia; Mohruni, Amrifan Saladin; Rodiana, T.; Zayanti, Des Alawine

doi:10.1088/1742-6596/1198/9/092004

Cited by 8 publications

(7 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…K-nearest neighbour is an effective classification method which is based on the majority of k-nearest neighbours and uses multinomial regression [13] which reduces the complexity of model and also distance similarity measure used for dot-wise operation. K-way classification problem [19] helps in the development of a visionbased waste detection system for determining the recyclability of household waste.…”

Section: E K-nearest Neighbourmentioning

confidence: 99%

See 1 more Smart Citation

AI-Bin

2022

View full text Add to dashboard Cite

Section: E K-nearest Neighbourmentioning

confidence: 99%

“…Image classification tasks often mitigate the over-fitting problem and retain model accuracy by resisting occlusion [13].…”

Section: F Image Classificationmentioning

confidence: 99%

AI-Bin

2022

View full text Add to dashboard Cite

“…The can classi cation system can also be built based on digital images, where the input variables are the pixel values of the color of the can digital image. Resti et al (2017); Resti et al (2019a); Resti et al (2019b) used the red, green, and blue (RGB) color models, while Resti et al (2020) used the cyan, magenta, yellow, and black (CMYK) color models to represent the pixel values of the color of the can digital image, however the accuracy rate obtained is not satisfactory (Resti et al (2017); Resti et al (2019a) obtains an accuracy rate of less than 80%, whereas Resti et al (2019b); Resti et al (2020) obtains an accuracy rate of less than 50%). There is no speci c de nition of a minimum accuracy rate of a classi cation system, but obtaining a better accuracy rate makes the system built more accurate, e cient and useful.…”

Section: Introductionmentioning

confidence: 99%

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

Resti

Burlian

Yani

et al. 2020

sci. technol. indones.

View full text Add to dashboard Cite

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%.

show abstract

“…The automation technology of an industrial system that uses intelligent computing systems has continued to develop rapidly recently (Kamboj et al (2019); Nikhil et al 2017; Oladapo et al (2016); Bargal et al (2016); Fluke (2015); Rosenblat et al (2014)) including the automation of sorting systems in the can recycling industry that uses object classi cation techniques based on digital images (Resti et al (2018); Resti et al (2017b)). Classi cation of cans based on digital images of cans placed on a static conveyor belt can be seen in (Resti et al (2019); Resti et al (2017a); Resti (2015); Yani et al (2009)). In real time, the classi cation of cans in a sorting system occurs when cans placed on a conveyor belt move at a certain speed.…”

Section: Introductionmentioning

confidence: 99%

Performance of Cans Classification System for Different Conveyor Belt Speed using Naïve Bayes

Resti

Burlian²,

Yani

2020

sci. technol. indones.

View full text Add to dashboard Cite

The classification system in the sorting process in the can recycling industry can be made based on digital images by exploring the basic color pixel values of images such as R, G, and B as variable inputs. In real time, the classification of cans in the sorting process occurs when cans placed on a conveyor belt move at a certain speed. This paper discusses the performance of can classification systems using the Naïve Bayes method. This method can handle all types of variables, including when all variables are continuous. Two types of conveyor belts are designed to get different speeds, and all images of the cans are captured on both conveyor belts. Two models of Bayes naive are built on the basis of the different distribution assumptions; the original model (all Gaussian distributed) and the model based on the best distribution. Performance of the classification system is built by dividing data into the learning data and the testing data with a composition of 50:50 in which each data is designed into 50 groups with different percentages on each type of cans using sampling technique without replacement. The results obtained are, first, the speed of the conveyor belt when capturing an image affects the pixel values of red, green, and blue and ultimately affects the results of the classification of cans. Second, not all input variables are Gaussian distributed. The classification system was built using assumption the best distribution model for each input variable has the better average accuracy level than the model that assumes all input variables are Gaussian distributed, and the accuracy level of classification on the first speeds of conveyor belt with a gear ratio of 12:30 and a diameter of 35 mm has an accuracy that is better than the other speed, both on the original model and the model based on the best distribution. However, it is necessary to test more statistical distribution models to obtain significant results.

show abstract

Study in Development of Cans Waste Classification System Based on Statistical Approaches

Cited by 8 publications

References 1 publication

AI-Bin

AI-Bin

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

Performance of Cans Classification System for Different Conveyor Belt Speed using Naïve Bayes

Contact Info

Product

Resources

About