Article Per Year (5 Year)
p-Index From 2019 - 2024
0.23
P-Index
This Author published in this journals
All Journal JOURNAL OF INFORMATICS AND TELECOMMUNICATION ENGINEERING
Fadlisyah Fadlisyah
Universitas Medan Area
Computer Science & IT Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Performance Evaluation Of Variations Boosting Algorithms For Classifying Formalin Fish From Photos Fadlisyah Fadlisyah; Muhathir Muhathir
JOURNAL OF INFORMATICS AND TELECOMMUNICATION ENGINEERING Vol. 6 No. 2 (2023): Issues January 2023
Publisher : Universitas Medan Area

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31289/jite.v6i2.6614

Abstract

Fish is one of the foods that are often consumed by humans to complete the protein in the body. Indonesia is rich in animal protein so some rogue traders to avoid losses due to rotten fish, sellers process fish to make it look fresh by fishing with formalin liquids so that buyers think the fish is still fresh, this problem is often found in the market so that it takes the right solution. The solution offered is to apply Machine Learning (Boosting Algorithm) to classify fresh fish and fish that have been planned with formalin by utilizing the extraction of GLCM features. The findings of this study indicate a variation of boosting algorithms can provide solutions to this problem. Accuracy, precision, recall, f1-score, f2-score, and Jaccard score in tilapia fish with a value of 0.95, 0.95, 0.95, 0.95, 0.95, 0.95 this result is obtained by extreme gradient boosting variations with the highest achievements compared to variations Other things are also similar to Tamban fish with a value of 0.78, 0.775, 0.78, 0.825, 0.77, 0.632. The effect of boosting algorithm on the measurement of model performance looks very increased in tilapia fish while in tamban fish do not provide maximum results, but these findings are better
Co-Authors Muhathir Muhathir