Claim Missing Document
Check
Articles

Found 2 Documents
Search

Enhancing Obesity Risk Classification: Tackling Data Imbalance with SMOTE and Deep Learning Syofian, Muhammad; Maulana, Ilham
Jurnal Riset Informatika Vol. 6 No. 4 (2024): September 2024
Publisher : Kresnamedia Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (3011.529 KB) | DOI: 10.34288/jri.v6i4.349

Abstract

Data imbalance is a significant challenge in classification models, often leading to suboptimal performance, especially for minority classes. This study explores the effectiveness of the Synthetic Minority Over-sampling Technique (SMOTE) in improving classification model performance by balancing data distribution. The evaluation was conducted using a confusion matrix to measure prediction accuracy for each class. The results indicate that SMOTE successfully enhances minority class representation and improves prediction balance, although some misclassifications remain. Therefore, in addition to oversampling, additional approaches such as class weighting or ensemble learning are required to further improve model accuracy. This study provides deeper insights into the role of SMOTE in addressing data imbalance and its impact on classification model performance.
Identification of Rotten Carrots Using Image Processing with Edge Detection and Convolution Techniques Syofian, Muhammad
Journal Medical Informatics Technology Volume 3 No. 4, December 2025
Publisher : SAFE-Network

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37034/medinftech.v3i4.53

Abstract

Carrot is one of the agricultural commodities with high nutritional value and a significant market demand. However, its quality can deteriorate due to various factors, one of which is rotting. Early detection of rotting carrots is crucial to prevent economic losses and maintain product quality. The main problem in identifying rotten carrots lies in the need for high precision and the time-consuming nature of manual methods. To address this issue, this research develops an automated method for detecting rotten carrots using image processing techniques. In this study, edge detection and convolution techniques are employed as the primary approaches in image analysis. Edge detection is used to recognize contours and boundaries in carrot images, while convolution techniques are applied to identify patterns of damage and texture differences between rotten and healthy carrots. The research findings indicate that this method is capable of detecting rotten carrots with high accuracy, making it reliable as a tool for sorting and quality assurance in carrot processing.