Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal Infokes : Jurnal Ilmiah Rekam Medis dan Informasi Kesehatan Edu Komputika Journal
Farahwahida Mohd
Universiti Kuala Lumpur
Education Health Professions Medicine & Pharmacology Nursing Public Health Veterinary

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Comparison of Machine Learning and Deep Learning Algorithms for Daily Retail Sales Forecasting Eko Purwanto; Bangun Prajadi Cipto Utomo; Hanifah Permatasari; Farahwahida Mohd
Edu Komputika Journal Vol. 12 No. 2 (2025): Edu Komputika Journal
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/edukom.v12i2.32773

Abstract

This study presents a comparative analysis of four machine learning (ML) and deep learning (DL) algorithms: Random Forest (RF), Support Vector Machine (SVM), Convolutional Neural Network (CNN), and Long Short-Term Memory (LSTM) for predicting daily retail sales time series. The models were evaluated using key metrics, such as Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and R-squared (R²). Results show that RF and SVM outperformed both CNN and LSTM in terms of MAE (3500.28 and 3325.11, respectively) and RMSE (4660.60 and 4293.42, respectively). However, all models had negative R² values, indicating none could explain the variation in the data. LSTM, in particular, was the least efficient model, with an MAE of 54087.25, RMSE of 54257.51, and R² of -158.59. The poor performance of LSTM can be attributed to overfitting, improper model configuration, and misalignment with the nature of the data. The dataset used includes over 1,000 daily retail sales transaction records collected over one year, with key attributes like CustomerID, ProductID, Quantity, Price, TransactionDate, PaymentMethod, StoreLocation, ProductCategory, DiscountApplied, and TotalAmount. While the dataset is representative, its size and complexity may not have been sufficient for deep learning models like LSTM and CNN, which generally require larger datasets for optimal performance. This study highlights the challenges of using deep learning for retail forecasting and suggests future research should focus on refining models and incorporating external datasets to improve prediction accuracy.
Evaluating U-Net Segmentation in Vgg16-Based Leukemia Classification: A Comparative Study Rizky Vera Oktarina; Afu Ichsan Pradana; Vihi Atina; Farahwahida Mohd
Jurnal Infokes Vol 16 No 2 (2026): Jurnal Ilmiah Rekam Medis dan Informatika Kesehatan
Publisher : Universitas Duta Bangsa Surakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47701/5d37ge60

Abstract

Background: Leukemia is a malignant hematological disorder characterized by abnormal proliferation of white blood cells (WBCs), affecting over 474,000 patients globally each year, with manual diagnosis limited by inter-observer variability of up to 40%. Objective: This study evaluates whether U-Net-based WBC segmentation improves leukemia classification by comparing three configurations: VGG16 on original images, VGG16 with U-Net-predicted masks, and VGG16 with ground truth masks. Methods: A total of 3,256 ALL microscopic blood smear images were divided into training, validation, and testing sets (70:10:20). U-Net was trained using a combined Binary Cross-Entropy and Dice loss, and the segmentation outputs were used as inputs for VGG16 classification. Performance was evaluated using DSC, IoU, accuracy, precision, recall, F1-score, and AUC-ROC. Results: U-Net achieved a DSC of 0.7885 and an IoU of 0.7134. VGG16 with U-Net masks achieved 98.62% accuracy (AUC 0.9958), while VGG16 with ground truth masks achieved 98.31%. The baseline VGG16 achieved the highest performance with 99.69% accuracy (AUC 0.9999). Conclusion: Explicit segmentation did not improve classification performance for the dataset used in this study and may introduce unnecessary computational overhead when discriminative features are already preserved in the original images. Suggestion: Future studies should evaluate heterogeneous datasets and advanced segmentation architectures to further investigate the contribution of segmentation to leukemia classification.
Co-Authors Afu Ichsan Pradana Atina, Vihi Bangun Prajadi Cipto Utomo Eko Purwanto Permatasari, Hanifah Rizky Vera Oktarina