Article Per Year (5 Year)
p-Index From 2021 - 2026
1.037
P-Index
This Author published in this journals
All Journal International Journal of Advances in Intelligent Informatics JOIN (Jurnal Online Informatika) Knowledge Engineering and Data Science Aptisi Transactions on Technopreneurship (ATT) Science in Information Technology Letters
Ismail, Amelia Ritahani
Unknown Affiliation
Humanities Computer Science & IT Economics, Econometrics & Finance Education Engineering Social Sciences

Published : 5 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 5 Documents
Search

 1 
Text classification of traditional and national songs using naïve bayes algorithm Simbolon, Triyanti; Wibawa, Aji Prasetya; Zaeni, Ilham Ari Elbaith; Ismail, Amelia Ritahani
Science in Information Technology Letters Vol 3, No 2 (2022): November 2022
Publisher : Association for Scientific Computing Electronics and Engineering (ASCEE)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31763/sitech.v3i2.1215

Abstract

In this research, we investigate the effectiveness of the multinomial Naïve Bayes algorithm in the context of text classification, with a particular focus on distinguishing between folk songs and national songs. The rationale for choosing the Naïve Bayes method lies in its unique ability to evaluate word frequencies not only within individual documents but across the entire dataset, leading to significant improvements in accuracy and stability. Our dataset includes 480 folk songs and 90 national songs, categorized into six distinct scenarios, encompassing two, four, and 31 labels, with and without the application of Synthetic Minority Over-sampling Technique (SMOTE). The research journey involves several essential stages, beginning with pre-processing tasks such as case folding, punctuation removal, tokenization, and TF-IDF transformation. Subsequently, the text classification is executed using the multinomial Naïve Bayes algorithm, followed by rigorous testing through k-fold cross-validation and SMOTE resampling techniques. Notably, our findings reveal that the most favorable scenario unfolds when SMOTE is applied to two labels, resulting in a remarkable accuracy rate of 93.75%. These findings underscore the prowess of the multinomial Naïve Bayes algorithm in effectively classifying small data label categories.
Deep Learning Approach for Dental Anomalies X-ray Imaging using YOLOv8 Ismail, Amelia Ritahani; Taseen, Md Salim Sadman
Knowledge Engineering and Data Science Vol 7, No 2 (2024)
Publisher : Universitas Negeri Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.17977/um018v7i22024p164-175

Abstract

Dental X-ray imaging is a critical diagnostic tool for identifying various dental anomalies. However, manual interpretation is time-consuming, prone to human error, and requires specialized expertise. Deep learning models, particularly object detection frameworks like YOLO, have demonstrated promising results in automating medical image analysis. This study aims to develop and evaluate a YOLOv8-based deep learning model for automated detection and classification of 14 dental anomaly categories, including Caries, Crowns, Fillings, Implants, and Periapical lesions. The proposed approach addresses limitations in previous YOLO versions by leveraging anchor-free detection and enhanced feature extraction for improved accuracy. The model was trained on a dataset of annotated dental X-ray images and preprocessed with data augmentation techniques to improve generalization. Performance was evaluated using Precision, Recall, F1-score, and Mean Average Precision (mAP). Additional insights were obtained from confusion matrices, precision-recall curves, and training-validation loss curves. The model achieved high precision in detecting Implants (0.90), Crowns (0.89), and Root Canal Treatment (0.69), demonstrating strong potential for clinical applications. However, Caries (0.30) and Periapical lesions (0.15) were detected with lower accuracy, indicating the need for further optimization. Analysis of training loss curves and label distributions suggested that class imbalance and anomaly co-occurrence influenced detection performance. YOLOv8 presents a promising AI-based solution for dental anomaly detection, capable of improving diagnostic efficiency and accuracy in clinical practice. The model’s integration into dental healthcare systems can reduce radiologists' workload and enhance early disease detection, particularly in resource-limited settings.
Privacy-Preserving U-Net Variants with pseudo-labeling for radiolucent lesion segmentation in dental CBCT Ismail, Amelia Ritahani; Azlan, Faris Farhan; Noormaizan, Khairul Akmal; Afiqa, Nurul; Nisa, Syed Qamrun; Ghazali, Ahmad Badaruddin; Pranolo, Andri; Saifullah, Shoffan
International Journal of Advances in Intelligent Informatics Vol 11, No 2 (2025): May 2025
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26555/ijain.v11i2.1529

Abstract

Accurate segmentation of radiolucent lesions in dental Cone-Beam Computed Tomography (CBCT) is vital for enhancing diagnostic reliability and reducing the burden on clinicians. This study proposes a privacy-preserving segmentation framework leveraging multiple U-Net variants—U-Net, DoubleU-Net, U2-Net, and Spatial Attention U-Net (SA-UNet)—to address challenges posed by limited labeled data and patient confidentiality concerns. To safeguard sensitive information, Differential Privacy Stochastic Gradient Descent (DP-SGD) is integrated using TensorFlow-Privacy, achieving a privacy budget of ε ≈ 1.5 with minimal performance degradation. Among the evaluated architectures, U2-Net demonstrates superior segmentation performance with a Dice coefficient of 0.833 and an Intersection over Union (IoU) of 0.881, showing less than 2% reduction under privacy constraints. To mitigate data annotation scarcity, a pseudo-labeling approach is implemented within an MLOps pipeline, enabling semi-supervised learning from unlabeled CBCT images. Over three iterative refinements, the pseudo-labeling strategy reduces validation loss by 14.4% and improves Dice score by 2.6%, demonstrating its effectiveness. Additionally, comparative evaluations reveal that SA-UNet offers competitive accuracy with faster inference time (22 ms per slice), making it suitable for low-resource deployments. The proposed approach presents a scalable and privacy-compliant framework for radiolucent lesion segmentation, supporting clinical decision-making in real-world dental imaging scenarios.
Vision-Based Vehicle Classification for Smart City Ismail, Ahsiah; Ismail, Amelia Ritahani; Shaharuddin, Nur Azri; Ara, Muhammad Afiq; Puzi, Asmarani Ahmad; Awang, Suryanti; Ramli, Roziana
Aptisi Transactions On Technopreneurship (ATT) Vol 7 No 2 (2025): July
Publisher : Pandawan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34306/att.v7i2.446

Abstract

Vehicle detection systems are essential for improving traffic management, enhancing safety, supporting law enforcement, facilitating toll collection, and contributing to smart city initiatives through real-time monitoring and data analysis. With the rapid growth of smart city technologies, the need for efficient, scalable, and high-accuracy vehicle detection models has become increasingly critical. This study aims to propose an advanced vehicle detection system using Convolutional Neural Networks (CNNs) in combination with the YOLOv5 model, which is known for its high-speed performance and superior accuracy in image recognition tasks. The proposed model is evaluated using a custom-trained YOLOv5s model, tested on a dataset comprising 1460 images of vehicles. These images are divided into five classes which are cars, motorcycles, trucks, ambulances, and buses. Performance evaluation metrics such as precision, recall, and mean Average Precision (mAP50-95) are used to assess the model's effectiveness. The results indicate that the YOLOv5-based model achieved impressive detection accuracy, with precision, recall, and mAP values exceeding 87%. The proposed system demonstrates its robustness in detecting and classifying various vehicle types across different conditions, including small, partially visible, and distant vehicles. The findings suggest that this model holds significant potential for real-world applications in urban traffic management and smart city infrastructure.
CPSO-LSTM: Chaotic Particle Swarm Optimization improved LSTM Hyperparameters for Air Pollution Prediction Andi, Tri; Pranolo, Andri; Ismail, Amelia Ritahani; Kusuma, Candra Juni Cahyo
JOIN (Jurnal Online Informatika) Vol 11 No 1 (2026)
Publisher : Department of Informatics, UIN Sunan Gunung Djati Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15575/join.v11i1.1689

Abstract

Accurate air pollution predictions are crucial for public health and environmental management, but achieving high prediction accuracy remains a challenge due to the complexity of temporal patterns in pollution data. This study aims to improve performance of Long Short-Term Memory (LSTM) by optimizing hyperparameters tuning based Chaotic Particle Swarm Optimization (CPSO) for air pollution predictions. Hyperparameter optimization included the number of hidden layers, neurons, activation functions, loss functions, optimizers, batch sizes, and epochs. The proposed model LSTM-CPSO compared to other models, baseline LSTM and PSO-LSTM, to predict the concentrations of PM2.5, PM10, NO2, SO2, CO, and O3 in Jakarta based on Mean Squared Error (MSE), Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and Mean Absolute Percentage Error (MAPE) metrics. The experimental results show that CPSO-LSTM achieves superior performance with MSE 0.012105, MAE 0.086356, RMSE 0.110022, and MAPE 32.31%, outperforming the baseline LSTM by 38.1% on the MSE metric and 11.9% on MAPE. Interestingly, LSTM-CPSO produces better architecture with 2 hidden layers and 91 neurons than LSTM-PSO that requires 7 hidden layers with 51 neurons. Similarly, LSTM-CPSO has shortest 5 training epochs better than LSTM-PSO with 16 epochs. This research demonstrates that chaos-based metaheuristic optimization can select the best hyperparameters to improve the performance of LSTM for air quality forecasting.
Co-Authors Afiqa, Nurul Aji Prasetya Wibawa Andri Pranolo Ara, Muhammad Afiq Awang, Suryanti Azlan, Faris Farhan Ghazali, Ahmad Badaruddin Ismail, Ahsiah Kusuma, Candra Juni Cahyo Nisa, Syed Qamrun Noormaizan, Khairul Akmal Puzi, Asmarani Ahmad Ramli, Roziana Saifullah, Shoffan Shaharuddin, Nur Azri Simbolon, Triyanti Taseen, Md Salim Sadman Tri Andi, Tri Zaeni, Ilham Ari Elbaith