Application of Convolutional Neural Network (CNN) for Web-Based Translation of Indonesian Text into Sign Language

DIAJENG PRAMESWARI — 2025-10-06

Communication for the deaf and hard of hearing is often hindered by the limited number of sign language interpreters. This research aims to develop a web-based text-to-text sign language translation system using Convolutional Neural Networks (CNN) to bridge this communication gap. The system is built with the ASL Alphabet dataset containing 87,000 images from 29 classes (A-Z, SPACE, DELETE, NOTHING). The CNN model was designed with three convolutional layers and trained for 15 epochs using 80% of the data, while 20% of the data was used for testing. The user interface was developed using Streamlit for ease of use. Training results showed a training accuracy of 98.96% and a validation accuracy of 98.61% at the 15th epoch. Model evaluation yielded an overall accuracy of 98%, with high precision, recall, and F1-score values for most classes. This research demonstrates the significant potential of CNN in developing automatic sign language translators, which is expected to improve information accessibility and inclusivity for the deaf community.

Feature Importance-Guided Ensemble Classification for Predicting Recurrence in Differentiated Thyroid Cancer

Muhammad Ghinan Navsih — 2025-10-06

Accurate prediction of cancer recurrence is critical for improving patient monitoring and personalized treatment planning. In this study, we propose a machine learning framework to predict recurrence in patients with differentiated thyroid cancer using statistically selected clinical features. Feature relevance was assessed using ANOVA for ordinal/numerical variables and the Chi-square test for one-hot encoded categorical variables, allowing us to identify the most informative predictors. We then trained three distinct classifiers—Random Forest, Logistic Regression, and XGBoost—and combined them using a hard voting ensemble strategy. The proposed ensemble achieved an accuracy of 98.7% on the test set, with particularly strong precision and recall scores for the recurrent class, indicating its potential clinical utility. Interestingly, all three base classifiers produced identical predictions on the test data, suggesting the dataset’s strong internal structure and the effectiveness of our feature selection process. This work highlights the value of integrating statistical feature selection with ensemble modeling for robust and interpretable prediction in clinical oncology applications.

Jurnal Aplikasi Sains Data

Application of Convolutional Neural Network (CNN) for Web-Based Translation of Indonesian Text into Sign Language

Feature Importance-Guided Ensemble Classification for Predicting Recurrence in Differentiated Thyroid Cancer