Claim Missing Document
Check
Articles

Found 3 Documents
Search

APPLICATION OF DEEP LEARNING TECHNIQUES FOR ENHANCING ARABIC VOCABULARY ACQUISITION IN STUDENTS AT MTS DARUN-NAJAH Isnaini, Misbachur Rohmatul; kurniasari, arvita agus; Arifianto, Aji Seto; Dewi Puspitasari, Pramuditha Shinta
Ultimatics : Jurnal Teknik Informatika Vol 16 No 2 (2024): Ultimatics : Jurnal Teknik Informatika
Publisher : Faculty of Engineering and Informatics, Universitas Multimedia Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31937/ti.v16i2.3701

Abstract

Arabic vocabulary recognition is an important aspect of learning at MTs Darun - Najah, a school that emphasizes on Islamic religious education. This research proposes the application of Convolutional Neural Network (CNN) and EfficientNet B7 to create learning media for Arabic vocabulary recognition for students. This method is implemented in the form of a web-based application. The built application offers an innovative approach in learning by utilizing deep learning. The results of several trials conducted showed that the application of Convolutional Neural Network (CNN) and EfficientNet B7 achieved 90% accuracy with an average precision of 94.6%, recall 94.6%, and f1-score 94.6%. Tests using User Acceptence Testing (UAT) have a success accuracy rate of 87.2% which proves that users can accept quite well.
Implementasi Deteksi Gerakan Tangan untuk Sistem Interaktif Kios menggunakan Metode Long Short-Term Memory (LSTM) Kurniasari, Arvita Agus; Wiryawan, I Gede; Dewi Puspitasari, Pramuditha Shinta; Rizaldi, Taufiq; Putra, Dhony Manggala
Komputika : Jurnal Sistem Komputer Vol. 14 No. 1 (2025): Komputika: Jurnal Sistem Komputer
Publisher : Computer Engineering Departement, Universitas Komputer Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34010/komputika.v14i1.14914

Abstract

Deaf individuals in Indonesia face challenges in using voice-based technology. This study aims to develop an interactive kiosk system utilizing hand gesture detection based on Long Short-Term Memory (LSTM) to provide a more inclusive solution. The research process includes collecting hand gesture datasets using MediaPipe, splitting the dataset into training and testing data with a 75:25 ratio, and training the model using a Learning Rate Scheduler. The model architecture is designed to capture patterns from keypoint data by optimizing the use of dropout layers and the softmax activation function. The evaluation shows that the model achieves an accuracy of 90.22% on the test data, with an average precision of 91%, recall of 89%, and F1-score of 90%. The trial results also demonstrate consistent performance for simple gestures, while accuracy decreases for complex gestures and greater distances. This research provides a significant contribution to enabling voice-free interaction, particularly for deaf individuals, by integrating LSTM technology into interactive kiosk systems.
APPLICATION OF DEEP LEARNING TECHNIQUES FOR ENHANCING ARABIC VOCABULARY ACQUISITION IN STUDENTS AT MTS DARUN-NAJAH Isnaini, Misbachur Rohmatul; kurniasari, arvita agus; Arifianto, Aji Seto; Dewi Puspitasari, Pramuditha Shinta
ULTIMATICS Vol 16 No 2 (2024): Ultimatics : Jurnal Teknik Informatika
Publisher : Faculty of Engineering and Informatics, Universitas Multimedia Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31937/ti.v16i2.3701

Abstract

Arabic vocabulary recognition is an important aspect of learning at MTs Darun - Najah, a school that emphasizes on Islamic religious education. This research proposes the application of Convolutional Neural Network (CNN) and EfficientNet B7 to create learning media for Arabic vocabulary recognition for students. This method is implemented in the form of a web-based application. The built application offers an innovative approach in learning by utilizing deep learning. The results of several trials conducted showed that the application of Convolutional Neural Network (CNN) and EfficientNet B7 achieved 90% accuracy with an average precision of 94.6%, recall 94.6%, and f1-score 94.6%. Tests using User Acceptence Testing (UAT) have a success accuracy rate of 87.2% which proves that users can accept quite well.