EUVIMEDEUVIMED entdecken
Open Access · CC BY-SA 4.0

Recognition of Arabic Vocabulary Based on Machine Learning Using a Convolutional Neural Network on Mobile Devices

Rahmat Rahmat, Fauzi, Muhammad Husni Mubarak

SEMESTA: Jurnal Ilmu Pendidikan dan Pengajaran · 04.06.2026 · 4 (2) · 154-172

DOI: 10.70115/semesta.v4i2.439 ↗

Kurz gefasst

Fachartikel in der Zeitschrift SEMESTA: Jurnal Ilmu Pendidikan dan Pengajaran, online erschienen am 04.06.2026. Verfasst von Rahmat Rahmat und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-SA 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study develops and evaluates machine-learning models based on Convolutional Neural Networks (CNNs) for recognizing images of Arabic vocabulary (mufradat) and for deploying these models on resource-constrained mobile devices. Whereas most prior research on Arabic-script recognition has concentrated on isolated characters executed on desktop hardware, the recognition of whole words—whose connected and visually similar glyphs increase classification difficulty—remains comparatively underexplored, particularly for on-device educational use. To address this gap, the study contributes (i) a purpose-built image dataset of fifteen academic Arabic words, (ii) a systematic comparison between a CNN trained from scratch and a MobileNetV2 transfer-learning model, and (iii) a quantified analysis of mobile deployment. An experimental approach was adopted using 3,000 images (200 per class) compiled from tablet handwriting and Microsoft Word screen-captured images, partitioned through a stratified 70/15/15 training, validation, and testing split. Both models were trained using the Adam optimizer (learning rate 1×10⁻⁴), a batch size of 32, and 50 epochs. The from-scratch five-convolution model attained 94.4% test accuracy (loss 0.26; macro-averaged F1-score 0.95), whereas the MobileNetV2 model attained 99.1% accuracy (loss 0.20; macro-averaged F1-score 0.99). After conversion to TensorFlow Lite, the MobileNetV2 model required only 9.1 MB of storage and 42 ms per inference on a mid-range Android device, compared with 103 MB and 180 ms for the from-scratch model, confirming its suitability for real-time use. The findings demonstrate that transfer learning achieves higher accuracy with markedly fewer parameters and a smaller computational footprint, providing an efficient foundation for mobile-assisted Arabic vocabulary learning.

Zitieren

APA

Rahmat, R., Fauzi, & Mubarak, M. H. (2026). Recognition of Arabic Vocabulary Based on Machine Learning Using a Convolutional Neural Network on Mobile Devices. SEMESTA: Jurnal Ilmu Pendidikan dan Pengajaran, 4(2), 154-172. https://doi.org/10.70115/semesta.v4i2.439

Vancouver

Rahmat R, Fauzi, Mubarak MH. Recognition of Arabic Vocabulary Based on Machine Learning Using a Convolutional Neural Network on Mobile Devices. SEMESTA: Jurnal Ilmu Pendidikan dan Pengajaran. 2026;4(2):154-172. doi:10.70115/semesta.v4i2.439

BibTeX
@article{Rahmat2026,
  author = {Rahmat, Rahmat and Fauzi and Mubarak, Muhammad Husni},
  title = {Recognition of Arabic Vocabulary Based on Machine Learning Using a Convolutional Neural Network on Mobile Devices},
  journal = {SEMESTA: Jurnal Ilmu Pendidikan dan Pengajaran},
  year = {2026},
  volume = {4},
  number = {2},
  pages = {154--172},
  doi = {10.70115/semesta.v4i2.439}
}
Kostenlos starten →