EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-SA 4.0

Perancangan dan Implementasi Sistem Deteksi Jatuh Otomatis Berbasis Citra Video Menggunakan Convolutional Neural Network (CNN)

Ardien Ferdinand Putra Setiawan, Virza Al Durra Winata, Hasan Ismail Abdulmalik, Gema Parasti Mindara, Endang Purnama Giri

Journal of Informatics and Communication Technology (JICT) · 03.06.2026 · 7 (2) · 129-135

DOI: 10.52661/jict.v7i2.477 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Informatics and Communication Technology (JICT), online erschienen am 03.06.2026. Verfasst von Ardien Ferdinand Putra Setiawan und 4 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-SA 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Falls represent one of the most critical safety risks for elderly individuals and people in high-risk environments. This study aims to design and implement an automatic fall-detection system based on video imagery using a Convolutional Neural Network (CNN) through a transfer-learning approach with the MobileNetV2 model. The dataset used in this research was obtained from the publicly available “Human-Fall-Detection” repository by Y-B-Class-Projects, consisting of labeled frames categorized as fall and normal. The system processes video input through stages of frame extraction, preprocessing, feature learning, and real-time classification. The Rapid Application Development (RAD) methodology was adopted to accelerate prototyping and iterative refinement. Experimental results demonstrate that the model achieves high performance, with an accuracy of 94.26%, balanced accuracy of 94.49%, and strong reliability metrics such as MCC and Cohen’s Kappa above 0.88. The system is further equipped with an automated alert mechanism to notify users when a fall is detected. Overall, the proposed MobileNetV2-based approach provides an effective and reliable solution for real-time fall detection and human-safety monitoring.

Zitieren

APA

Setiawan, A. F. P., Winata, V. A. D., Abdulmalik, H. I., Mindara, G. P., & Giri, E. P. (2026). Perancangan dan Implementasi Sistem Deteksi Jatuh Otomatis Berbasis Citra Video Menggunakan Convolutional Neural Network (CNN). Journal of Informatics and Communication Technology (JICT), 7(2), 129-135. https://doi.org/10.52661/jict.v7i2.477

Vancouver

Setiawan AFP, Winata VAD, Abdulmalik HI, Mindara GP, Giri EP. Perancangan dan Implementasi Sistem Deteksi Jatuh Otomatis Berbasis Citra Video Menggunakan Convolutional Neural Network (CNN). Journal of Informatics and Communication Technology (JICT). 2026;7(2):129-135. doi:10.52661/jict.v7i2.477

BibTeX
@article{Setiawan2026,
  author = {Setiawan, Ardien Ferdinand Putra and Winata, Virza Al Durra and Abdulmalik, Hasan Ismail and Mindara, Gema Parasti and Giri, Endang Purnama},
  title = {Perancangan dan Implementasi Sistem Deteksi Jatuh Otomatis Berbasis Citra Video Menggunakan Convolutional Neural Network (CNN)},
  journal = {Journal of Informatics and Communication Technology (JICT)},
  year = {2026},
  volume = {7},
  number = {2},
  pages = {129--135},
  doi = {10.52661/jict.v7i2.477}
}
Kostenlos starten →