Implementasi Sistem Deteksi Bullying Berbasis YOLOv11 pada CCTV Sekolah dengan Dashboard Monitoring dan Notifikasi Telegram

Yasmin Maulidia Andini Putri; Rania Ayu Praesmawardhani; Annisa Ahmada Atusta; Hamim Thohari Mahfudhillah

doi:10.33884/jif.v14i02.11945

Authors

Yasmin Maulidia Andini Putri MTsN 6 Malang
Rania Ayu Praesmawardhani MTsN 6 Malang
Annisa Ahmada Atusta MTsN 6 Malang
Hamim Thohari Mahfudhillah MTsN 6 Malang

DOI:

https://doi.org/10.33884/jif.v14i02.11945

Keywords:

CCTV, YOLOv11, computer vision, Flask, bullying, Telegram

Abstract

Physical bullying in school environments often occurs spontaneously, making it difficult to monitor continuously using conventional Closed-Circuit Television (CCTV) systems. This study aims to implement SAFEYE-AI, a YOLOv11-based bullying detection system integrated with school CCTV, a Flask-based monitoring dashboard, and Telegram notifications. The research employs the AI Project Cycle framework, encompassing problem scoping, data acquisition, data exploration, modeling, evaluation, and deployment. The YOLOv11n model was trained using 3,771 images from school CCTV footage across 10 classes, comprising nine types of physical bullying actions and a student class. Training was conducted over 100 epochs using an NVIDIA RTX 4060 GPU. Evaluation results yielded a precision of 0.903, recall of 0.953, mAP@0.5 of 0.954, and mAP@0.5:0.95 of 0.686. Confidence threshold analysis identified an optimal value of 0.25, resulting in an F1-score of 0.929. Implementation on the CCTV infrastructure demonstrated the system's capability to process up to nine camera streams simultaneously. The system successfully detected kicking and fighting incidents within the school environment and transmitted incident information via Telegram. These results indicate that the integration of YOLOv11, a Flask dashboard, CCTV, and Telegram creates a bullying monitoring system that supports real-time detection and alerting in school environments.

References

S. Metha, “Pertanggung jawaban pidana atas tindakan perundungan fisik oleh pelaku anak di bawah umur,” Soll. J. Kaji. Kontemporer Huk. Dan Masy., vol. 1, no. 02, 2023.

UNICEF, “Half of world’s teens experience peer violence in and around school – UNICEF.” Accessed: Aug. 21, 2025. [Online]. Available: https://www.unicef.org/eca/press-releases/half-worlds-teens-experience-peer-violence-and-around-school-unicef?utm_source=chatgpt.com

F. N. Fintari and M. Fauziah, “Analisis Dampak Bullying Verbal Terhadap Kemampuan Berbicara Peserta Didik Di Tingkat Sekolah Dasar.,” J. Pendidik. Indones., vol. 5, no. 10, 2024.

A. P. Sidiq, A. Darmawan, O. Supriadi, and O. A. Rozak, “Implementasi Sistem Monitoring CCTV Berbasis IP untuk Peningkatan Keamanan di SMK Khazanah Kebajikan,” J. Keilmuan Dan Keislam., pp. 690–698, 2025.

Y. Yanto, F. Aziz, and I. Irmawati, “YOLO-V8 peningkatan algoritma untuk deteksi pemakaian masker wajah,” JATI J. Mhs. Tek. Inform., vol. 7, no. 3, pp. 1437–1444, 2023.

D. A. Farizki and A. L. Pramana, “ANALISIS KOMPARATIF KINERJA YOLOV5, YOLOV8, DAN YOLO11 PADA DETEKSI OBJEK LALU LINTAS MALAM HARI MENGGUNAKAN CLAHE,” JATI J. Mhs. Tek. Inform., vol. 10, no. 4, pp. 6757–6766, 2026.

K. B. Sahay, B. Balachander, B. Jagadeesh, G. Anand Kumar, R. Kumar, and L. Rama Parvathy, “A real time crime scene intelligent video surveillance systems in violence detection framework using deep learning techniques,” Comput. Electr. Eng., vol. 103, p. 108319, Oct. 2022, doi: 10.1016/j.compeleceng.2022.108319.

W. Xu, D. Zhu, R. Deng, K. Yung, and A. W. H. Ip, “Violence-YOLO: Enhanced GELAN Algorithm for Violence Detection,” Appl. Sci., vol. 14, no. 15, p. 6712, Jan. 2024, doi: 10.3390/app14156712.

L. Ye, L. Wang, H. Ferdinando, T. Seppänen, and E. Alasaarela, “A Video-Based DT–SVM School Violence Detecting Algorithm,” Sensors, vol. 20, no. 7, p. 2018, Apr. 2020, doi: 10.3390/s20072018.

H. A. Pratiwi, M. Cahyanti, and M. Lamsani, “Implementasi deep learning flower scanner menggunakan metode convolutional neural network,” J. Inform., vol. 2, no. 1, pp. 41–59, 2021.

S. A. Putri, A. Rifai, and I. Nawawi, “Aplikasi Cerdas Sistem Deteksi Tindak Kekerasan Fisik Untuk Pengawasan Perundungan Dengan Convolutional Neural Network,” JSAI J. Sci. Appl. Inform., vol. 7, no. 2, 2024.

S. A. Putri, A. Rifai, and I. Nawawi, “Sistem Cerdas Deteksi Tindak Kekerasan Untuk Pengawasan Perundungan Dengan Model Deep Learning,” JSAI J. Sci. Appl. Inform., vol. 7, no. 2, pp. 332–340, Jun. 2024, doi: 10.36085/jsai.v7i2.6451.

F. Cai, Y. Du, and X. Qin, “An Improved YOLOv7-CO Classroom Behavior Detection Algorithm Combining Coordinate Attention Mechanism and Omni-Dimensional Dynamic Convolution,” in Artificial Intelligence and Human-Computer Interaction, Y. Ye and P. Siarry, Eds., SAGE Publications, 2024. doi: 10.3233/FAIA240167.

M. Sofhia, “Comparative Evaluation of YOLOv8 and YOLOv11 for Student Behavior Detection in Classroom CCTV Environments.” Accessed: Aug. 06, 2026. [Online]. Available: https://www.jurnal.polgan.ac.id/index.php/sinkron/article/view/15648

L. Ye, L. Wang, H. Ferdinando, T. Seppänen, and E. Alasaarela, “A Video-Based DT–SVM School Violence Detecting Algorithm,” Sensors, vol. 20, no. 7, p. 2018, Apr. 2020, doi: 10.3390/s20072018.

M. S. Januriansyah and F. Samopa, “YOLOv11-Based Early Warning System for Violence and Weapon Detection,” in 2025 International Conference on Innovation and Intelligence for Informatics, Computing, and Technologies (3ICT), Sakhir, Bahrain: IEEE, Nov. 2025, pp. 1–6. doi: 10.1109/3ict68299.2025.11442141.