Implementation of an Artificial Intelligence-Based Smart Attendance Automatic Attendance System with Face Detection Using YOLOv11 at Muhammadiyah Ahmad Dahlan University, Palembang

Key findings from this study

This research indicates that:

• YOLOv11-based facial detection enables real-time student identification and automatic attendance recording without manual intervention.
• Integration with academic databases provides immediate attendance data accessibility to institutional stakeholders.
• Automated systems substantially reduce opportunities for attendance fraud and administrative recording errors.

Overview

This research describes the design and implementation of an automated student attendance system at Muhammadiyah Ahmad Dahlan University using YOLOv11-based facial detection integrated with campus academic databases. The system addresses operational challenges in manual attendance processes, including attendance fraud, recording delays, and administrative errors in higher education settings.

Methods and approach

The research employed the YOLOv11 algorithm for real-time facial detection and recognition. The system was integrated with the institutional academic database to enable automatic attendance recording and data transparency across lecturer and administrative interfaces.

Results

The implementation produced an automated attendance system capable of recognizing student faces in real-time and recording attendance data directly into campus databases. The system provides accessible attendance records to both lecturers and administrative personnel through transparent data presentation mechanisms. The deployment demonstrates technical feasibility of facial detection integration within higher education infrastructure.

Implications

The system reduces operational friction in attendance management by eliminating manual recording processes and associated administrative errors. Automated facial recognition diminishes opportunities for fraudulent attendance reporting while standardizing data collection across institutional enrollment. The implementation establishes a foundation for broader adoption of AI-based technologies within academic service delivery frameworks.

Further development could enhance system features and scalability for deployment across multiple educational institutions. The work exemplifies how computer vision technologies can address specific administrative challenges in higher education environments while supporting institutional digital transformation initiatives.

Scope and limitations

This summary is based on the study abstract and available metadata. It does not include a full analysis of the complete paper, supplementary materials, or underlying datasets unless explicitly stated. Findings should be interpreted in the context of the original publication.