Rasid, Saiful (2026) Sistem Presensi Guru dan Siswa Menggunakan Convolutional Neural Network Berbasis Mobile (Studi Kasus di SMKN 1 Tamanan). Undergraduate thesis, Politeknik Negeri Jember.
![[img]](https://sipora.polije.ac.id/style/images/fileicons/text.png) |
Text (Abstract)
Abstract.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (11kB) |
|
Text (Bab 1 Pendahuluan)
Bab 1 Pendahuluan.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (165kB) |
|
Text (Daftar Pustaka)
Daftar Pustaka.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (273kB) |
|
Text (Laporan Lengkap)
Laporan Lengkap.pdf Restricted to Registered users only Download (3MB) | Request a copy |
Abstract
The attendance system used at SMKN 1 Tamanan has several weaknesses, including time inefficiency, the potential for fraud, and difficulties in managing and recapitulating the data. These issues arise because the school still relies on a manual method in which teachers call students one by one in each subject session, followed by homeroom teachers rechecking attendance to confirm student presence. This process is highly time-consuming and produces records that are difficult to compile and interpret by other stakeholders. To address these limitations, the study proposes a mobile-based attendance system for teachers and students using a Convolutional Neural Network (CNN) approach with the Mobilefacenet architecture for facial recognition. The system was developed using the Flutter framework, MediaPipe for face detection, and a pretrained Mobilefacenet model as a feature extractor. The attendance process consists of face detection, preprocessing, feature extraction in the form of s, and verification using the Cosine Similarity method with a predefined threshold. Testing results indicate that the system performs well, achieving a 100% success rate in Blackbox Testing, an average facial recognition accuracy of 80.88%, and a User Acceptance Test (UAT) score of 77.31%. Therefore, the developed system is able to improve the attendance process by making it easier and more efficient, and more manageable through online integration.
Actions (login required)
 |
View Item |
