DESIGN AND DEVELOPMENT OF A MOBILE-BASED STUDENT ATTENDANCE SYSTEM INTEGRATING GEOLOCATION AND FACE RECOGNITION USING MOBILEFACENET AT THE D-III INFORMATICS ENGINEERING STUDY PROGRAM, PONTIANAK STATE POLYTECHNIC

Abstract

Student attendance in the D-III Informatics Engineering Study Program at Pontianak State Polytechnic is still recorded manually, making it prone to recording errors and time-consuming recapitulation. This applied research designs and develops a mobile-based attendance prototype that integrates on-device MobileFaceNet face verification with geofencing-based location validation using a prototyping approach. The prototype consists of a Flutter application, a Laravel backend, and a web dashboard featuring a liveness challenge, one-time attendance permits, offline attendance, attendance recapitulation, and an early warning mechanism for Warning Letters. All 255 automated backend tests and 214 mobile application tests passed. Evaluation of 1,485 impostor face pairs resulted in a False Accept Rate (FAR) of 0% at a threshold of 0.60, while load testing with 20–40 concurrent users produced 95th-percentile response times below 2 seconds. However, the False Reject Rate (FRR) has not yet been measured, location and facial evidence are still computed on the device, and the liveness mechanism has not been tested against photo attacks, video replay, or deepfakes. Therefore, the system cannot yet be claimed to prevent proxy attendance or location spoofing.