Implementation of Convolutional Neural Network and Vincenty Formula on Face Attendance System Web-Based for Managing the Attendance

Abstract

The level of student attendance at tertiary institutions has a crucial role in determining the quality of education. The Information Technology Department at Padang State Polytechnic realizes the urgent need to increase the efficiency of managing student attendance, which currently still relies on a manual attendance system. As an innovative solution, this research proposes designing a face-based attendance system that utilizes facial recognition technology to verify student attendance automatically. One of the challenges in developing a face-based attendance system is the accuracy of calculating the distance between the student's location and the institutional location. To overcome this problem, the research used the Vincenty Formula method which was proven to have a high level of accuracy in calculating the distance between two points on the earth. The integration of this method is expected to increase the accuracy of calculating the distance between the student's location and the institution. Apart from that, this attendance system adopts the Convolutional Neural Network (CNN) algorithm, an algorithm specifically designed to process two-dimensional data. CNN is used to learn and detect features in images so that facial recognition can be done with a high level of accuracy. This approach is expected to improve system performance in recognizing and verifying student attendance.