Development geofencing process and face recognition design using haversine formula and the k-nearest neighbor algorithm in the employee attendance application

Abstract

Attendance is an important factor in assessing employee discipline for a company. Discipline issues in recording employee attendance are an important concern for companies that have many branches or outlets because the company cannot directly monitor their employees. Some companies usually use finger print machines and some even use manual methods. This method is a problem for several companies that have several outlets or branches to record attendance data centrally and accurately. As a solution that is with the application of employee attendance that applies geofencing and face recognition as security in recording the attendance of employees who are at the company's outlets or branches. Geofencing is a technology for conducting remote surveillance of a predetermined area. While face recognition is a technology from a computer to recognize a person's face. In this study using the haversine formula, Euclidean distance, and KNN (K-Nearest Neighbor) algorithm in determining the last location and face recognition of employees by comparing face data that has been registered in the database. Users who record attendance outside the radius cannot record attendance. The face recognition accuracy rate has a percentage of 98%.