Smart Attendance: An Automated Attendance Management System Using Machine Learning Techniques

Abstract

The Smart Attendance system is a machine learning-based system that aims to improve the management and tracking of student attendance. It can be utilized in educational institutions to keep track of their students' attendance. The system uses radio frequency identification tags to record information in real time, which helps the system to provide updated and accurate records. The system uses machine learning techniques to analyze the data collected by it to identify trends and patterns in student attendance. This method can then be used to identify individuals who are habitually late or have high absenteeism rates. It can help educators implement effective measures to improve student attendance. The performance of various machine learning algorithms was evaluated in this study. The four algorithms were randomly forest, decision tree, SVM, and naive bayes. They were tested against conditions such as students who frequently skip certain classes, habitual latecomers, and individuals with high absenteeism rates. The results of the study revealed that the SVM and random forest algorithms performed well and had the highest accuracy rates. These findings show that these algorithms can help educators identify patterns in student behavior and implement effective measures to boost attendance. The Smart Attendance system has demonstrated the potential of artificial intelligence to help improve the management of student attendance in educational institutions. Through the use of machine learning and RFID tags, the system can provide up-to date and accurate records, as well as insights into the behavior of students. This information can then be utilized to implement effective measures to reduce absenteeism and improve student outcomes.