No Detail Found!

Fraud detection using isolation forest for RFID-based attendance monitoring system

Author(s)
Mark Lister V. Nalupa University of Science and Technology of Southern Philippines, C.M. Recto Ave., Lapasan, Cagayan de Oro City, Philippines
Jodie Rey D. Fernandez University of Science and Technology of Southern Philippines, C.M. Recto Ave., Lapasan, Cagayan de Oro City, Philippines
Wencel Jean C. Dacay University of Science and Technology of Southern Philippines, C.M. Recto Ave., Lapasan, Cagayan de Oro City, Philippines
Miriam M. Bergado University of Science and Technology of Southern Philippines, C.M. Recto Ave., Lapasan, Cagayan de Oro City, Philippines
Abstract
Monitoring students' attendance using RFID technology on a regular basis is of utmost importance in the education sector. However, the use of RFID-based attendance has been heavily criticized for its vulnerability to counterfeit attendance. Anyone holding the RFID tag can mark an attendance to the system. This study aims to design and develop fraud detection on attendance. The system implementation resulted in an RFID-based attendance monitoring system capable of detecting suspicious attendance. The Isolation Forest, an unsupervised machine learning algorithm, was used to identify anomalies within the attendance dataset. The result shows that the machine learning model attained an accuracy score of 95.69%, a precision score of 96.33%, and a recall score of 95.81%. The study concludes that detecting suspicious attendance using an Isolation Forest is possible. It is recommended to be integrated with existing RFID-based attendance monitoring systems to minimize fraud or counterfeit attendance.
Publication Details
Page(s) 511-517
DOI DOI not available
Published Journal: Science International, Volume: 34, Issue: 6, Year: 2022

Request the full text from PASTIC

Keywords
Fraud Detection, RFID-based attendance, attendance monitoring system, isolation forest
0

Citations

0

Downloads

147

Views