RFID Monitoring System Using Machine Learning: A Design Thinking Approach for Smarter Attendance Solutions

• Published in: 2024 10th International Conference on Advanced Computing and Communication Systems (ICACCS) Vol. 1; pp. 1816 - 1820
• Main Authors: Sivasankari, B., Vishwamoorthy, R., Kannan, K. Surya, Nithyaprakash, B., Sabarish, S.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 14-03-2024
• Subjects: Accuracy; Attendance Monitoring; Data Accuracy; Machine Learning; Manuals; Monitoring; Prediction algorithms; Predictive Analysis; Predictive models; Radio Frequency Identification (RFID); Radiofrequency identification; Random forests; Resource management; RFID tags; Smart Attendance Solutions; Smart Systems
• ISBN: 9798350384352
• ISSN: 2469-5556
• DOI: 10.1109/ICACCS60874.2024.10717244

In the context of attendance monitoring, Radio Frequency Identification (RFID) technology has emerged as a critical option, providing seamless and efficient tracking capabilities. This study solves challenges common to traditional attendance tracking methods, such as data discrepancies and manual errors, by utilizing advanced algorithms and Machine Learning (ML) techniques. The suggested method employs ML, specifically a Random Forest Classifier, effectively analyzes recorded data, allowing for proactive resource allocation based on previous attendance trends. By examining historical attendance trends, the ML model may predict future attendance, allowing for more proactive resource allocation and management decisions. It also displays crucial insights from the collected data in visually attractive formats such as charts and graphs. Data accuracy is improved by utilizing hardware infrastructure such as RFID scanners and tags, which collect data automatically and precisely. RFID tags include unique identification codes that are scanned by RFID readers. This enables faster and more error-free data collection, improving accuracy as compared to human data entry methods. The seamless integration of RFID and machine learning not only streamlines the attendance tracking process, but also paves the way for future advances in predictive attendance management.