AI-SLMS: An AI-Integrated Framework for Predictive Maintenance, Intelligent Scheduling, and Access Control in University Laboratory Management Systems

Abstract

In recent years, a smart, safe, and efficient way to run university labs has become increasingly popular. Traditional management systems rely on manual processes that are error-prone, slow, and offer limited adaptability. To address these challenges, this study proposes a Smart Laboratory Management System (AI-SLMS) that optimizes operations, improves safety, and enhances the user experience in academic labs. AI-SLMS integrates predictive maintenance, intelligent scheduling, and secure access control using machine learning and the Internet of Things (IoT). The system employs Random Forest and Logistic Regression models, trained on integrated datasets (Kaggle Predictive Maintenance and TON_IoT), to anticipate equipment failures. For resource allocation, an intelligent scheduling module utilizes genetic algorithms for optimization. The system also enforces role-based access through RFID and biometric authentication. Experimental validation over three months in a university setting demonstrated significant improvements across key metrics: a 71.2% reduction in equipment downtime, a 78.7% decrease in scheduling conflicts, a 53.5% improvement in resource utilization, and 98.3% authentication accuracy. In conclusion, AI-SLMS offers a scalable and intelligent framework that significantly enhances the efficiency, security, and responsiveness of university laboratory management systems.