Design and Optimization of Smart Campus Framework Based on Artificial Intelligence

Abstract

In this study, an artificial intelligence (AI)-based smart campus framework is built and optimized with the aim of improving user happiness, raising AI model performance, maximizing resource utilization, and promoting smart campus adoption. The study technique employs a mixed-methods approach that combines quantitative data analysis and qualitative user feedback in order to completely evaluate the effectiveness of the framework. Literature reviews, Questionnaires of 544, interviews of 56 persons, and observations are used to collect data on user satisfaction, AI model performance, optimization strategies, and adoption of smart campuses AI models are built using statistical methodology and AI techniques for performance evaluation. In the Smart Campus Framework based on Artificial Intelligence, we gathered the data by constructing IoT sensor networks for real-time monitoring and merging student data to provide insights into academic performance and student engagement. The findings indicate that, on average, users are satisfied, and the performance ratings for the AI models vary from 7.25 to 8.25. The smart campus framework is effective, as evidenced by the optimization metric's 7.53 average score. A score of 7.4 for smart campus adoption combines user knowledge, perceived utility, and perceived ease of use. The practical implications include better user experience, cost optimization, and smart campus architecture. Theoretical implications include the verification of the mixed-methods strategy and the creation of a framework for AI model optimization. The study's findings act as a model for upcoming smart campus research, spurring creativity and change in institutions of higher learning. The study’s limitations suggest that results can be generalized with minor contextual change and this is the biggest challenge for researchers and policy makers.