Saved in:
| Main Author: | |
|---|---|
| Format: | Recurso digital |
| Language: | |
| Published: |
Zenodo
2026
|
| Online Access: | https://doi.org/10.5281/zenodo.20064408 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Table of Contents:
- <h3>Abstract</h3> <div>Contemporary educational establishments are confronting a twofold challenge: ensuring student safety while reducing substantial electricity expenses. At present, many campuses depend on security personnel and manual controls to handle this, yet these approaches are sluggish, costly, and susceptible to human mistakes. This project introduces a Smart Campus Automation System that eliminates the necessity for manual management to tackle these inefficiencies. The system utilizes a network of Raspberry Pi controllers and ESP32 sensors to gather data in real-time. We incorporated two particular AI models: Convolutional Neural Networks (CNN) for automatic identification of security threats, and Deep Reinforcement Learning (DRL) for forecasting energy requirements based on occupancy in rooms. When compared with findings from ten recent studies, this automated method anticipated a decrease in energy usage of about 40%. At the same time, it enhanced security response times by 30%, identifying unauthorized access much quicker than human oversight. These results demonstrate that combining IoT with Artificial Intelligence provides a scalable, affordable solution that converts typical campuses into self-managing, secure, and sustainable settings.</div> <h3>Keywords</h3> <p>Smart Campus, Internet of Things (IoT), Artificial Intelligence, Energy Optimization, Convolutional Neural Networks (CNN), Automation.</p>