IoT-Based Classroom Temperature Monitoring and Missing Data Prediction Using Raspberry Pi and ESP32

Navarrete-Sanchez, M. A.
Olivera-Reyna, Re.
Olivera-Reyna, Ro.
Perez-Chimal, R. J.
Munoz-Minjares, J. U.

Journal of Robotics and Control (JRC)
Vol. 6 No. 1 (2025)

This study focuses on accurate temperature monitoring to optimize classroom conditions, enhancing student comfort and performance by providing precise data on temperature dynamics and ensuring reliability through advanced algorithms for handling missing data. Currently, advances in the Internet of Things (IoT) have enabled the development of simple, scalable, and intuitive systems for real-time environmental monitoring. This work presents a novel architecture for monitoring temperature dynamics in an electronic laboratory, leveraging a system of interconnected IoT devices with Wireless Fidelity (WiFi) communication. The system employs an ESP32 microcontroller and DS18B20 temperature sensors placed strategically around the classroom, including near windows and doors, to provide comprehensive data on heat distribution. The ESP32 is a small, low-cost, and powerful electronic chip that acts as the central processor for IoT systems, capable of handling data and connecting to a Wireless Network trough WiFi. While the DS18B20 can be defined as a digital sensor that accurately measures temperature and transmits the data electronically to a connected device. Therefore, the ESP32 microcontroller acts as the central processor, receiving temperature data from the DS18B20 sensors, which are configured to detect and transmit measurements. So, this data is then sent over a secure local WiFi network for real-time monitoring and analysis. The proposed system offers several advantages over existing solutions, including cost effective deployment, ease of integration, and real time monitoring. By using a secure local network for communication, it ensures reliable and uninterrupted data transmission. Furthermore, the I-UFIR algorithm was implemented to estimate missing temperature data points, significantly improving the accuracy of temperature readings and providing smoother, more reliable estimations. This system not only demonstrates the feasibility of IoT-based temperature monitoring in educational settings, but also highlights its potential to improve learning environments by optimizing classroom conditions.