AI Based Ventilation KPI Using Embedded IoT Devices

Abstract

This paper presents an Artificial Intelligence (AI)- based Key Performance Indicator (KPI) system for ventilation, integrating embedded Internet of Things (IoT) devices to enhance indoor air quality management. The proposed model employs sensors such as MQ135, MQ2, DHT11, and a dust sensor, interfaced with a Raspberry Pi for real-time monitoring. The system uses a linear regression algorithm to predict ventilation efficiency and automatically activates actuators such as a relay- controlled ozone generator and CPU fan to optimize airflow and purification. The results show that the system effectively improves air quality, energy efficiency, and automation for smart building environments.

Introduction

The text discusses the importance of Indoor Air Quality (IAQ) in maintaining human health and highlights the limitations of traditional ventilation systems, which are often inefficient and unable to respond proactively to pollution. Poor IAQ can lead to serious health problems such as respiratory and cardiovascular diseases. To address these issues, the paper proposes an AI-based smart ventilation system that combines Artificial Intelligence (AI) and the Internet of Things (IoT) for real-time monitoring and automated air quality management.

The proposed system uses multiple sensors, including MQ135, MQ2, Dust Sensor, and DHT11, connected to a Raspberry Pi through an MCP3208 ADC module. These sensors monitor gases, dust particles, temperature, and humidity. The collected data is analyzed using machine learning techniques such as Linear Regression and Random Forest Classifier to predict ventilation efficiency and detect unsafe environmental conditions.

Based on the predicted air quality KPI, the system automatically controls an ozone generator and CPU cooling fan through relay modules to purify and circulate air efficiently. The architecture consists of sensor, processing, actuation, and display layers, ensuring continuous monitoring, intelligent decision-making, and user alerts through an LCD display and buzzer.

Compared to traditional threshold-based systems, the proposed model offers predictive analytics, automation, energy efficiency, and improved reliability. By integrating AI, IoT, embedded systems, and machine learning, the system provides a smart, data-driven solution for maintaining healthy indoor air quality while minimizing energy consumption.

Conclusion

The proposed framework offers a robust and intelligent solution for monitoring and optimizing ventilation performance by seamlessly integrating embedded IoT devices with AI- driven KPI analytics. Leveraging a network of environmental sensors, microcontroller-based processing, and advanced data analysis, the system provides continuous, real-time evaluation of indoor air quality and overall operational efficiency. This integration enhances the accuracy, adaptability, and responsiveness of ventilation control while simultaneously enabling energy optimization and predictive maintenance. By transforming conventional ventilation systems into dynamic, data-informed, and self-regulating infrastructures, the approach demonstrates significant potential to improve occupant health, operational reliability, and environmental sustainability. Overall, the system advances the development of smart building technologies and contributes to healthier and more resilient indoor environments.

References

[1] Alekhya, K., Sravya, P. D., Naik, N. C., & Lakshmi Narayana, B. J. (2023). Ambient Air Quality Monitoring System. ICONAT, 2023. [2] Amado, T. M., & Dela Cruz, J. C. (2018). Development of Machine Learning-Based Predictive Models for Air Quality Monitoring. IEEE TENCON. [3] Ansari, M., & Alam, M. (2023). An Intelligent IoT-Cloud-Based Air Pollution Forecasting Model. Arabian Journal for Science and Engineering, 49. [4] Alam, M. A., Sohel, A., Uddin, M. M., & Siddiki, A. (2024). Big Data and Chronic Disease Management Through Patient Monitoring and Treatment With Data Analytics. Academic Journal on AI, ML, and MIS. [5] Buelvas, J., Múnera, D., Tobón, D. P., Aguirre, J., & Gaviria, N. (2023). Data Quality in IoT-Based Air Quality Monitoring Systems. Water, Air, & Soil Pollution, 234. [6] P. S. Sharma and G. S. Tomar, “IoT-Based Real-Time Air Quality Monitoring and Control System,”

Copyright

Copyright © 2026 Bindu T, Chandana CV, Chithra D, Dhanusha DS, Dr. Kavitha. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.