Eco-Pulse: an IoT-Based Multi-Sensor Environmental Monitoring and Air Quality Prediction System

View at publisher Summarise with VIRAT
Authors: K. U. Gayathri, J. Kavipriya, S.R. Karthick
Cited by: 0
References: 10

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Environmental surveillance has also become a crucial issue into the study and alleviation of the effects of urbanization and climate change on the quality of the air and ecological wellbeing. In this paper, the author introduces EcoPulse, a system of integrated environmental monitoring relying on IoT to combine the real-time collection of sensor data with a machine-based air quality forecasting. Arduino UNO R3 microcontroller with several environmental sensors (mq-135, MQ-2, DHT22) and ESP8266 NodeMCU is used to transmit the data wirelessly. The developed model was a Random Forest regression model, which predicted the values of Air Quality Index (AQI) with Mean Absolute Error (MAE) of 5.38 and R2 of 0.220. Comparison of Eco-Pulse data with the reference data of Chennai revealed high correlation between temperature (r > 0.95) and humidity (r > 0.92) with the AQI monitoring approach revealing the mean expense of variation amounting to 3.2 units. The system was able to classify environmental conditions into four different zones with the use of K-means clustering with an accuracy of 0.81 with Gradient Boosting classification. The analysis of feature importance indicated that temperature was the most important predictor (importance=0.424), then humidity (0.341) and noise level (0.208). This was proved by continuous 24-hour monitoring, where the system could have constant environmental surveillance with a noise level reading of 48 to 78 dB.

Fields of Study & Subjects

Air Quality Monitoring and Forecasting Arduino and IoT Applications Water Quality Monitoring Technologies

Publication details

Journal / source
International Conference on Communication, Computing and Electronics Systems (ICCCES)
Pages
319–326
Publication date
21 January 2026
Language
EN