Comparison and Evaluation of Air Quality Monitoring Methods Using Iot Devices (Published)
Comparing the efficiency and accuracy of air quality monitoring methods is an important aspect to ensure the protection of the environment and the health of citizens. In this study, we developed a project to measure air quality in several areas using Internet-connected devices built with Arduino and a standardised device such as AirVisual. To evaluate the accuracy and performance of the two monitoring methods, we collected data including humidity levels, temperature, and PM 2.5 (particulate matter) from both devices. Through the analysis of these data, we compared and evaluated the changes in air quality and the performance of the two methods in real time. The results of our study provide a deep understanding of the compatibility and accuracy of different air quality monitoring methods and contribute to the development of knowledge in this field. This study points out the importance of using IoT technology for air quality monitoring and the opportunities for improving existing monitoring methods.
Keywords: AirVisual, IoT, air quality, arduino, data, low cost devices
Applying an Ordinary Least Squares (OLS) Regression Model On Processed Air Quality and Environment Data (Published)
This scientific research is primarily based on real-time data collected on air quality. A comprehensive and extensive study was initially conducted to explore the key factors contributing to air pollution. Other relevant information will encompass additional components such as PM10, PM1, and weather-related factors like temperature, humidity, and air pressure. In order to provide a more reliable but at the same time qualitative information it was essential to examine the anomalies and issues revealed by the gathered data. After carefully identifying and correcting anomalies in the dataset, various statistical analyses have been conducted and results have been presented in both tabular and visual formats. These data are based on fundamental inquiries directly tied to the significance of air quality. After interpreting the statistics, a regression model such as OSL was used always including data that do not have multicollinearity. Based on the findings, it appears that this model is not suitable for forecasting PM2.5 levels because of a significant association between PM10 and PM1
Keywords: AQI, Model, PM 2.5, Regression Model, data, displot function