A COMPARATIVE ANALYSIS OF AIR QUALITY INDEX (AQI) CALCULATIONS USING RAW AND CLEANED SENSOR DATA
Reyimberdiyev T. . & Khujaev O. .
Annotatsiya
This study presents a comparative analysis of Air Quality Index (AQI) calculations derived from raw and cleaned PM2.5 sensor data within a smart city monitoring framework. While low-cost sensors enable dense real-time monitoring, they are inherently susceptible to noise, calibration drift, and outliers that distort AQI accuracy. To mitigate these issues, a multi-stage data processing pipeline was developed, integrating moving average smoothing, Kalman filtering, physical constraint enforcement, and Z-score–based anomaly detection. Utilizing a dataset of 15,000 records, the methodology demonstrates that data cleaning significantly enhances signal reliability: the standard deviation of PM2.5 concentrations was reduced from 17.09 to 3.51, while AQI variability decreased from 40.94 to 7.75. AQI values were computed using U.S. EPA breakpoints and classified under the IQAir framework, revealing that cleaned data provide a more stable and interpretable representation of air quality levels. The findings confirm that robust preprocessing is a critical prerequisite for accurate environmental assessment and informed decision-making in smart city monitoring systems.
Adabiyotlar
- World Health Organization (WHO), WHO Global Air Quality Guidelines: Particulate Matter (PM2.5 and PM10), Ozone, Nitrogen Dioxide, Sulfur Dioxide and Carbon Monoxide. Geneva: World Health Organization, 2021.
- U.S. Environmental Protection Agency (EPA), Technical Assistance Document for the Reporting of Daily Air Quality – the Air Quality Index (AQI), EPA-454/B-18-007, Research Triangle Park, NC, 2018.
- E. G. Snyder et al., "The changing paradigm of air pollution monitoring," Environmental Science & Technology, vol. 47, no. 20, pp. 11369–11377, 2013.
- [4] N. Castell et al., "Can commercial low-cost sensor platforms contribute to air quality monitoring and exposure estimates?" Environment International, vol. 99, pp. 293–302, 2017.
- G. E. P. Box, G. M. Jenkins, G. C. Reinsel, and G. M. Ljung, Time Series Analysis: Forecasting and Control, 5th ed. Hoboken, NJ: Wiley, 2015.
- R. E. Kalman, "A new approach to linear filtering and prediction problems," Journal of Basic Engineering, vol. 82, no. 1, pp. 35–45, 1960.
- G. Welch and G. Bishop, "An introduction to the Kalman filter," Univ. of North Carolina at Chapel Hill, Chapel Hill, NC, Tech. Rep. TR 95-041, 2006.
- C. C. Aggarwal, Outlier Analysis, 2nd ed. New York, NY: Springer, 2017.
- V. Chandola, A. Banerjee, and V. Kumar, "Anomaly detection: A survey," ACM Computing Surveys, vol. 41, no. 3, pp. 1–58, 2009.
- A. Kerimray et al., "Assessing air quality changes in Almaty, Kazakhstan: Diagnosis of the strict quarantine lockdown effects," Environmental Pollution, vol. 256, Art. no. 115766, 2020.
- F. I. Salomova et al., "Monitoring of air pollution in Uzbekistan," American Journal of Pedagogical and Educational Research, vol. 11, pp. 173–179, 2023.
- L. K. Abdukadirova, "Study and assessment of the dynamics of atmospheric air pollution in Tashkent city," Tashkent Medical Academy, Tashkent, Uzbekistan, Rep., 2023.
- K. Shipilova and M. Radkevich, "Assessment of the atmospheric air quality in Tashkent," Universum: Technical Sciences, no. 12(81), 2020.
- B. M. Kono, "Urban Air Quality and IoT Sensor Health Data," Kaggle Datasets, 2024. [Online]. Available: https://www.kaggle.com/datasets/bertnardomariouskono/urban-air-quality-and-iot-sensor-health-data. [Accessed: Feb. 04, 2025].
- R. Mokhtari, A. Ghaffari, and A. R. Kian, "Deep learning-based calibration of low-cost air quality sensors," in Proc. IEEE Int. Conf. Smart City, 2021, pp. 1–6.
- Y. Zheng, F. Liu, and H. P. Hsieh, "U-Air: When urban air quality inference meets big data," in Proc. 19th ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining, 2013, pp. 1436–1444.