OPTIMIZED SMART CITY POLLUTION MONITORING AND CONTROL SYSTEM FOR AWKA METROPOLIS USING WIRELESS SENSOR NETWORKS AND IOT

Obodoeze Fidelis C.; Ogbonna-Mba Calister Nnenna; Dr. Odegwo James I.; Ikedilo Obiora Emeka; Osuji Levi Nnaemeka

Authors

Dr. Obodoeze Fidelis C. Department of Computer Engineering, Akanu Ibiam Federal Polytechnic,Unwana, Ebonyi State, Nigeria
Ogbonna-Mba Calister Nnenna Department of Electrical/Electronic Engineering, Alex Ekwueme Federal University, Ndufu-Alike, Ebonyi State, Nigeria
Dr. Odegwo James I. Department of Data Sciences and Analytics , Southern Delta University, Ozoro, Delta State, Nigeria
Dr. Ikedilo Obiora Emeka Department of Computer Science, Akanu Ibiam Federal Polytechnic, Unwana, Nigeria
Osuji Levi Nnaemeka Department of Computer Engineering, Akanu Ibiam Federal Polytechnic, Unwana, Nigeria

Keywords:

Smart city, Awka Metropolis, Air pollution, Noise pollution, Air Quality Index (AQI), Wireless Sensor Network (WSN), Internet of Things (IoT), Artificial Neural Network (ANN), Pollution monitoring, Real-time system, Smart Citizen Kit

Abstract

This paper presents the development and validation of a cost-effective, real-time air quality monitoring and control system for Awka Metropolis, Nigeria, integrating Wireless Sensor Networks (WSNs) and Internet of Things (IoT) technologies. By deploying pollution sensors at eight city hotspots and creating an ANN-based predictive model for the Air Quality Index (AQI), the system enables smart forecasting, real-time cloud visualization, and mobile accessibility via an Android app. Air pollution and environmental noise have become critical public health concerns in rapidly urbanizing cities like Awka, Anambra State, Nigeria. In response, this study developed and optimized a smart city air and noise pollution monitoring and prediction system using a wireless sensor network and machine learning models. A real-time monitoring substation, built with the Smart Citizen Kit (SCK), was deployed across Awka Metropolis to collect 12,958 datasets over 43 days. The system recorded six pollutant variables—PM1.0, PM2.5, PM10.0, eCO₂, TVOC, and noise—alongside meteorological parameters including temperature, pressure, humidity, and light intensity. Eight machine learning algorithms—Multiple Linear Regression (MLR), Support Vector Regression (SVR), Multi-Layer Perceptron (MLP-ANN), Decision Tree, Random Forest, AdaBoost, XGBoost, and Extra Trees—were evaluated using both Train-Test Split and 10-Fold Cross-Validation. Results showed that ensemble models, particularly Extra Trees and Random Forest, significantly outperformed others in terms of predictive accuracy (R² ≥ 0.99 for key pollutants) and residual error (low RMSE and MAE). Hybrid models (stacking and voting ensembles) did not offer additional performance gains. Noise prediction yielded poor results (R² < 0.60), suggesting the need for broader contextual features. The research contributes a deployable low-cost monitoring system and pollutant-specific predictive models that can support proactive environmental health interventions in Awka and similar urban centers.

References

Aarthi, A., et al. (2020). Air Quality Prediction Through Regression Model. International Journal of Scientific and Technology Research, 9(3), 923–928.

Aceves-Fernández, M.A., et al. (2020). Evaluation of Key Parameters Using Deep Convolutional Neural Networks for Airborne Pollution (PM10) Prediction. Hindawi.

Aljanabi, M., et al. (2020). Ground-level Ozone Prediction Using Machine Learning Techniques: A Case Study in Amman, Jordan. International Journal of Automation and Computing.

Allam, Z. (2019). Achieving Neuroplasticity in Artificial Neural Networks through Smart Cities. Smart Cities, 2, 118–134.

Anambra State–Nigeria Erosion and Watershed Management Project (ANS-NEWMAP). (2014). Environmental and Social Management Plan Draft Report for Nerose Plaza–Thomas Aquinas Gully Erosion Intervention Site.

Arroyo, P., Herrero, J. L., Suárez, J. I., & Lozano, J. (2019). Wireless Sensor Network Combined with Cloud Computing for Air Quality Monitoring. Sensors, 19(3), 691.

Brienza, S., Galli, A., Anastasi, G., & Bruschi, P. (2015). A low-cost sensing system for cooperative air quality monitoring in urban areas. Sensors, 15(6), 12242–12259.

Castelli, M., et al. (2020). A Machine Learning Approach to Predict Air Quality in California. Hindawi Complexity.

Chiou-Jye, H., & Ping-Huan, K. (2018). A Deep CNN-LSTM Model for Particulate Matter (PM2.5) Forecasting in Smart Cities. Sensors, 18(2220).

Cortina-Januchs, M.G., et al. (2015). Development of a Model for Forecasting of PM10 Concentrations in Salamanca Mexico. Atmospheric Pollution Research, 6, 626–634.

Dedovic, M.N., et al. (2016). Forecasting PM10 Concentrations Using Neural Networks and Systems for Improving Air Quality. XI International Symposium on Telecom (BIHTEL).

Devi, P.D. & Chandrakala, M. (2021). Air Quality Prediction Using Ensemble Machine Learning Algorithm. IJERT.

Džaferovic, E., & Hadžiabdic, K.K. (2021). Air Quality Prediction and Application Using Machine Learning Methods: A Case Study of Bjelave Neighborhood. Lecture Notes in Network Systems, 142.

Eslami, E., et al. (2019). A Real-Time Hourly Ozone Prediction System Using Deep Convolutional Neural Network. Neural Computing and Applications.

Feng, X., et al. (2015). Artificial Neural Network Forecasting of PM2.5 Pollution Using Air Mass Trajectory Based Geographic Model and Wavelet Transformation. Atmospheric Environment, 107, 118–128.

Goulier, L., et al. (2020). Modelling of Urban Air Pollutant Concentrations with Artificial Neural Networks Using Novel Input Variables. International Journal of Environmental Research and Public Health, 17(2025).

Ghazali, S., & Ismail, L.H. (2017). Air Quality Prediction Using Artificial Neural Networks. CORE.

Joharestani, M., et al. (2019). PM2.5 Prediction Based on Random Forest, XGBoost, and Deep Learning Using Multisource Remote Sensing Data. Atmosphere, 10(373).

Kıymet Kaya & Öğüdücü, Ş.G. (2020). Deep Flexible Sequential Model for Air Pollution Forecasting. Scientific Reports, 10(3346).

Khanna, E. (2015). Neural Network Based Regression Testing. International Journal of Advanced Technology in Engineering and Science, 1(3).

Liang, Y.-C., et al. (2020). Machine Learning-Based Prediction of Air Quality. Applied Sciences, 10(9151).

Madhuri, V.M., et al. (2020). Air Pollution Prediction Using Machine Learning Supervised Learning Approach. IJSTR, 9(4), 118–123.

Mansour, S., Nasser, N., Karim, L., & Ali, A. (2014). Wireless Sensor Network-based Air Quality Monitoring System. IEEE Computing, Networking and Communications Conference.

Masih, A. (2019). Machine Learning Algorithms in Air Quality Modeling. Global Journal of Environmental Science and Management, 5(4), 515–534.

Memon, M. (2022). ANN vs CNN vs RNN: Neural Networks Guide. Levity.ai..

Mishra, A. (2018). Air Pollution Monitoring System Based on IoT: Forecasting and Predictive Modeling Using Machine Learning. AESPC 2018 Conference Proceedings.

Obodoeze, F. C., & Amadi, A. O. (2018). The Awka Smart City Project: Challenges and Roadmap. In Proceedings of the 2018 Biennial School of Engineering Conference, Unwana, Nigeria.

Pan, B. (2018). Application of XGBoost Algorithm in Hourly PM2.5 Concentration Prediction. IOP Conf. Ser.: Earth Environ. Sci., 113(012127).

Qadeer, K., et al. (2020). A Long Short-Term Memory Network for Hourly Estimation of PM2.5 Concentration in Two Cities of South Korea. Applied Sciences, 10(3984).

Rahimi, A. (2017). Short-Term Prediction of NO2 and NOx Concentrations Using Multilayer Perceptron Neural Network. Ecological Processes, 6(4).

Sankar, G.S., et al. (2019). Forecasting Air Quality Index Using an Ensemble of Artificial Neural Networks and Regression Models. Journal of Intelligent Systems, 28(5), 893–903.

Shah, S., et al. (2021). A Hybrid Model for Forecasting of Particulate Matter Concentrations Based on Multiscale Characterization and Machine Learning. Mathematical Biosciences and Engineering, 18(3), 1992–2009.

Shashi, R.G., et al. (2020). Analysis of Fine-Grained Air Quality and Prediction of Air Pollution. IRJET, 7(5), 6125–6127.

Shishegaran, A., et al. (2020). Prediction of Air Quality in Tehran by Developing the Nonlinear Ensemble Model. Journal of Cleaner Production, 259(120825).

Smartcitizenkit (2025). Smart Citizens Kit. Accessed online at https://docs.smartcitizen.me/hardware/kit/

Subramanian, V.N. (2016). Data Analysis for Predicting Air Pollutant Concentration in Smart City Uppsala. MSc Thesis, Uppsala Universitet.

Su, X., et al. (2020). Prediction of Ozone Hourly Concentrations by Support Vector Machine and Kernel Extreme Learning Machine. Atmospheric Pollution Research, 11(6), 51–60.

Wang, W., et al. (2019). Estimation of PM2.5 Concentrations in China Using a Spatial Back Propagation Neural Network. Scientific Reports, 9(13788).

Zamani, M., et al. (2019). PM2.5 Prediction Based on Random Forest, XGBoost and Deep Learning Using Multisource Remote Sensing Data. Atmosphere, 10(373).

Zhang, Y., et al. (2012). A review of air pollution prediction methods. Environment International, 32(6), 707–717.

Wikipedia Contributors. (2020). Awka. Retrieved from https://en.wikipedia.org/wiki/Awka

OPTIMIZED SMART CITY POLLUTION MONITORING AND CONTROL SYSTEM FOR AWKA METROPOLIS USING WIRELESS SENSOR NETWORKS AND IOT

Authors

Keywords:

Abstract

References

Downloads

Published

Issue

Section

License