Air pollution has very serious health impacts as well as detrimental effects on ecosystems. Addressing this issue will require operational real-time monitoring and management, specifically in urban environments. Potential sensors that could provide the necessary high accuracy are too costly for mass deployment in the Internet of Things (IoT) environment. On the other hand, low-cost sensors usually have noisy, unreliable, and less accurate outputs, preventing them from being effective tools in real-time applications. Therefore, there is a lack of cost-effective, accurate, and scalable solutions to enhance the reliability of low-cost sensors such that they can improve air quality monitoring and control in real-time. Consequently, this research proposes a novel approach that advances the use of embedded machine learning with edge computing to enhance the accuracy and real-time actions at the local level. In the system, the Raspberry Pi was utilized for processing sensor information as the embedded edge device to monitor multiple real-time air pollutants, including SO2, NO2, and PM2.5. In this research, the one-rank cuckoo search-driven adaptive support vector machine (ORCS-ASVM) was proposed to improve the prediction accuracy of low-cost sensors with noise. The ORCS-ASVM machine learning model predicts air quality and reduces the amount of computing power required while providing immediate knowledge about the amount of air pollution present. This model strives to enhance the accuracy of low-cost sensor readings, thus accommodating erroneous sensor readings in pollution prediction. Data on air pollution that is continuously collected from the sensors will be monitored at regular intervals to provide real-time monitoring. Sensor data often contains noise, requiring filtering and preprocessing techniques to correct sensor errors. Smoothing and normalization are the most common preprocessing methods used to correct sensor errors. Compared with traditional prediction algorithms, the proposed model outperformed traditional methods in terms of error reduction. Air pollutants such as PM2.5, SO2, and NO2 achieved detection accuracies of 94.2%, 95.2%, and 94.8%, respectively. An embedded machine learning system approach for air quality monitoring and in situ pollution mitigation is a low-cost method that can be extended to other industries, making it suitable for smart city infrastructure, smart agriculture, and other important areas. An embedded machine learning approach is applicable to many areas as it has great scalability and flexibility and is therefore very suitable for widespread adoption by IoT-based pollution monitoring networks.
Citation: Xiaobo Li, Xinggang Ye, Meirong Qian. An embedded machine learning system method for air pollution monitoring and control[J]. AIMS Environmental Science, 2025, 12(4): 576-593. doi: 10.3934/environsci.2025026
Air pollution has very serious health impacts as well as detrimental effects on ecosystems. Addressing this issue will require operational real-time monitoring and management, specifically in urban environments. Potential sensors that could provide the necessary high accuracy are too costly for mass deployment in the Internet of Things (IoT) environment. On the other hand, low-cost sensors usually have noisy, unreliable, and less accurate outputs, preventing them from being effective tools in real-time applications. Therefore, there is a lack of cost-effective, accurate, and scalable solutions to enhance the reliability of low-cost sensors such that they can improve air quality monitoring and control in real-time. Consequently, this research proposes a novel approach that advances the use of embedded machine learning with edge computing to enhance the accuracy and real-time actions at the local level. In the system, the Raspberry Pi was utilized for processing sensor information as the embedded edge device to monitor multiple real-time air pollutants, including SO2, NO2, and PM2.5. In this research, the one-rank cuckoo search-driven adaptive support vector machine (ORCS-ASVM) was proposed to improve the prediction accuracy of low-cost sensors with noise. The ORCS-ASVM machine learning model predicts air quality and reduces the amount of computing power required while providing immediate knowledge about the amount of air pollution present. This model strives to enhance the accuracy of low-cost sensor readings, thus accommodating erroneous sensor readings in pollution prediction. Data on air pollution that is continuously collected from the sensors will be monitored at regular intervals to provide real-time monitoring. Sensor data often contains noise, requiring filtering and preprocessing techniques to correct sensor errors. Smoothing and normalization are the most common preprocessing methods used to correct sensor errors. Compared with traditional prediction algorithms, the proposed model outperformed traditional methods in terms of error reduction. Air pollutants such as PM2.5, SO2, and NO2 achieved detection accuracies of 94.2%, 95.2%, and 94.8%, respectively. An embedded machine learning system approach for air quality monitoring and in situ pollution mitigation is a low-cost method that can be extended to other industries, making it suitable for smart city infrastructure, smart agriculture, and other important areas. An embedded machine learning approach is applicable to many areas as it has great scalability and flexibility and is therefore very suitable for widespread adoption by IoT-based pollution monitoring networks.
| [1] |
Bălă GP, Râjnoveanu RM, Tudorache E, et al. (2021) Air pollution exposure—the (in) visible risk factor for respiratory diseases. Environ Sci Pollut Res 28: 19615–19628. https://doi.org/10.1007/s11356-021-13208-x doi: 10.1007/s11356-021-13208-x
|
| [2] |
Anjum MS, Ali SM, Subhani MA, et al. (2021) An emerged challenge of air pollution and ever-increasing particulate matter in Pakistan: A critical review. J Hazard Mater 402: 123943. https://doi.org/10.1016/j.jhazmat.2020.123943 doi: 10.1016/j.jhazmat.2020.123943
|
| [3] |
Ahmed N, Hamid Z, Mahboob F, et al. (2022) Causal linkage among agricultural insurance, air pollution, and agricultural green total factor productivity in the United States: Pairwise Granger causality approach. Agriculture 12: 1320. https://doi.org/10.3390/agriculture12091320 doi: 10.3390/agriculture12091320
|
| [4] |
Villanueva F, Ródenas M, Ruus A, et al. (2022) Sampling and analysis techniques for inorganic air pollutants in indoor air. Appl Spectrosc Rev 57: 531–579. https://doi.org/10.1080/05704928.2021.2020807 doi: 10.1080/05704928.2021.2020807
|
| [5] |
Seesaard T, Kamjornkittikoon K, Wongchoosuk C (2024) A comprehensive review of advancements in sensors for air pollution applications. Sci Total Environ 175696. https://doi.org/10.1016/j.scitotenv.2024.175696 doi: 10.1016/j.scitotenv.2024.175696
|
| [6] |
Jin H, Kong F, Li X, et al. (2024) Artificial intelligence in microplastic detection and pollution control. Environ Res 119812. https://doi.org/10.1016/j.envres.2024.119812 doi: 10.1016/j.envres.2024.119812
|
| [7] |
Singh D, Dahiya M, Kumar R, et al. (2021) Sensors and systems for air quality assessment, monitoring, and management: A review. J Environ Manag 289: 112510. https://doi.org/10.1016/j.jenvman.2021.112510 doi: 10.1016/j.jenvman.2021.112510
|
| [8] |
Malla S, Sahu PK, Patnaik S, et al. (2023) IoT-enabled smart anti-smog towers: A novel approach to urban air pollution control. Ingén Syst Inf 28. https://doi.org/10.18280/isi.280605 doi: 10.18280/isi.280605
|
| [9] |
Natrayan PC, LBT JRRG, Geetha BT, et al. (2022) IoT-enabled environmental toxicology for air pollution monitoring using AI techniques. Environ Res 205: 112574. https://doi.org/10.1016/j.envres.2021.112574 doi: 10.1016/j.envres.2021.112574
|
| [10] |
Tomson M, Kumar P, Barwise Y, et al. (2021) Green infrastructure for air quality improvement in street canyons. Environ Int 146: 106288. https://doi.org/10.1016/j.envint.2020.106288 doi: 10.1016/j.envint.2020.106288
|
| [11] |
Harrison RM, Van Vu T, Jafar H, et al. (2021) More mileage in reducing urban air pollution from road traffic. Environ Int 149: 106329. https://doi.org/10.1016/j.envint.2020.106329 doi: 10.1016/j.envint.2020.106329
|
| [12] |
Saini J, Dutta M, Marques G (2021) Sensors for indoor air quality monitoring and assessment through the Internet of Things: A systematic review. Environ Monit Assess 193: 66. https://doi.org/10.1007/s10661-020-08781-6 doi: 10.1007/s10661-020-08781-6
|
| [13] |
Subramaniam S, Raju N, Ganesan A, et al. (2022) Artificial intelligence technologies for forecasting air pollution and human health: A narrative review. Sustainability 14: 9951. https://doi.org/10.3390/su14169951 doi: 10.3390/su14169951
|
| [14] |
Krupnova TG, Rakova OV, Bondarenko KA, et al. (2022) Environmental justice and the use of artificial intelligence in urban air pollution monitoring. Big Data Cogn Comput 6: 75. https://doi.org/10.3390/bdcc6030075 doi: 10.3390/bdcc6030075
|
| [15] |
Rahardja U, Aini Q, Manongga D, et al. (2023) Implementation of TensorFlow in air quality monitoring based on artificial intelligence. Int J Artif Intell Res 6. https://doi.org/10.29099/ijair.v6i1.430 doi: 10.29099/ijair.v6i1.430
|
| [16] |
Taheri S, Razban A (2021) Learning-based CO₂ concentration prediction: Application to indoor air quality control using demand-controlled ventilation. Build Environ 205: 108164. https://doi.org/10.1016/j.buildenv.2021.108164 doi: 10.1016/j.buildenv.2021.108164
|
| [17] |
Kaginalkar A, Kumar S, Gargava P, et al. (2021) Review of urban computing in air quality management as a smart city service: An integrated IoT, AI, and cloud technology perspective. Urban Clim 39: 100972. https://doi.org/10.1016/j.uclim.2021.100972 doi: 10.1016/j.uclim.2021.100972
|
| [18] |
Kalajdjieski J, Trivodaliev K, Mirceva G, et al. (2023) A complete air pollution monitoring and prediction framework. IEEE Access 11: 88730–88744. https://doi.org/10.1109/ACCESS.2023.3251346 doi: 10.1109/ACCESS.2023.3251346
|
| [19] |
Ramadan MN, Ali MA, Khoo SY, et al. (2024) Real-time IoT-powered AI system for monitoring and forecasting air pollution in an industrial environment. Ecotoxicol Environ Saf 283: 116856. https://doi.org/10.1016/j.ecoenv.2024.116856 doi: 10.1016/j.ecoenv.2024.116856
|
| [20] | Babak VP, Babak SV, Eremenko VS, et al. (2021) Monitoring the air pollution with UAVs. In: Models and Measures in Measurements and Monitoring, Springer. 191–225. https://doi.org/10.1007/978-3-030-70783-5_7 |
| [21] |
Han Y, Lam JC, Li VO, et al. (2021) A Bayesian LSTM model to evaluate the effects of air pollution control regulations in Beijing, China. Environ Sci Policy 115: 26–34. https://doi.org/10.1016/j.envsci.2020.10.004 doi: 10.1016/j.envsci.2020.10.004
|
| [22] | Kalaivani G, Mayilvahanan P (2021) Air quality prediction and monitoring using machine learning algorithm-based IoT sensor: A researcher's perspective. In: 2021 6th Int Conf Commun Electron Syst (ICCES), IEEE. 1–9. https://doi.org/10.1109/ICCES51350.2021.9489153 |
| [23] | Jiyal S, Saini RK (2020) Prediction and monitoring of air pollution using the Internet of Things (IoT). In: 2020 6th Int Conf Parallel Distrib Grid Comput (PDGC), IEEE. 57–60. https://doi.org/10.1109/PDGC50313.2020.9315831 |
| [24] | Karthikeyan S, Moses LM, Perarasi T (2022) Machine learning-based air pollution monitoring and predicting causes for pollution. In: IOP Conf Ser Earth Environ Sci 1125: 012020. https://doi.org/10.1088/1755-1315/1125/1/012020 |
| [25] |
Fu L, Li J, Chen Y (2023) An innovative decision-making method for air quality monitoring based on big data-assisted artificial intelligence technique. J Innov Knowl 8: 100294. https://doi.org/10.1016/j.jik.2022.100294 doi: 10.1016/j.jik.2022.100294
|
Figures(5) / Tables(4)
Xiaobo Li, Xinggang Ye, Meirong Qian. An embedded machine learning system method for air pollution monitoring and control[J]. AIMS Environmental Science, 2025, 12(4): 576-593. doi: 10.3934/environsci.2025026
DownLoad: