İç Ortam Hava Kalitesinin Tahmini için Makine Öğrenmesi Tabanlı Modellerin Karşılaştırılması

Nurullah Öztürk; Ramazan Aldemir

doi:10.31466/kfbd.1721495

TR EN

İç Ortam Hava Kalitesinin Tahmini için Makine Öğrenmesi Tabanlı Modellerin Karşılaştırılması

Abstract

Hava kirliliği, günümüzde çevre ve halk sağlığı açısından önemli bir tehdit oluşturmaktadır ve özellikle iç ortamlarda maruziyetin sürekli olması riskleri artırmaktadır. Bu nedenle, iç ortam hava kalitesinin güvenilir biçimde izlenmesi ve tahmin edilmesi büyük önem taşımaktadır. Bu çalışmada, iç ortam hava kirliliğine neden olan CO, NH3, NO2 ve PM2.5 kirleticilerinin tahmini amacıyla Karar Ağaçları, Rastgele Orman, Destek Vektör Makineleri, Doğrusal Regresyon, Yapay Sinir Ağları ve bu modellerin ağırlıklandırılmasıyla oluşturulan hibrit model karşılaştırmalı olarak değerlendirilmiştir. Çalışmada, Mendeley kütüphanesinde yer alan “Dataset of Indoor Air Pollutants using Low-Cost Sensor” veri seti kullanılmıştır. Veriler, kronolojik yapı korunarak %70 eğitim ve %30 test olacak şekilde ayrılmış; tüm modellerin hiperparametreleri yalnızca eğitim verisi üzerinde uygulanan 5-katlı çapraz doğrulama ve sistematik grid arama yöntemiyle optimize edilmiştir. Model performansları RMSE, MSE, MAE ve R^2 metrikleri ile değerlendirilmiş, yöntemler arasındaki farkların istatistiksel anlamlılığı Friedman ve Wilcoxon testleri ile analiz edilmiştir. Sonuçlar, CO değişkeni için hibrit modelin en dengeli ve başarılı yöntemi sunduğunu, NH3, NO2 ve özellikle PM2.5 değişkenlerinde ise tüm yöntemlerin test seti üzerinde sınırlı başarım sergilediğini göstermektedir. Bununla birlikte, hibrit modelin tüm kirleticiler için tekil modellere kıyasla daha tutarlı hata dağılımları ürettiği ve istatistiksel olarak anlamlı performans farkları sağladığı ortaya konmuştur.

Keywords

İç ortam hava kalitesi, Makine öğrenmesi, Hibrit model, Düşük maliyetli sensörler

Comparative Analysis of Machine Learning-Based Models for Indoor Air Quality Prediction

Abstract

This Air pollution presents a considerable challenge to both environmental preservation and public well-being, especially within indoor settings where prolonged exposure amplifies the associated hazards. Consequently, reliable monitoring and forecasting of indoor air quality are of great importance. In this study, Decision Trees, Random Forest, Support Vector Machines, Linear Regression, Artificial Neural Networks, and a hybrid model developed through the weighted integration of these methods, to predict indoor air pollutants: CO, NH3, NO2, and PM2.5. The experiments were performed utilising the "Dataset of Indoor Air Pollutants using Low-Cost Sensor," obtained from the Mendeley data repository.The dataset was chronologically divided into 70% to training and 30% to testing. Hyperparameter optimization of all models was conducted solely on the training data, employing 5-fold cross-validation and a systematic grid search. Model performance was assessed through RMSE, MSE, MAE, and R^2 metrics; furthermore, the statistical significance of performance disparities among the methodologies was examined via the Friedman and Wilcoxon tests. The findings suggest that the hybrid model demonstrates the most balanced and robust performance for the CO pollutant. Conversely, for NH3, NO2, and especially PM2.5, all methods displayed restricted predictive capabilities on the test set. Nevertheless, the hybrid model conducts more stable error distributions compared to individual models, and achieves statistically significant performance distinctions across all pollutants.

Keywords

Indoor air quality, Machine learning, Hybrid model, Low-Cost sensors

References

Adekoya, O. B., Olabode, J. K., Rafi, S. K. (2021). Renewable energy consumption, carbon emissions and human development: Empirical comparison of the trajectories of world regions. Renewable Energy, 179, 1836–1848. https://doi.org/10.1016/j.renene.2021.08.019
Amoatey, P., Omidvarborna, H., Baawain, M. S., Al-Mamun, A. (2018). Indoor air pollution and exposure assessment of the gulf cooperation council countries: A critical review. Environment international, 121, 491-506. https://doi.org/10.1016/j.envint.2018.09.043
Aram, S. A., Nketiah, E. A., Saalidong, B. M., Wang, H., Afitiri, A. R., Akoto, A. B., Lartey, P. O. (2024). Machine learning-based prediction of air quality index and air quality grade: A comparative analysis. International Journal of Environmental Science and Technology, 21(2), 1345–1360. https://doi.org/10.1007/s13762-023-05016-2
Bakó-Biró, Z., Clements-Croome, D. J., Kochhar, N., Awbi, H. B., Williams, M. J. (2012). Ventilation rates in schools and pupils’ performance. Building and Environment, 48, 215–223. https://doi.org/10.1016/j.buildenv.2011.08.018
Berkani, M. R. A., Chouchane, A., Himeur, Y., Ouamane, A., Amira, A. (2023). An intelligent edge-deployable indoor air quality monitoring and activity recognition approach. arXiv preprint arXiv:2311.03920. https://doi.org/10.48550/arXiv.2311.03920
Chaturvedi, P. (2024). Air Quality Prediction System Using Machine Learning Models. Water, Air, & Soil Pollution, 235(9), 578. https://doi.org/10.1007/s11270-024-07390-0
Chatzidiakou, L., Mumovic, D., Summerfield, A. J. (2012). What do we know about indoor air quality in school classrooms? A critical review of the literature. Intelligent Buildings International, 4(4), 228–259. https://doi.org/10.1080/17508975.2012.725530
Chicco, D., Warrens, M. J., Jurman, G. (2021). The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation. Peerj computer science, 7, e623. https://doi.org/10.7717/peerj-cs.623
Dong, J., Goodman, N., Rajagopalan, P. (2023). A review of artificial neural network models applied to predict indoor air quality in schools. International Journal of Environmental Research and Public Health, 20(15), 6441. https://doi.org/10.3390/ijerph20156441
Dun, M., Xu, Z., Chen, Y., Wu, L. (2020). Short-term air quality prediction based on fractional grey linear regression and support vector machine. Mathematical Problems in Engineering, 2020, Article ID 8914501. https://doi.org/10.1155/2020/8914501

El-Tanbouly, R., Hassan, Z., El-Messeiry, S. (2021). The role of indoor plants in air purification and human health in the context of COVID-19 pandemic: a proposal for a novel line of inquiry. Frontiers in Molecular Biosciences, 8, 709395. https://doi.org/10.3389/fmolb.2021.709395
Hahad, O., Lelieveld, J., Birklein, F., Lieb, K., Daiber, A., Münzel, T. (2020). Ambient air pollution increases the risk of cerebrovascular and neuropsychiatric disorders through induction of inflammation and oxidative stress. International journal of molecular sciences, 21(12), 4306. https://doi.org/10.3390/ijms21124306
Hodson, T. O. (2022). Root mean square error (RMSE) or mean absolute error (MAE): When to use them or not. Geoscientific Model Development Discussions, 2022, 1-10
Intergovernmental Panel on Climate Change (IPCC). (2014). Climate change 2014: Synthesis report. In Contribution of Working Groups I, II and III to the Fifth Assessment Report of the Intergovernmental Panel on Climate Change (p. 151). IPCC. https://www.ipcc.ch/report/ar5/syr/
Kamiński, B., Jakubczyk, M., Szufel, P. (2018). A framework for sensitivity analysis of decision trees. Central European Journal of Operations Research, 26(1), 135–159. https://doi.org/10.1007/s10100-017-0479-6
Lazaridis, M. (2011). First principles of meteorology and air pollution. Springer. https://doi.org/10.1007/978-94-007-0162-5_2
Liu, H., Li, J., Sun, Y., Wang, Y., Zhao, H. (2020). Estimation method of carbon emissions in the embodied phase of low carbon building. Advances in Civil Engineering, 2020, Article ID 8846917. https://doi.org/10.1155/2020/8853536
Maleki, H., Sorooshian, A., Goudarzi, G., Baboli, Z., Tahmasebi Birgani, Y., Rahmati, M. (2019). Air pollution prediction by using an artificial neural network model. Clean Technologies and Environmental Policy, 21, 1341–1352. https://doi.org/10.1007/s10098-019-01709-w
Mata, T. M., Martins, A. A., Calheiros, C. S., Villanueva, F., Alonso-Cuevilla, N. P., Gabriel, M. F., Silva, G. V. (2022). Indoor air quality: a review of cleaning technologies. Environments, 9(9), 118. https://doi.org/10.3390/environments9090118
Megahed, N. A., Ghoneim, E. M. (2021). Indoor Air Quality: Rethinking rules of building design strategies in post-pandemic architecture. Environmental research, 193, 110471. https://doi.org/10.1016/j.envres.2020.110471
Nanfack, G., Temple, P., Frénay, B. (2023). Learning customised decision trees for domain-knowledge constraints. Pattern Recognition, 142, 109610. https://doi.org/10.1016/j.patcog.2023.109610
Othman, H., Azari, R., Guimarães, T. (2024). Low-cost IoT-based indoor air quality monitoring. Technology | Architecture + Design, 8(2), 250–270. https://doi.org/10.1080/24751448.2024.2405403
Peters, A., Dockery, D. W., Muller, J. E. (2019). Air pollution and cardiovascular disease: A scientific statement from the American Heart Association. Circulation, 116(1), 123–133. https://doi.org/10.1161/CIRCULATIONAHA.116.024620
Pietraru, R. N., Olteanu, A., Adochiei, I. R., Adochiei, F. C. (2024). Reengineering indoor air quality monitoring systems to improve end-user experience. Sensors, 24(8), 2659. https://doi.org/10.3390/s24082659
Rajagopalan, S., Al-Kindi, S. G., Brook, R. D. (2018). Air pollution and cardiovascular disease: JACC state-of-the-art review. Journal of the American College of Cardiology, 72(17), 2054-2070. https://doi.org/10.1016/j.jacc.2018.07.099
Saravanan, D., Kumar, K. S. (2023). Improving air pollution detection accuracy and quality monitoring based on bidirectional RNN and the Internet of Things. Materials Today: Proceedings, 81, 791-796. https://doi.org/10.1016/j.matpr.2021.04.239
Serefoglu Cabuk, K., Cengiz, S. K., Guler, M. G., Topcu, H., Cetin Efe, A., Ulas, M. G., Poslu Karademir, F. (2024). Chasing the objective upper eyelid symmetry formula; R2, RMSE, POC, MAE, and MSE. International Ophthalmology, 44(1), 303. https://doi.org/10.1007/s10792-024-03157-y
Sonawani, S., Patil, K. (2022). Dataset of indoor air pollutants using low-cost sensors. Mendeley Data, V1. https://doi.org/10.17632/2r232jpfb2.1
Srivastava, R. K., Sarkar, S., Beig, G. (2014). Correlation of various gaseous pollutants with meteorological parameter (temperature, relative humidity and rainfall). Global Journal of Science Frontier Research, 14(6), 56–65. https://journalofscience.org/index.php/GJSFR/article/view/1452
World Health Organization. (2018). Air quality and health. https://www.who.int/publications/i/item/9789241565585 (Erişim tarihi: 10 Şubat 2025)
Yadav, V., Yadav, A. K., Singh, V., Singh, T. (2024). Artificial neural network an innovative approach in air pollutant prediction for environmental applications: A review. Results in Engineering, 102305 https://doi.org/10.1016/j.rineng.2024.102305
Yaman, C. (2024). A review on the process of greenhouse gas inventory preparation and proposed mitigation measures for reducing carbon footprint. Gases, 4(1), 18-40. https://doi.org/10.3390/gases4010002
Zhang, B., Geng, Z., Zhang, H., Pan, J. (2022). Densely connected convolutional networks with attention long short-term memory for estimating PM2.5 values from images. Journal of Cleaner Production, 333, 130101. https://doi.org/10.1016/j.jclepro.2021.130101

Details

Primary Language

Turkish

Subjects

Computer Software

Journal Section

Research Article

Authors

Nurullah Öztürk ^*
0000-0001-7766-6757
Türkiye

Ramazan Aldemir
0000-0002-4279-3649
Türkiye

Publication Date

May 12, 2026

Submission Date

June 17, 2025

Acceptance Date

February 6, 2026

Published in Issue

Year 2026 Volume: 16 Number: 2

DOI

https://doi.org/10.31466/kfbd.1721495

IZ

https://izlik.org/JA63UJ28JY

APA

Öztürk, N., & Aldemir, R. (2026). İç Ortam Hava Kalitesinin Tahmini için Makine Öğrenmesi Tabanlı Modellerin Karşılaştırılması. Karadeniz Fen Bilimleri Dergisi, 16(2), 689-714. https://doi.org/10.31466/kfbd.1721495

AMA

1.Öztürk N, Aldemir R. İç Ortam Hava Kalitesinin Tahmini için Makine Öğrenmesi Tabanlı Modellerin Karşılaştırılması. KFBD. 2026;16(2):689-714. doi:10.31466/kfbd.1721495

Chicago

Öztürk, Nurullah, and Ramazan Aldemir. 2026. “İç Ortam Hava Kalitesinin Tahmini Için Makine Öğrenmesi Tabanlı Modellerin Karşılaştırılması”. Karadeniz Fen Bilimleri Dergisi 16 (2): 689-714. https://doi.org/10.31466/kfbd.1721495.

EndNote

Öztürk N, Aldemir R (May 1, 2026) İç Ortam Hava Kalitesinin Tahmini için Makine Öğrenmesi Tabanlı Modellerin Karşılaştırılması. Karadeniz Fen Bilimleri Dergisi 16 2 689–714.

IEEE

[1]N. Öztürk and R. Aldemir, “İç Ortam Hava Kalitesinin Tahmini için Makine Öğrenmesi Tabanlı Modellerin Karşılaştırılması”, KFBD, vol. 16, no. 2, pp. 689–714, May 2026, doi: 10.31466/kfbd.1721495.

ISNAD

Öztürk, Nurullah - Aldemir, Ramazan. “İç Ortam Hava Kalitesinin Tahmini Için Makine Öğrenmesi Tabanlı Modellerin Karşılaştırılması”. Karadeniz Fen Bilimleri Dergisi 16/2 (May 1, 2026): 689-714. https://doi.org/10.31466/kfbd.1721495.

JAMA

1.Öztürk N, Aldemir R. İç Ortam Hava Kalitesinin Tahmini için Makine Öğrenmesi Tabanlı Modellerin Karşılaştırılması. KFBD. 2026;16:689–714.

MLA

Öztürk, Nurullah, and Ramazan Aldemir. “İç Ortam Hava Kalitesinin Tahmini Için Makine Öğrenmesi Tabanlı Modellerin Karşılaştırılması”. Karadeniz Fen Bilimleri Dergisi, vol. 16, no. 2, May 2026, pp. 689-14, doi:10.31466/kfbd.1721495.

Vancouver

1.Nurullah Öztürk, Ramazan Aldemir. İç Ortam Hava Kalitesinin Tahmini için Makine Öğrenmesi Tabanlı Modellerin Karşılaştırılması. KFBD. 2026 May 1;16(2):689-714. doi:10.31466/kfbd.1721495

The published articles in The Black Sea Journal of Sciences are licensed under Creative Commons Attribution-NonCommercial 4.0 International

İç Ortam Hava Kalitesinin Tahmini için Makine Öğrenmesi Tabanlı Modellerin Karşılaştırılması

Abstract

Keywords

Comparative Analysis of Machine Learning-Based Models for Indoor Air Quality Prediction

Abstract

Keywords

References

Details

Primary Language

Subjects

Journal Section

Authors

Publication Date

Submission Date

Acceptance Date

Published in Issue

DOI

IZ

Cite