FARKLI ÖZELLİK SEÇİMİ ALGORİTMALARI KULLANILARAK ISIL KONFOR PARAMETRELERİNİN KARŞILAŞTIRILMASI

Year 2025, Volume: 33 Issue: 3, 1964 - 1974, 19.12.2025

Resul Özlük , Türkan Göksal Özbalta

https://doi.org/10.31796/ogummf.1717391

Abstract

Bu çalışma, bir eğitim binasına ait amfi mekânında kullanıcı ısıl konforunu etkileyen çevresel parametreleri incelemek ve bu parametrelerin etkilerini farklı özellik seçimi algoritmalarıyla karşılaştırmayı amaçlamaktadır. Isıl konfor göstergelerinden PPD ve onu etkileyen çevresel parametreler, Testo 480 cihazının ölçümleriyle hesaplanmıştır. Öznel veriler, kullanıcıların ısıl kabul edilebilirlik ve ısıl konfor algısını ölçen anketlerle elde edilmiştir. Öğrencilerin ısıl konforunu etkileyen çevresel parametrelerin etki sırasının karşılaştırılmasında Random Forest Regressor, SHAP ve Correlation Attribute Eval algoritmaları kullanılmıştır. Sonuçlar, yüzey sıcaklığı ve iç ortam sıcaklığının kullanıcı konforu üzerinde en etkili parametreler olduğunu göstermiştir. SHAP ve Correlation Attribute Eval algoritmalarında yüzey sıcaklığı, Random Forest Regressor algoritmasında ise iç ortam sıcaklığı en etkili parametre olarak belirlenmiştir. Ayrıca anket sonuçları ile karşılaştırıldığında kullanıcı konforu üzerinde en az etkili çevresel parametrenin Correlation Attribute Eval algoritması ile aynı sonucu verdiği görülmüştür. Bu bulgular, kullanıcı konforunu etkileyen faktörlerin daha iyi yorumlanmasına ve benzer mekanların ısıl konfor açısından optimize edilmesine yönelik önemli sonuçlar sağlamaktadır.

Keywords

Isıl konfor , Yapay zeka algoritmaları , Eğitim binası , Çevresel parametreler , Özellik seçimi algoritmaları

COMPARISON OF THERMAL COMFORT PARAMETERS USING DIFFERENT FEATURE SELECTION ALGORITHMS

Abstract

This study aims to examine the environmental parameters affecting user thermal comfort in an amphitheater belonging to an educational building and to compare the effects of these parameters using different feature selection algorithms. Thermal comfort indicators PPD and environmental parameters were calculated using measurements from the Testo 480 device. Subjective data were obtained through surveys measuring users' thermal acceptability and thermal comfort perception. The RandomForestRegressor, SHAP, and CorrelationAttributeEval algorithms were used to compare the order of influence of environmental parameters affecting students' thermal comfort. The results showed that surface temperature and indoor air temperature are the most influential parameters on user comfort. In the SHAP and CorrelationAttributeEval algorithms, surface temperature was identified as the most influential parameter, while in the RandomForestRegressor algorithm, indoor temperature was identified as the most significant parameter. Additionally, when compared with survey results, the environmental parameter with the least effect on user comfort was found to yield the same result as the CorrelationAttributeEval algorithm. These findings provide important insights into better interpreting the factors affecting user comfort and optimizing thermal comfort in similar spaces.

Keywords

Thermal comfort , AI algorithms , Educational building , Environmental Parameters , Feature selection algorithms

References

• Alsahaf, A., Petkov, N., Shenoy, V., & Azzopardi, G. (2022). A framework for feature selection through boosting. Expert Systems with Applications, 187. https://doi.org/10.1016/j.eswa.2021.115895
• ANSI/ASHRAE Standard 55-2017. (2017). Thermal Environmental Conditions for Human Occupancy. Available at: www.ashrae.org/technology
• Aparicio-Ruiz, P., Barbadilla-Martín, E., Guadix, J., & Muñuzuri, J. (2021). A field study on adaptive thermal comfort in Spanish primary classrooms during summer season. Building and Environment, 203. https://doi.org/10.1016/j.buildenv.2021.108089
• Bai, Y., Dong, Z., & Liu, L. (2025). Hybrid feature selection-based machine learning methods for thermal preference prediction in diverse seasons
• and building environments. Building and Environment, 269. https://doi.org/10.1016/j.buildenv.2024.112450
• Caner, I., & Ilten, N. (2020). Evaluation of occupants’ thermal perception in a university hospital in Turkey. Proceedings of the Institution of Civil Engineers: Engineering Sustainability, 173(8), 414–428. https://doi.org/10.1680/jensu.19.00059
• CEN, E. 15251:2007. (2007). Indoor Environmental Input Parameters for Design and Assessment of Energy Performance of Buildings Addressing Indoor Air Quality, Thermal Environment, Lighting and Acoustics.
• Colgan, S., Quille, K., Mchugh, S., & Vasic, J. (2019). Predicting Student Success. Early for a VTOS Student. Paper presented at the International Conference on Engaging Pedagogy (ICEP), University of Limerick, Ireland.
• Cui, X., Lee, M., Koo, C., & Hong, T. (2024). Energy consumption prediction and household feature analysis for different residential building types using machine learning and SHAP: Toward energy-efficient buildings. Energy and Buildings, 309. https://doi.org/10.1016/j.enbuild.2024.113997
• De Giuli, V., Da Pos, O., & De Carli, M. (2012). Indoor environmental quality and pupil perception in Italian primary schools. Building and Environment, 56, 335–345. https://doi.org/10.1016/j.buildenv.2012.03.024
• Fanger, P. O. (1970). Thermal Comfort: Analysis and Applications in Environmental Engineering. Danish Technical Press.
• Gao, Y., Fu, Q., Chen, J., & Liu, K. (2025). Deep transfer learning-based hybrid modelling method for individual thermal comfort prediction. Indoor and Built Environment. https://doi.org/10.1177/1420326X251317447
• Heracleous, C., & Michael, A. (2020). Thermal comfort models and perception of users in free-running school buildings of East-Mediterranean region. Energy and Buildings, 215. https://doi.org/10.1016/j.enbuild.2020.109912
• Huang, X., Kroening, D., Ruan, W., Sharp, J., Sun, Y., Thamo, E., Wu, M. and Yi, X. (2020). A survey of safety and trustworthiness of deep neural networks: Verification, testing, adversarial attack and defence, and interpretability. In Computer Science Review, 37. https://doi.org/10.1016/j.cosrev.2020.100270
• Katafygiotou, M. C., & Serghides, D. K. (2014). Thermal comfort of a typical secondary school building in Cyprus. Sustainable Cities and Society, 13, 303–312. https://doi.org/10.1016/j.scs.2014.03.004
• Li, Q., Zhang, L., Zhang, L., & Wu, X. (2021). Optimizing energy efficiency and thermal comfort in building green retrofit. Energy, 237. https://doi.org/10.1016/j.energy.2021.121509
• Liang, H. H., Lin, T. P., & Hwang, R. L. (2012). Linking occupants’ thermal perception and building thermal performance in naturally ventilated school buildings. Applied Energy, 94, 355–363. https://doi.org/10.1016/j.apenergy.2012.02.004
• Liu, Y., Li, X., Sun, C., Dong, Q., Yin, Q., & Yan, B. (2025). An indoor thermal comfort model for group thermal comfort prediction based on K-means++ algorithm. Energy and Buildings, 327. https://doi.org/10.1016/j.enbuild.2024.115000
• Meddage, P., Ekanayake, I., Perera, U. S., Azamathulla, H. M., Said, M. A. M., & Rathnayake, U. (2022). Interpretation of Machine-Learning-Based (Black-box) Wind Pressure Predictions for Low-Rise Gable-Roofed Buildings Using Shapley Additive Explanations (SHAP). Buildings, 12(6). https://doi.org/10.3390/buildings12060734
• Medved, S., Domjan, S., & Arkar, C. (2019). Springer Tracts in Civil Engineering Sustainable Technologies for Nearly Zero Energy Buildings Design and Evaluation Methods. Springer Nature Switzerland AG. https://doi.org/https://doi.org/10.1007/978-3-030-02822-0
• Morgan, G. A., Leech, N. L., Gloeckner, G. W., & Barrett, K. C. (2004). SPSS for Introductory Statistics (Second edition). Psychology Press. https://doi.org/10.4324/9781410610539
• Olesen, B. W., & Parsons, K. C. (2002). Introduction to thermal comfort standards and to the proposed new version of EN ISO 7730. Energy and Buildings, 34(6), 537–548. https://doi.org/10.1016/S0378-7788(02)00004-X
• Park, K. Y., & Woo, D. O. (2023). PMV Dimension Reduction Utilizing Feature Selection Method: Comparison Study on Machine Learning Models. Energies, 16(5). https://doi.org/10.3390/en16052419
• Rahmanparast, A., Milani, M., Camci, M., Karakoyun, Y., Acikgoz, O., & Dalkilic, A. S. (2025). A comprehensive method for exploratory data analysis and preprocessing the ASHRAE database for machine learning. Applied Thermal Engineering, 273. https://doi.org/10.1016/j.applthermaleng.2025.126556
• Smith, P. F., Ganesh, S., & Liu, P. (2013). A comparison of random forest regression and multiple linear regression for prediction in neuroscience. Journal of Neuroscience Methods, 220(1), 85–91. https://doi.org/10.1016/j.jneumeth.2013.08.024
• Szokolay, S. V. (2004). Introduction to architectural science the basis of sustainable design. Architectural Press.
• Wang, M., Li, Y., Yuan, H., Zhou, S., Wang, Y., Adnan Ikram, R. M., & Li, J. (2023). An XGBoost-SHAP approach to quantifying morphological impact on urban flooding susceptibility. Ecological Indicators, 156. https://doi.org/10.1016/j.ecolind.2023.111137
• Wang, Z., Wang, Y., Zeng, R., Srinivasan, R. S., & Ahrentzen, S. (2018). Random Forest based hourly building energy prediction. Energy and Buildings, 171,11–25. https://doi.org/10.1016/j.enbuild.2018.04.008
• Zeiler, W., & Boxem, G. (2009). Effects of thermal activated building systems in schools on thermal comfort in winter. Building and Environment, 44(11), 2308–2317. https://doi.org/10.1016/j.buildenv.2009.05.005