EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Improved Thermal Comfort Model Leveraging Conditional Tabular GAN Focusing on Feature Selection

Md. Shajalal, Milad Bohlouli, Hari Prasanna Das, Alexander Boden, Gunnar Stevens

IEEE Access · 2024 · 12 · 30039-30053

DOI: 10.1109/access.2024.3366453 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Access, 2024. Verfasst von Md. Shajalal und 4 weiteren Autor:innen. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: European Union (EU) Horizon 2020 Marie Sklodowska-Curie International Training Network GECKO.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The indoor thermal comfort in both homes and workplaces significantly influences the health and productivity of inhabitants. The heating system, controlled by Artificial Intelligence (AI), can automatically calibrate the indoor thermal condition by analyzing various physiological and environmental variables. To ensure a comfortable indoor environment, smart home systems can adjust parameters related to thermal comfort based on accurate predictions of inhabitants’ preferences. Modeling personal thermal comfort preferences poses two significant challenges: the inadequacy of data and its high dimensionality. An adequate amount of data is a prerequisite for training efficient machine learning (ML) models. Additionally, high-dimensional data tends to contain multiple irrelevant and noisy features, which might hinder ML models’ performance. To address these challenges, we propose a framework for predicting personal thermal comfort preferences, combining the conditional tabular generative adversarial network (CTGAN) with multiple feature selection techniques. We first address the data inadequacy challenge by applying CTGAN to generate synthetic data samples, incorporating challenges associated with multimodal distributions and categorical features. Then, multiple feature selection techniques are employed to identify the best possible sets of features. Experimental results based on a wide range of settings on a standard dataset demonstrated state-of-the-art performance in predicting personal thermal comfort preferences. The results also indicated that ML models trained on synthetic data achieved significantly better performance than models trained on real data. Overall, our method, combining CTGAN and feature selection techniques, outperformed existing known related work in thermal comfort prediction in terms of multiple evaluation metrics, including area under the curve (AUC), Cohen’s Kappa, and accuracy. Additionally, we presented a global, model-agnostic explanation of the thermal preference prediction system, providing an avenue for thermal comfort experiment designers to consciously select the data to be collected.

Förderung

  • European Union (EU) Horizon 2020 Marie Sklodowska-Curie International Training Network GECKO

Zitieren

APA

Shajalal, M., Bohlouli, M., Das, H. P., Boden, A., & Stevens, G. (2024). Improved Thermal Comfort Model Leveraging Conditional Tabular GAN Focusing on Feature Selection. IEEE Access, 12, 30039-30053. https://doi.org/10.1109/access.2024.3366453

Vancouver

Shajalal M, Bohlouli M, Das HP, Boden A, Stevens G. Improved Thermal Comfort Model Leveraging Conditional Tabular GAN Focusing on Feature Selection. IEEE Access. 2024;12:30039-30053. doi:10.1109/access.2024.3366453

BibTeX
@article{Shajalal2024,
  author = {Shajalal, Md. and Bohlouli, Milad and Das, Hari Prasanna and Boden, Alexander and Stevens, Gunnar},
  title = {Improved Thermal Comfort Model Leveraging Conditional Tabular GAN Focusing on Feature Selection},
  journal = {IEEE Access},
  year = {2024},
  volume = {12},
  pages = {30039--30053},
  doi = {10.1109/access.2024.3366453}
}
Kostenlos starten →