Window state or action modeling? An explainable AI approach in offices

Farzan Banihashemi, Manuel Weber, Bing Dong, Salvatore Carlucci, Roland Reitberger, Werner Lang

Research output: Contribution to journalArticlepeer-review

1 Scopus citations


Window operation significantly impacts energy use and indoor environmental quality in buildings. Individuals behave differently, making it difficult for models trained on a specific dataset to encompass the entire spectrum of these actions. A generalizable model is essential to predict the behavior of diverse occupants in office spaces. To address this need, this paper presents a systematic approach that captures this diversity, thereby contributing to developing a model towards generalizability. The approach involves state and action modeling through a Random Forest algorithm on the ASHRAE Global Occupant Behavior Database. The data pre-processing, hyperparameter tuning, and evaluation are deeply described and applied to window action and state datasets. Our results demonstrated that including metadata in a state model and applying a G-Mean threshold moving technique can result in an F1-score of 0.74. This score slightly outperformed the state room-wise model, which was trained only on its own dataset and achieved an F1-score of 0.73. However, both models had similar accuracies of 77%. The action model did not fare as well as the state models, with an F1-score and accuracy score of just 0.42 and 49%, respectively. In contrast, the action model showed more explainable results for domain experts than state models.

Original languageEnglish (US)
Article number113546
JournalEnergy and Buildings
StatePublished - Nov 1 2023


  • Bayesian optimization
  • Explainable AI
  • Machine learning
  • Occupant behavior
  • Window opening

ASJC Scopus subject areas

  • Civil and Structural Engineering
  • Building and Construction
  • Mechanical Engineering
  • Electrical and Electronic Engineering


Dive into the research topics of 'Window state or action modeling? An explainable AI approach in offices'. Together they form a unique fingerprint.

Cite this