# Balancing thermal comfort datasets: We GAN, but should we?

arXiv: https://arxiv.org/abs/2009.13154 · HTML: https://mlsanity.com/paper/2009.13154/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Sep 2020.

## Built on by (most cited first, 7 of 7)

- [GANmapper: geographical data translation](https://mlsanity.com/paper/2108.04232/) (2021)
- [Creating synthetic energy meter data using conditional diffusion and building metadata](https://mlsanity.com/paper/2404.00525/) (2024)
- [Personal thermal comfort models using digital twins: Preference prediction with BIM-extracted spatial-temporal proximity data from Build2Vec](https://mlsanity.com/paper/2111.00199/) (2021)
- [Cohort comfort models -- Using occupants' similarity to predict personal thermal preference with less data](https://mlsanity.com/paper/2208.03078/) (2022)
- [Conditional Synthetic Data Generation for Personal Thermal Comfort Models](https://mlsanity.com/paper/2203.05242/) (2022)
- [Machine Learning for Smart and Energy-Efficient Buildings](https://mlsanity.com/paper/2211.14889/) (2022)
- [Explaining AI Decisions: Towards Achieving Human-Centered Explainability in Smart Home Environments](https://mlsanity.com/paper/2404.16074/) (2024)

## Abstract (arXiv)

Thermal comfort assessment for the built environment has become more available to analysts and researchers due to the proliferation of sensors and subjective feedback methods. These data can be used for modeling comfort behavior to support design and operations towards energy efficiency and well-being. By nature, occupant subjective feedback is imbalanced as indoor conditions are designed for comfort, and responses indicating otherwise are less common. This situation creates a scenario for the machine learning workflow where class balancing as a pre-processing step might be valuable for developing predictive thermal comfort classification models with high-performance. This paper investigates the various thermal comfort dataset class balancing techniques from the literature and proposes a modified conditional Generative Adversarial Network (GAN), textttcomfortGAN, to address this imbalance scenario. These approaches are applied to three publicly available datasets, ranging from 30 and 67 participants to a global collection of thermal comfort datasets, with 1,474; 2,067; and 66,397 data points, respectively. This work finds that a classification model trained on a balanced dataset, comprised of real and generated samples from textttcomfortGAN, has higher performance (increase between 4% and 17% in classification accuracy) than other augmentation methods tested. However, when classes representing discomfort are merged and reduced to three, better imbalanced performance is expected, and the additional increase in performance by textttcomfortGAN shrinks to 1-2%. These results illustrate that class balancing for thermal comfort modeling is beneficial using advanced techniques such as GANs, but its value is diminished in certain scenarios. A discussion is provided to assist potential users in determining which scenarios this process is useful and which method works best.