Indoor thermal comfort immensely impacts the health and performance of occupants. Therefore, researchers and engineers have proposed numerous computational models to estimate thermal comfort (TC). Given the impetus toward energy efficiency, the current focus is on data-driven TC prediction solutions that leverage state-of-the-art machine learning (ML) algorithms. However, an indoor occupant's perception of indoor thermal comfort (TC) is subjective and multi-dimensional. Different aspects of TC are represented by various standard metrics/scales viz., thermal sensation (TSV), thermal comfort (TCV), and thermal preference (TPV). The current ML-based TC prediction solutions adopt the Single-task Learning approach, i.e., one prediction model per metric. Consequently, solutions often focus on only one TC metric. Moreover, when several metrics are considered, multiple TC models for a single indoor space lead to conflicting predictions, making real-world deployment infeasible. This work addresses these problems. With the vision toward energy conservation and real-world application, naturally ventilated primary school classrooms are considered. First, month-long field experiments are conducted in 5 schools and 14 classrooms, including 512 unique student participants. Further, "DeepComfort," a Multi-task Learning inspired deep-learning model is proposed. DeepComfort predicts multiple TC output metrics viz., TSV, TPV, and TCV, simultaneously, through a single model. It demonstrates high F1-scores, Accuracy (>90%), and generalization capability when validated on the ASHRAE-II database and the dataset created in this study. DeepComfort is also shown to outperform 6 popular metric-specific single-task machine learning algorithms. To the best of our knowledge, this work is the first application of Multi-task Learning to thermal comfort prediction in classrooms.

本研究针对能源效率和实际应用的目标，在自然通风的小学教室中进行了为期一个月的实地实验，并提出了一种名为 DeepComfort 的多任务深度学习模型，可同时预测室内热舒适度（包括热感觉、热舒适度和热偏好）多个指标的输出，该模型证明了高的 F1 分数、准确度（>90%）和泛化能力，在ASHRAE-II数据库和本研究所创建的数据集上进行了验证。DeepComfort也显示出优于6种常见的单任务机器学习算法的性能。据我们所知，这项工作是将多任务学习应用于教室热舒适度预测的首次尝试。

多任务学习在同时预测热舒适度、感受和偏好方面的应用