A personal comfort model is an approach to thermal comfort modeling, for thermal environmental design and control, that predicts an individual's thermal comfort response, instead of the average response of a large population. We developed personal thermal comfort models using lab grade wearable in normal daily activities. We collected physiological signals (e.g., skin temperature, heart rate) of 14 subjects (6 female and 8 male adults) and environmental parameters (e.g., air temperature, relative humidity) for 2-4 weeks (at least 20 hours per day). Then we trained 14 models for each subject with different machine-learning algorithms to predict their thermal preference. The results show that the median prediction power could be up to 24% /78% /0.79 (Cohen's kappa/accuracy/AUC) with all features considered. The median prediction power reaches 21% /71% /0.7 after 200 subjective votes. We explored the importance of different features on the prediction performance by considering all subjects in one dataset. When all features included for the entire dataset, personal comfort models can generate the highest performance of 35% /76% /0.80 by the most predictive algorithm. Personal comfort models display the highest prediction power when occupants' thermal sensations is outside thermal neutrality. Skin temperature measured at the ankle is more predictive than measured at the wrist. We suggest that Cohen's kappa or AUC should be employed to assess the performance of personal thermal comfort models for imbalanced datasets due to the capacity to exclude random success.

Ceiling fans may cool room occupants very efficiently, but the air speeds experienced in the occupied zone are inherently non-uniform. Designers should be aware of several generic flow patterns when positioning ceiling fans in a room. Key to these are the fan jet itself and lateral spreading near the floor. Adding workstation furniture redirects the jet's airflow laterally in a deeper spreading zone, making room air flows more complex but potentially increasing the cooling experienced by the occupants. This paper presents the first evaluation of the effects of tables and workstation partitions on a room's generic air flow and comfort profiles. In a test room with a ceiling fan, we moved five anemometers mounted in a "tree" at heights of 0.1, 0.6, 0.75, 1.1, and 1.7 m to sample a dense measurement grid of 7 rows and 6 columns. We tested five different table and partition configurations and compared them to the empty room base case. From the results we propose a simplified model of room airflow under ceiling fans, useful for positioning fans and workstation furniture. We also present comfort contours measured in two ways that have comfort standards implications. The measured data are publicly available on the internet. Keywords: Ceiling fan; air speed; furniture; comfort cooling; corrective power Highlights 1. We performed high resolution measurements of ceiling-fan-induced air flow in an empty room; 2. We compare this reference case to air flow profiles measured in the room with five different table and partition configurations. The data are included as publicly available supplementary material; 4. The initial ceiling fan flow in the room could be modeled as a free jet; 5. The subsequent room circulation, with and without tables and partitions, may be represented by an intuitive model for designers who are placing fans and furniture; 6. The extent of comfort cooling provided by the fan air flow can be represented by the metric 'corrective power'. Corrective power equates the cooling effect of the fan as an ambient temperature reduction, ºC. We present the corrective power distribution in the room in two ways--with and without the air speed at ankle level--to evaluate air speed cooling effect. This evaluation is significant for thermal comfort standards.

No abstract

No abstract