English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Indoor thermal comfort immensely impacts the health and performance ofoccupants. Therefore, researchers and engineers have proposed numerouscomputational models to estimate thermal comfort (TC). Given the impetus towardenergy efficiency, the current focus is on data-driven TC prediction solutionsthat leverage state-of-the-art machine learning (ML) algorithms. However, anindoor occupant's perception of indoor thermal comfort (TC) is subjective andmulti-dimensional. Different aspects of TC are represented by various standardmetrics/scales viz., thermal sensation (TSV), thermal comfort (TCV), andthermal preference (TPV). The current ML-based TC prediction solutions adoptthe Single-task Learning approach, i.e., one prediction model per metric.Consequently, solutions often focus on only one TC metric. Moreover, whenseveral metrics are considered, multiple TC models for a single indoor spacelead to conflicting predictions, making real-world deployment infeasible. Thiswork addresses these problems. With the vision toward energy conservation andreal-world application, naturally ventilated primary school classrooms areconsidered. First, month-long field experiments are conducted in 5 schools and14 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-IIdatabase and the dataset created in this study. DeepComfort is also shown tooutperform 6 popular metric-specific single-task machine learning algorithms.To the best of our knowledge, this work is the first application of Multi-taskLearning to thermal comfort prediction in classrooms.

Multi-task Learning for Concurrent Prediction of Thermal Comfort, Sensation, and Preference