Dataset Open Access

OccuTherm: Occupant Thermal Comfort Inference using Body Shape Information

Jonathan Francis; Matias Quintana; Nadine von Frankenberg; Sirajum Munir; Mario Bergés

Project member(s)
Michael Frenak; Charles Shelton; Nicole Ho; Alexander Davis

OccuTherm: Occupant Thermal Comfort Inference using Body Shape Information

This repository contains the official data from a USDOE-funded project at Carnegie Mellon University and Bosch Research Pittsburgh. 

The primary goal of the project was to investigate the relationship between indoor commercial building occupant thermal comfort and various biometric and environmental predictors. We performed 77 individual comfort experiments, approved by our Institutional Review Board (IRB) and in satisfaction of participant consent guidelines. Our goal was to generate a dataset than enables comprehensive study of human thermal comfort preferences, in a commercial building environment, across a wide range of indoor environmental conditions. The data is comprised of the following feature groups: depth camera frames, biometrics sensor data, body shape information, subjective comfort data from the mobile device application, environmental sensor data from the commercial building HVAC system, and outdoor weather station data.

This is the official dataset release for the following conference paper:

Jonathan Francis*, Matias Quintana*, Nadine von Frankenberg, Sirajum Munir, and Mario Bergés. 2019. OccuTherm: Occupant Thermal Comfort Inference using Body Shape Information. In BuildSys '19: ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation, November 13–14, 2019, New York, NY. ACM, New York, NY, USA, 10 pages.

To use this dataset, first download all the files.

Next, issue the following commands on, e.g., Linux terminal:

>$ cd /path/to/dataset/files
>$ cat occutherm_dataset_v0-0-0.tar.gza* > archive.tar.gz
>$ tar -xvzf archive.tar.gz

Modeling and mobile application code are available in our project repository: https://github.com/jonfranc/occutherm

If you find the repository or the dataset useful, please cite our paper:

@inproceedings{francis_buildsys2019,
 author = {Francis, Jonathan and Quintana, Matias and von Frankenberg, Nadine and Munir, Sirajum and Berges, Mario},
 title = {OccuTherm: Occupant Thermal Comfort Inference using Body Shape Information},
 booktitle = {Proceedings of the 6th International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation},
 series = {BuildSys '19},
 year = {2019},
 isbn = {978-1-4503-7005-9/19/11},
 location = {New York, NY},
 numpages = {10},
 acmid = {3360858},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {Thermal Comfort, Human Studies, Machine Learning},
}

 

Files (99.6 GB)
Name Size
occutherm_dataset_v0-0-0.tar.gzaa
md5:a572d0288c775e3962109203707d55e9
32.2 GB Download
occutherm_dataset_v0-0-0.tar.gzab
md5:d097eac2935daa702497ee7195f92a07
32.2 GB Download
occutherm_dataset_v0-0-0.tar.gzac
md5:15e38d2da9a479a12a95e52bb1505dc4
32.2 GB Download
occutherm_dataset_v0-0-0.tar.gzad
md5:196517801917b09c6c4f7577bcef24ed
3.0 GB Download
164
101
views
downloads
All versions This version
Views 164164
Downloads 101101
Data volume 3.1 TB3.1 TB
Unique views 139139
Unique downloads 3939

Share

Cite as