Humans-as-a-Sensor for Buildings — Intensive Longitudinal Indoor Comfort Models
Evaluating and optimising human comfort within the built environment is challenging due to the large number of physiological, psychological and environmental variables that affect occupant comfort preference. Human perception could be helpful to capture these disparate phenomena and interpreting the...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-10-01
|
Series: | Buildings |
Subjects: | |
Online Access: | https://www.mdpi.com/2075-5309/10/10/174 |
id |
doaj-5fb9027eb6cb473c8d898ac0f6b8ae8a |
---|---|
record_format |
Article |
spelling |
doaj-5fb9027eb6cb473c8d898ac0f6b8ae8a2020-11-25T04:02:42ZengMDPI AGBuildings2075-53092020-10-011017417410.3390/buildings10100174Humans-as-a-Sensor for Buildings — Intensive Longitudinal Indoor Comfort ModelsPrageeth Jayathissa0Matias Quintana1Mahmoud Abdelrahman2Clayton Miller3Building and Urban Data Science (BUDS) Lab, National University of Singapore (NUS), 4 Architecture Dr., Singapore 117566, SingaporeBuilding and Urban Data Science (BUDS) Lab, National University of Singapore (NUS), 4 Architecture Dr., Singapore 117566, SingaporeBuilding and Urban Data Science (BUDS) Lab, National University of Singapore (NUS), 4 Architecture Dr., Singapore 117566, SingaporeBuilding and Urban Data Science (BUDS) Lab, National University of Singapore (NUS), 4 Architecture Dr., Singapore 117566, SingaporeEvaluating and optimising human comfort within the built environment is challenging due to the large number of physiological, psychological and environmental variables that affect occupant comfort preference. Human perception could be helpful to capture these disparate phenomena and interpreting their impact; the challenge is collecting spatially and temporally diverse subjective feedback in a scalable way. This paper presents a methodology to collect intensive longitudinal subjective feedback of comfort-based preference using micro ecological momentary assessments on a smartwatch platform. An experiment with 30 occupants over two weeks produced 4378 field-based surveys for thermal, noise, and acoustic preference. The occupants and the spaces in which they left feedback were then clustered according to these preference tendencies. These groups were used to create different feature sets with combinations of environmental and physiological variables, for use in a multi-class classification task. These classification models were trained on a feature set that was developed from time-series attributes, environmental and near-body sensors, heart rate, and the historical preferences of both the individual and the comfort group assigned. The most accurate model had multi-class classification F1 micro scores of 64%, 80% and 86% for thermal, light, and noise preference, respectively. The discussion outlines how these models can enhance comfort preference prediction when supplementing data from installed sensors. The approach presented prompts reflection on how the building analysis community evaluates, controls, and designs indoor environments through balancing the measurement of variables with <i>occupant preferences</i> in an intensive longitudinal way.https://www.mdpi.com/2075-5309/10/10/174indoor environmental qualitythermal comfort modelspersonalised comfort modelmachine learningecological momentary assessmentoccupant behaviour |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Prageeth Jayathissa Matias Quintana Mahmoud Abdelrahman Clayton Miller |
spellingShingle |
Prageeth Jayathissa Matias Quintana Mahmoud Abdelrahman Clayton Miller Humans-as-a-Sensor for Buildings — Intensive Longitudinal Indoor Comfort Models Buildings indoor environmental quality thermal comfort models personalised comfort model machine learning ecological momentary assessment occupant behaviour |
author_facet |
Prageeth Jayathissa Matias Quintana Mahmoud Abdelrahman Clayton Miller |
author_sort |
Prageeth Jayathissa |
title |
Humans-as-a-Sensor for Buildings — Intensive Longitudinal Indoor Comfort Models |
title_short |
Humans-as-a-Sensor for Buildings — Intensive Longitudinal Indoor Comfort Models |
title_full |
Humans-as-a-Sensor for Buildings — Intensive Longitudinal Indoor Comfort Models |
title_fullStr |
Humans-as-a-Sensor for Buildings — Intensive Longitudinal Indoor Comfort Models |
title_full_unstemmed |
Humans-as-a-Sensor for Buildings — Intensive Longitudinal Indoor Comfort Models |
title_sort |
humans-as-a-sensor for buildings — intensive longitudinal indoor comfort models |
publisher |
MDPI AG |
series |
Buildings |
issn |
2075-5309 |
publishDate |
2020-10-01 |
description |
Evaluating and optimising human comfort within the built environment is challenging due to the large number of physiological, psychological and environmental variables that affect occupant comfort preference. Human perception could be helpful to capture these disparate phenomena and interpreting their impact; the challenge is collecting spatially and temporally diverse subjective feedback in a scalable way. This paper presents a methodology to collect intensive longitudinal subjective feedback of comfort-based preference using micro ecological momentary assessments on a smartwatch platform. An experiment with 30 occupants over two weeks produced 4378 field-based surveys for thermal, noise, and acoustic preference. The occupants and the spaces in which they left feedback were then clustered according to these preference tendencies. These groups were used to create different feature sets with combinations of environmental and physiological variables, for use in a multi-class classification task. These classification models were trained on a feature set that was developed from time-series attributes, environmental and near-body sensors, heart rate, and the historical preferences of both the individual and the comfort group assigned. The most accurate model had multi-class classification F1 micro scores of 64%, 80% and 86% for thermal, light, and noise preference, respectively. The discussion outlines how these models can enhance comfort preference prediction when supplementing data from installed sensors. The approach presented prompts reflection on how the building analysis community evaluates, controls, and designs indoor environments through balancing the measurement of variables with <i>occupant preferences</i> in an intensive longitudinal way. |
topic |
indoor environmental quality thermal comfort models personalised comfort model machine learning ecological momentary assessment occupant behaviour |
url |
https://www.mdpi.com/2075-5309/10/10/174 |
work_keys_str_mv |
AT prageethjayathissa humansasasensorforbuildingsintensivelongitudinalindoorcomfortmodels AT matiasquintana humansasasensorforbuildingsintensivelongitudinalindoorcomfortmodels AT mahmoudabdelrahman humansasasensorforbuildingsintensivelongitudinalindoorcomfortmodels AT claytonmiller humansasasensorforbuildingsintensivelongitudinalindoorcomfortmodels |
_version_ |
1724442524050784256 |