Humans-as-a-sensor for buildings: Intensive longitudinal indoor comfort models
Prageeth Jayathissa, Matias Quintana, Mahmoud Abdelrahman, and Clayton Miller ∗
Building and Urban Data Science (BUDS) Lab, National University of Singapore (NUS), Singapore
∗Corresponding Author: email@example.com, +65 81602452
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 4,378 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 strategically asking for occupant preferences in an intensive longitudinal way.
Indoor environmental quality, Thermal comfort models, Personalised comfort model, Machine learning, Ecological momentary
assessment, Occupant-centric, Occupant behaviour
Many oﬃce workers are familiar with the battle of the ther-
mostat, or that co-worker who talks loudly on the phone. Many
researchers in indoor comfort are also aware of the high rates
of discomfort amongst oﬃce workers [1, 2]. Vast global eﬀorts
have been undertaken to evaluate this discomfort, and with that
knowledge, build models that can be used for the design and
control of buildings. In the realm of thermal comfort, for exam-
ple, two dominant models are in use. The ﬁrst is the Predicted
Mean Vote (PMV) that models comfort based on heat transfer
characteristics between the human and their surrounding envi-
ronment . The other, more modern version, is the Adaptive
Comfort model that includes the human adaptability to climate,
drawing a linear relationship between the indoor and outdoor
The underlying issue with modelling human comfort is the
sheer number of variables present and the diﬃculty in accu-
rately measuring them. Figure 1 highlights this issue by de-
tailing a list of studied physiological, psychological, and en-
vironmental variables that inﬂuence thermal, visual, and aural
comfort. While the empirical models in the academic literature
are capable of incorporating a handful of these variables, the
exclusion of the rest can cause signiﬁcant errors. One reason
is that the interrelationship between diﬀerent indoor environ-
mental parameters is not well-known . It was shown in a
recent study that the lowest indoor environmental satisfaction
factor drives the overall satisfaction . For example, while
one can measure the temperature and humidity of a room; the
type of meal a person ate, and even the spices present in the
meal, can put the human body in a diﬀerent state of thermal
perception [7, 8]. Furthermore, most of the studies that depend
on measuring environmental variables using mobile carts with
mounted sensors [9, 10, 11] or low-cost continuous sensing sen-
sors  face problems related to the accuracy and calibration
. While being comprehensive in capturing most comfort-
related factors, Figure 1 excludes literature about physical and
mental ailments, which further adds variance to the models.
It is, therefore, not surprising to ﬁnd that preference pre-
diction models with only a handful of the factors in Figure 1
have low accuracy. For example, the previously mentioned
PMV model uses personal and environmental parameters
such as temperature, humidity, mean radiant temperature,
air movement, and clothing and metabolism levels to predict
thermal comfort. A recent analysis showed that this model
is only accurate 34% of the time . In the control of real
buildings, these models are further simpliﬁed, and it is usually
the only variables of temperature, illuminance, and noise levels
that are used to evaluate thermal, visual, and aural comfort,
Preprint submitted to Buildings August 25, 2020
arXiv:submit/3338023 [cs.HC] 25 Aug 2020
Near Body Heat
Base Metabolic Rate
Thermal Comfort Visual Comfort
- Frequency of Perception
Seniority in the Company
Figure 1: Graphical review of physiological, psychological and environmental factors inﬂuencing human comfort. Thermal - clockwise from top left: adaptation to
outdoor environment , air ﬂow , solar radiation , circadian rhythm , daylight perception , environmental long wave radiation , perspiration
, diet-induced thermo-genesis , subcutaneous fat thickness , posture , temperature/humidity  , physical activity , clothing level
, vascular anatomy , near body heat sources , gender , age , basal metabolic rate , thermal regulation  , alliesthesia .
Visual - clockwise from top left: circadian calibration , daylight , view , spectrum , uni-
formity , illuminance , ﬂicker , susceptibility to migraines , biophilia , glare .
Aural - clockwise from top: seniority in a company , subjective sensitivity , sound privacy , sound absorption , controllability , task
, variable and constant noise .
1.1. Can longitudinal human perception feedback supplement
The human nervous system detects sensation and converts it
into thoughts and feelings, which are the very foundation of the
word comfort. What if occupants in buildings were asked about
their subjective preference in spaces, instead of only measur-
ing environmental variables and using them to infer comfort?
Collecting enough comfort preference feedback from a single
person over days or weeks would take advantage of a human’s
ability to evaluate dozens of variables simultaneously, includ-
ing those that are diﬃcult to measure. How can this type of
methodology be accomplished in a scalable way without an-
noying occupants too much or inducing survey fatigue? Can
this approach provide insight into comfort problem areas that
contemporary sensors are too expensive or problematic in im-
The goal of this paper was to test the ability of an intensive
longitudinal method to capture numerous environmental feed-
back data from experimental participants in a ﬁeld setting. This
study uses Micro Ecological Momentary Assessments (EMA) as
a subjective feedback methodology that overcomes many of the
challenges presented by traditional methods . Micro-EMA
is a method of using a smartwatch interface to prompt and
collect momentary, right-here-right-now subjective feedback
from a single person over several weeks . Receiving a large
amount of feedback from a single person in a diversity of spaces
and comfort exposures provided the ability to understand the
comfort preference tendencies of a person. It is proposed that
these behavioural tendencies can be used to segment people
into groups related to how they perceive their environment.
Grouping people with similar comfort preferences could,
therefore, increase the accuracy of predicting where a person
will be comfortable and what the system can to respond without
additional sensors. Additionally, collecting large amounts of
subjective preference data from numerous people in a particular
space can characterise the comfort-related attributes of that
space to supplement data being collected from the sensors
installed. If technically scalable and not too disruptive to an
occupant, using humans-as-a-sensor in buildings could change
the way post-occupancy evaluations, building and system
design, and controls and automation are done. There would
be opportunities for people to provide feedback for short-term
episodic uses (days or weeks), for building commissioning or
long-term (months or years), and for continuous system control
and management. This work complements the momentum
from other disciplines focused on the use of humans as sensors
for applications in detection of events using social media data
, for detecting emergencies , and for cybersecurity .
1.2. Paper overview
This paper presents how high-frequency micro-EMA, com-
bined with sensor data time-series analysis, can enable the eval-
uation, control, and rethinking of the design of indoor environ-
ments. Section 2 ﬁrst gives a more detailed overview of founda-
tional work in indoor preference capture and modelling and the
novelty being proposed. Section 3 provides a comprehensive
explanation of the design and deployment of a smart watch-
based subjective preference data collection and environmental
variable measurement system. Section 4 details the results from
a ﬁeld-based implementation at [removed for anonymization]
and the testing of various preference models based on intensive
longitudinal data. Finally, Section 5 and 6 discusses integration
Figure 2: The cozie watch-face, built on the Fitbit smartwatch platform was used to collect subjective feedback. The phone that is paired with the Fitbit can be used
to set up additional questions.
methods in buildings, limitations, future work, and details on
how to reproduce the study using open data and code.
2. Background and novelty
This work builds upon previous literature focused on the
measurement of factors that may inﬂuence thermal, visual,
and aural comfort in the built environment. These modelling
techniques are converged with an intensive longitudinal expe-
rience sampling technique that is common in the medical and
psychological communities, but only emerging in the analysis
of buildings. This section covers previous work in the building
context using intensive longitudinal data and an overview
of the novelty of the work in this paper as compared to the
2.1. Indoor environmental comfort variables and models
There are generally two models types used in the literature
for indoor comfort assessment: 1) objective-subjective, and 2)
objective-criteria . Which method to use is decided based
on the aim of the evaluation. On the one hand, the objective-
subjective model combines the indoor environmental measure-
ments from sensors with the subjective feedback from users,
mostly in the form of post-occupancy evaluation (POE) sur-
veys [57, 58, 59, 60]. On the other hand, the objective-criteria
model is used in ranking or rating a building by comparing the
indoor measurements from IEQ sensors with building perfor-
mance measurement protocols such as LEED or WELL certiﬁ-
cations . Both of the methods have drawbacks both in mea-
suring the environmental data as well as surveying occupants
In terms of environmental measurements, work has been
done that used accurate sensors that were mounted on movable
carts [61, 11]. However, these sensors were not aﬀordable to
all building operations scenarios . The aﬀordability chal-
lenge was met using low-cost continuous sensing sensors that
required frequent calibration . Nevertheless, the location
of these sensors in buildings, and interpolation of the readings
still represented a challenge in the literature, given the fact that
indoor spaces are heterogeneous . On the other side of the
spectrum, surveys pose some problems related to questions, e.g.
what to ask, whom to ask, and how to interpret the results .
Additionally, Porter et al.  discussed the term survey fatigue
in which users feel overwhelmed by questions that may lead to
a misrepresentation in responses and reduced response rates.
A related area of recent focus is the use of wearable and
infrared radiation sensors to capture near-body physiological
data that deﬁne the environmental conditions close to or at
the skin surface of an occupant. A recent study focused on
creating personalised comfort models from these data in the
context of ﬁeld-based deployment on 14 subjects . This
deployment and the models produced used wrist and ankle skin
temperature from several sensors placed on the participants
and a smartphone application to collect surveys. Further work
in the indoor context showed that both wearable sensors and
infrared radiation cameras led to a 3-4% increase in accuracy
of thermal comfort sensation prediction, marginally justifying
the cost of implementation in a ﬁeld setting .
2.2. Ecological momentary assessments (EMA)
The next area of background focuses on the challenge of
collecting large amounts of longitudinal data from a person.
Many ﬁelds of study have relied upon the ecological momen-
tary assessment  methodology to meet this challenge. This
method is a type of intensive longitudinal experience sampling
most often utilised in studying human behaviour. The word
ecological describes that fact that the measurement is taken
in the subjects’ natural environment without impacting their
task at hand. The word momentary pertains to the fact that
feedback is requested at the moment of experience, as opposed
to asking a subject to recall a past experience. And ﬁnally,
the assessments are not static one-oﬀoutcomes but occur
over time, thus accounting for temporal dynamics. Traditional
models found in literature such as surveys are insuﬃcient as
their sampling rates are low, require the occupant to completely
stop their task at hand to focus on the survey, and in many
cases, ask for a recollection of past experiences. There is the
further issue of survey fatigue  and even when willing
to participate, there is a concern about how accurate their
responses are . The use of a smartwatch for data collection,
coined micro ecological momentary assessments, has been
shown to be so user-friendly that it does not signiﬁcantly
disrupt any ongoing activity . Furthermore, an eight-fold
increase in sampling frequency can be obtained, in comparison
to smartphone use, without burdening the user. Recent work
has used ecological momentary assessments to assess the built
environment through the use of smartphones . While such
applications are a step in the right direction, they were only
able to collect eight feedback points per occupant, which is
insuﬃcient for time-series analysis.
2.3. Similar work in intensive longitudinal data collection in
the built environment
Intensive longitudinal methodologies have begun to emerge
as a way to characterise occupants for various built environ-
ment objectives. In the urban context, several studies have
deployed sensors on people to understand their experiences
across their daily lives. A large study based in Singapore
used thousands of wearable sensors in populations of students
to discover travel patterns , collect information about
thermal parameters , and even infer the impact of public
spaces on happiness . Work has been done in a controlled
outdoor ﬁeld study to understand the impact of the urban
context on various emotions and physiological responses of
human . In the indoor setting, targeted work on collecting
longitudinal data for more speciﬁc purposes has also emerged.
The previously mentioned wearable study focusing on thermal
comfort collected numerous data from the 14 participants over
the 2-4 week study . Another recent study that deployed
a cyber-physical system to collect longitudinal data in oﬃces
focused on occupant concentration . The work in this
paper is most directly related to previous work in collecting
longitudinal comfort feedback from smartphone interfaces for
the allocation of activity-based workspaces  and through a
sustainability tour in a university campus building .
2.4. Novelty of proposed approach
Despite the momentum in ﬁeld-based intensive longitudinal
methodologies, there are still several barriers to their implemen-
tation in real-world settings. Not the least is the challenge of
getting human occupants to give data for comfort surveys, in-
stall applications, or wear devices. Working from this knowl-
edge, the authors developed cozie, as seen in Figure 2, an open-
source, smartwatch clock-face designed to conduct micro-EMA
surveys for high-frequency data collection . The applica-
tion is open-sourced and free to download and use on the Fitbit
The innovations outlined in this work as compared to the pre-
viously mentioned studies are:
•The hardware and software deployment methodology have
a focus on practicality in scalable, ﬁeld-based implementa-
tions. Experimental participants were only asked to wear a
single smartwatch device and answer survey questions that
utilise a relatively small amount of time. The focus was on
testing a conﬁguration that was easily applied in a real-
world context. The modelling methodology was designed
to capture as much signal as possible in the ﬁeld setting
without the ability to control and verify sensor proximity
and accuracy consistently.
•A series of pre-processing steps were developed to convert
intensive longitudinal data into model input features that
characterise the tendency of groups of people to have simi-
lar comfort preferences, sometimes independent of the ob-
jective environmental factors such as temperature. A sim-
ple example of this concept is the commonly discussed, yet
often anecdotal, person who seems always to need more
cooling, even when the temperature is already low rela-
tive to the comfort zone. In this study, clustering was used
to group people into comfort preference types as an input
feature to a preference prediction model.
•This paper introduces and tests a simple form of a cold
start variant to the preference models that could be used
to predict an occupant’s preference with limited or no data
about their preference history in a particular space or ac-
cording to particular objective measurements such as tem-
perature, humidity, or other factors. This model enables
the deployment of the cozie data collection methodology
by a set of participants in a building and then the creation
of prediction models that could accommodate future occu-
pants regardless of whether they have worn a smartwatch
in those spaces.
•The process seeks to show that comfort-based preference
prediction can be accurate even in the absence of environ-
mental sensors if enough intensive longitudinal data has
been collected from enough occupants. The context of this
experiment was in relatively uncontrolled, ﬁeld-based set-
tings as opposed to laboratory conditions.
To collect intensive longitudinal data in a ﬁeld setting, the
cozie platform was built on the Fitbit smart watch2and various
time-series database technologies. In this section, the details of
this technology stack are explained in the context of a deploy-
ment on 30 test participants in buildings at the National Uni-
versity of Singapore (NUS) in the School of Design and En-
vironment (SDE). The deﬁnition of an occupant in this study
was a test participant who wore the smartwatch, and a manager
as the person who coordinated the study. Thirty participants
were recruited via an online form, were compared to the inclu-
sion criteria for the study, and were on-boarded according to
an approved ethics review application. Priority was given to
participants who work full time in the SDE-related buildings
Tier 2: smart-watch
Tier 3: smart-watch
+ environmental sensors
+ near body sensor
- Thermal Feedback
- Visual Feedback
- Noise Feedback
- Heart Rate
SENSing Air Sense
- Noise Level
Tier 1: smart-watch
Figure 3: Overview of the experimental deployment in the SDE buildings in four distinct tiers: Tier 1 is the base methodology which is production-ready for
real-building deployment. It requires a smart watch with the cozie clock-face installed. Tier 1b, is an extension to the base methodology by adding a temperature
sensor to the watch. Tier 2 includes building-wide indoor localisation. In this experiment, Steerpath Bluetooth beacons were used, which communicate with the
occupant’s smartphone to determine the occupant’s location. Tier 3 merges the localised feedback points with environmental sensors in the same comfort zone as
on campus, and they were selected to maintain an even gender
The technology used in the deployment of this study can be
sub-sectioned into individual tiers as described in Figure 3, with
each level requiring additional resources to implement. For the
experiment in SDE4, all tiers were incorporated.
3.1. Tier 1: Smartwatch for micro-EMA
Tier 1 is the core methodology presented in this paper, which
uses the cozie clock-face, as shown in Figure 2. The occupants
were asked to wear a Fitbit Versa smartwatch during daytime
hours while on the NUS campus at the very least but were also
welcome to wear the device for the entire duration of the study.
Participants were asked to leave momentary assessment feed-
back on their comfort preferences at diﬀerent points throughout
the day on the watch face of the Fitbit device. Each time they
responded to the survey, they were asked about their thermal,
visual and aural preference using the options found in Figure
2. Comfort preference was chosen as the feedback most ap-
plicable to the methodology due to a three-point scale that is
most appropriate for frequent watch-based surveys. Preference
surveys also provide more meaningful information by indicat-
ing how the occupant would want the environment to change
as opposed to satisfaction or sensation survey types that only
capture how the occupant feels. The participants were asked to
answer the questions when they moved from one environment
to another, which amounted to approximately 5-15 assessments
per day. The smartwatch also prompted the occupants with a
small vibration that requested feedback from them at diﬀerent
timed points in the day. This prompt only occurred during day-
time hours when the subject was active. The momentary as-
sessment took less than 15 seconds to complete. Throughout
the experiment, the cumulative amount of time spent answering
the momentary assessment was approximately 20-40 minutes.
Detailed documentation for using cozie, along with the
source code to an open-source repository, can be found on a
GitHub repository3. The platform also can collect sensation,
satisfaction and objective feedback such as clothing and activ-
ity levels. These features were added after the experiments out-
lined in this paper and were not used in this study.
3.2. Tier 2: Indoor localisation
Tier 1 is likely suﬃcient for experiments conducted in small
oﬃce spaces. If only a few diﬀerent zones exist, then an occu-
pant’s location could be quickly determined through a supple-
mentary question in the question ﬂow of the survey. However,
in a large building, such as the SDE4 building where the out-
lined experiment was conducted, a more sophisticated indoor
localisation system was required. The SDE4 building has six
diﬀerent ﬂoors, a gross ﬂoor area of around 8,500 square me-
ters, and a large variety of diﬀerent indoor environments. To
determine an occupant’s location in a building, 100 Bluetooth
beacons and the Steerpath4platform were installed throughout
the building. These beacons communicated with a custom-built
smartphone application, called the Yak App , to determine
their location with a one-meter precision. The location data was
then used to geo-fence the occupant within various zones of the
building and was merged with the subjective preference feed-
back data in the cloud.
3.3. Tier 3: Preference data convergence with environmental
Tier 3 included the deployment of 45 indoor and outdoor
environmental quality (IEQ) sensors in the experimental con-
text. This data collection tier was used to compare the results
of the subjective feedback, with existing environmental mod-
els. The IEQ sensors were WiFi-connected and were deployed
by the company SenSING5as part of an installation of sensors
campus-wide. These sensor kits measured temperature, humid-
ity, noise level, and illuminance. At least one sensor device was
installed in each zone of the building, and the data was pulled
from an API and merged with the subjective preference data in
3.4. Tier 1b: Strap-mounted sensor kit
Tier 3b included a temperature sensor was used from mbient
labs6, which was attached to the watch through a custom three
dimensional (3D) printed case. The design ﬁle for this case
can be found online7. The mbient device logged data locally,
which was transferred to the cloud database at the end of the
3.5. Occupant and room preference clustering
This analysis included the hypothesis that the feedback of
one of the occupants in such groups could be used to char-
acterise the preferences of all group members for a particular
space or set of conditions. In this step, the preference history
of occupants was used to do a simple clustering-based segmen-
tation step to group occupants according to their raw feedback
preference tendencies. For example, occupants who more fre-
quently indicated prefer cooler as compared to a no change
would be grouped. This strategy was a simpliﬁed version of
this type of clustering as it neglects other context-based vari-
ables (environmental and physiological measurements). This
choice was made to keep the method feasible even in situations
in which other measurements are not available.
Given its widespread usage in related literature, occupant and
room clustering is calculated using the k-means clustering algo-
rithm with Euclidean distance, using the scikit-learn package8.
The features used for clustering were the ratio of votes of each
feedback class value for each subject. For example, the ratio
of prefer cooler for a given participant, or room, would be cal-
culated as follows: #prefer cooler votes
#total votes . This calculation is repeated
for all types of feedback responses for thermal, light, and aural
feedback. Then, the number of clusters was chosen to match
the number of possible responses per type of feedback, this led
to initially k=9, but given that there were no data points with
prefer louder responses, the clusters were merged into eight.
3.6. Occupant comfort preference prediction
The metric of comparison in this study was the prediction
improvement of a machine learning model using added fea-
ture sets extracted from the intensive longitudinal preference
data. This structure matches implementation-based environ-
mental comfort studies outlined in the literature that showed
the predictive improvement of additional data [64, 65]. This
approach can be compared to more controlled, lab-based meth-
ods that seek to isolate variables and individually test their in-
The prediction problem translates to predicting the right class
value or, in this case, the preference feedback response, at the
given feature values. A random forest classiﬁer from the scikit
learn package was chosen to handle this comfort prediction.
Random forest classiﬁers have been proven to have the highest
accuracy at predicting personal comfort in one previous study
 and is one of the best performing of other recent studies
[64, 65, 78]. The decision was made to focus on the implemen-
tation of a single model type that has been proven eﬀective and
is straightforward to use based on documentation and ease-of-
tuning. With this in mind, we ﬁxed the hyper-parameters for the
random forest classiﬁer to 1000 number of trees, Gini criterion
for node splitting, and two minimum samples per split.
Additionally, the prediction problem was divided into an in-
dividual and a grouped prediction task. The former refers to a
model developed speciﬁcally for a given occupant, using only
parts of its data to train a model and test it on its remaining
data. On the other hand, the latter approach consists of combin-
ing all occupants’ training data subsets with training a model
and testing it on all the occupants’ remaining data.
The data of each occupant was split into a 60:40 train test
set based on time. That is, the ﬁrst 60% of votes from each
occupant was used in their training set, and the remaining 40%
was used for testing. The sets were split by time to prevent the
scenario of future data being used to predict the past. For the
grouped model, all the occupants’ training sets (60% of each
occupant’s data) was used as one training set, and the remaining
40% of each occupant’s data was combined with being used as
one test set.
A primary component of the method was to test the ability
for various feature sets to inﬂuence the prediction power of the
random forest model. The method used six combinations of
these feature sets to test the inﬂuence each has in the predictive
capability of the overall model. The following is an overview
of these feature categories developed for testing:
•Time was created through feature engineering the time
stamp of when an occupant gave feedback. This feature
was a cyclical representation of the hour of the day and
day of the week. This simple feature type detects if cer-
tain cyclical habits or components have a role in prefer-
ence prediction and was included in all scenarios.
•Environmental Sensors were features extracted from
measurement data from lighting (lux level), noise (dB
level), temperature (deg. Celsius), and relative humidity
(RH%) measurement. These variables were collected from
the IEQ sensors that were closest spatially and temporally
to an occupant when they gave feedback.
•Near Body Temperature was a feature created from the
temperature sensor mounted on the smartwatch strap that
had temporal proximity to the time-stamp of when the oc-
cupant gave feedback.
•Heart Rate was collected from the Fitbit smartwatch de-
vice as an instantaneous value collected when the occupant
•Room was a feature that was encoded to a numerical pref-
erence type based on the history of feedback in the room
in which the survey was taken. This feature was designed
to increase the prediction accuracy by complimenting data
from rooms of similar comfort proﬁles. For example, if an
occupant only works from their oﬃce, the model will still
be able to accurately predict how that occupant may feel
in other rooms that have a similar comfort proﬁle to their
•Preference History features are similar to the Room fea-
tures. These features use the ratio of responses of each
type (thermal, visual, and aural) that were calculated for
each user. This ratio was only calculated for the responses
of prefer cooler,prefer warmer,prefer dimmer,prefer
brighter,prefer quieter, and prefer louder. E.g., the ratio
of response of prefer cooler responses of a given occupant
is calculated the following way: #prefer cooler votes
#total votes .
Model classiﬁcation results were calculated using the F1-
micro scores (as shown in Equation 1) which were equivalent
to accuracy in the a multi-class classiﬁcation problem by cal-
culating precision and recall averaged across all classes,
i.e., subjective thermal comfort response value. As the objec-
tive was to provide a comparison among diﬀerent feature sets
with a standard metric, F1-micro was chosen due to its usage
for benchmarking diﬀerent aspects of the modelling pipeline in
thermal comfort datasets .
precision +recall (1)
The results presented in this section are complemented with
an interactive web application9and interactive code10 which
10https://github.com/buds- lab/humans-as-a-sensor-for- buildings
Intensive Longitudinal Preference Collection
Prefer No Change
Prefer No Change
Prefer No Change
Figure 4: Overview of the intensive longitudinal data collected from the occu-
pants according to the three categories: Prefer warmer (red) and Prefer cooler
(blue) for thermal, Prefer Brighter (orange) and Prefer Dimmer (purple) for
lighting, and Prefer Quieter (green) for acoustics. Each row is an occupant and
each box in that row shows that occupant’s feedback answers collected sequen-
tially. The visualisation is diagrammatic in that vertical alignment of the boxes
between diﬀerent occupants does not imply identical time stamps.
enables the reader to regenerate all the plots. During a two
week collection time of 30 participants, 4,378 comfort prefer-
ence votes were collected, which is 146 data feedback points
per person on average. From this set, 1,474 data points were
successfully localised to building environmental sensors. To al-
low for comparison with those data, this subset was used for
analysis and machine learning in the following sections.
4.1. Grouping comfort preference tendencies
Figure 4 illustrates an overview of the intensive longitudinal
preference history data for each person according to the three
preference categories. These feedback responses were only
those collected in the SDE4 building, and a maximum num-
ber of 75 votes is shown. A simple clustering step was applied
in this ﬁgure to represent the segmentation according to each
preference category on its own. This visualisation shows how
this simpliﬁed clustering step captured the tendency of an occu-
pant to lean more towards one feedback response over the oth-
ers. This segmentation was independent of the environmental
parameters of the spaces to maintain the simplicity of the ap-
proach. The subsequent modelling steps were designed to test
the eﬀectiveness of doing this type of simpliﬁed segmentation.
Figure 5a is an aggregated representation of the segmenta-
tion process for each occupant, this time with all three prefer-
Prefer Cooler Brighter Quieter
Prefer Brighter Quieter
Indoor Comfort Personality Tendencies:
(a) Occupant-based Clustering
Naturally Ventilated Work Space
Naturally Ventilated Cafe
Naturally Ventilated Circulation Space
Cooler Quieter requests
Relatively higher percentage of:
Cooler Quieter requests
Work Spaces / Offices
(b) Room-based Clustering
Figure 5: K-means clustering of preference tendencies quantiﬁed by average number of votes by occupant (a), and by room (b) within the test building. Each row
presents the percentage of votes that fell into a respective preference. Dark colours in cells indicate higher preference.
Figure 6: Interactive visualisation of the data collection in the SDE4 building that highlights the spatial distribution of subjective preference data for thermal comfort
in three dimensions. In terms of preference feedback, the blue dots indicate prefer cooler responses, the yellow dots are no change, and the red dots are prefer
ence categories being used in the clustering process. This ﬁg-
ure summarises each occupant as a row of data, and the colour
of the box represents the percentage of votes given to a par-
ticular preference category, where dark colours indicate higher
preference. These clusters provided segmentation of the users
according to their preference tendency types that were used in
the preference models. Even in a sample size of 30 occupants,
there were varying comfort tendencies present, which comple-
mented the concept of a personal comfort model tested by Kim
et al. . This clustering step provided the foundation for the
creation of the individual versus grouped models used in the
4.2. Tagging the spatial context with preference feedback
While the subjective feedback highlighted varying comfort
tendencies within a building, localisation also enabled the char-
acterisation of preference tendencies in certain zones. Figure 5b
presents each room as a row, where the colour of each cell rep-
resents the percentage of a preference vote given for a particular
room. The utilisation of k-means clustering once again enabled
the splitting and labelling of these zones, this time by the ten-
dency for diﬀerent comfort preferences to be left by occupants
in those spaces. This result ﬁrstly served as an overview for
facility managers to understand the oﬃce spaces they manage,
and take action to improve upon the comfort. A visualisation of
the subjective thermal preference data can be found in Figure 6
4.3. Correlation with indoor environmental quality variables
One standard aspect of environmental comfort studies is the
comparison of feedback to objective environmental measure-
ments. For the data collected in this study, standard distribu-
tion plots of the environmental sensor data are summarised in
Figure 7. Intuitive insight in the data can be observed, such
as the absence of prefer brighter votes after an illuminance
threshold of 250 lux. Nevertheless, there was a signiﬁcant over-
lap between classes for each of the environmental parameters,
which were likely attributed to the numerous unmeasured vari-
ables described by Figure 1, and the varying comfort tendencies
shown in Figure 5. This result reinforces the evidence that en-
vironmental measurements are not descriptive enough to char-
acterise a person’s preferences, which results in poor prediction
as found in previous studies .
4.4. Predicting ﬁeld-based indoor preference using intensive
In this section, the time-series feedback was used to predict
comfort satisfaction. Figure 8 shows a comparison of the var-
ious models built with the feature sets and process outlined in
Section 3. The individual comfort model uses the occupant’s
training data for prediction, while the grouped comfort model
uses the input data for the groupings outlined in Figure 5. The
top of Figure 8 shows a table in which each row represents the
feature set that was used to train the model in that column.
Several insights were evident from this modelling analysis.
Firstly, there were only small diﬀerences in the F1 scores be-
tween the diﬀerent feature sets for the visual and aural pref-
erence models. These models, in general, had higher F1 scores
Environmental Temperature (C°) Environmental Humidity (RH%)Near Body Temperature (C°)
Environmental Light (lux)Heart Rate (beats per minute)
Prefer No Change
Prefer No Change
Prefer No Change
Environmental Noise (dB)
Figure 7: Distribution of sensor data by preference vote. While trends can be observed many feedback votes overlap for the same environmental or physiological
measurement. This was possibly due to the diﬀerent comfort tendencies as shown in Figure 5 or numerous other variables described in Figure 1 that are not
accounted for. Near body temperature and noise appear to have the most distinct diﬀerentiation.
than thermal preference prediction. Aural preference prediction
had the highest F1 score, which was intuitive since it became a
binary classiﬁcation challenge due to the lack of prefer louder
Thermal preference prediction had more diversity across the
feature sets tested as compared to the other preference cate-
gories. Merely using the conventional time-series and environ-
mental sensor features had the lowest F1 score. Adding the
physiological attributes of heart rate and near body temperature
provided marginal improvements. The best thermal preference
model used the physiological, room, and preference history fea-
tures while excluding the environmental sensor data.
For all three preference categories, the grouped comfort
model performed better than the individual version. Partici-
pants with similar comfort preferences became clustered to-
gether, thus increasing the training dataset for that particular
occupant type. This result showed the impact that assigning a
variety of peer groups can have on preference prediction.
4.5. Cold-start comfort preference prediction
The success of the preference models using grouping allowed
for models that can predict an occupant’s preferences without
their own personal data present. This scenario was labelled as
acold-start situation as it emulates when an occupant doesn’t
wear a watch to collect data in a particular building, but relies
on crowdsourced data from peers that have a similar comfort
preference. The line graphs to the right of Figure 8 show the
results of this type of analysis. They illustrate the number of
occupants required to suﬃciently crowdsource the data for an
average occupant for each of the preference categories. The
orange line represents an ordinary person who doesn’t wear a
smartwatch, whereas the blue line is a smartwatch owner who
is regularly giving feedback. In this study, nine and ﬁve users
were suﬃcient on average to crowdsource the thermal and vi-
sual comfort prediction respectively to the same accuracy as a
user wearing a watch.
4.6. Predicting continuous comfort preference without sensors
Since the preference feedback in this methodology was at a
much higher high-frequency than a typical survey or occupants
acting on the thermostat, this study had preference data with
relatively high temporal and spatial diversity. The random for-
est classiﬁer was used to predict comfort preference based on
a time-stamp input for each zone to create a continuous pre-
diction over time. This approach emulates the concept of us-
ing human feedback as a type of sensor. Figure 9 illustrates
the prediction of two diﬀerent zones, an oﬃce and an outdoor
space, for a typical week using this model output. First, one can
see that the oﬃce was generally a comfortable space, while the
outdoor seating had an overall higher preference for cooling.
Time-dependent ﬂuctuations show how the model was able to
predict comfort preference for diﬀerent parts of the day or days
of the week. The oﬃce had a peak of warmer preference around
mid-day. Finally, it was observed how the model, often inaccu-
rately, tried to predict comfort at times where no data is present.
The square peaks in the oﬃce for aural and visual prediction
between the hours of 22:00 and 7:00 were due to an absence of
data to accurately predict during these times.
The results of this implementation showed the potential of
collecting intensive longitudinal feedback from occupants in
the built environment. This approach revealed that the deploy-
ment and implementation of such a methodology were eﬀec-
tive, and comfort models for visual, aural, and thermal comfort
can have similar performance to sensor measurements. The key
focus in this section is to discuss the practical uses and limita-
tions of the proposed methodology.
5.1. Practical Application of Intensive Longitudinal Data in
At the foundation of the method, the creation of more sig-
niﬁcant amounts of occupant feedback information in the form
of preferences was successful. The utilisation of these type of
high-frequency subjective feedback data has potential for build-
ing evaluation and occupant comfort optimisation. It changes
the paradigm in which facility managers operate a building.
For example, instead of saying light levels are below the com-
fort threshold in Oﬃce-1, the new conclusions could state that a
higher frequency of prefer brighter votes are recorded in Oﬃce-
1. Furthermore, due to the high-frequency sampling rate pro-
vided by the micro ecological momentary assessment method-
ology, these periods of discomfort can also be mapped to partic-
ular times, and certain groups of people. The time series com-
fort proﬁles could also serve as input data for occupant-centric-
control eﬀorts of building systems which can then optimise for
human comfort and energy optimisation.
5.1.1. Post-occupancy evaluation, commissioning, and sensor
A focus on post-occupancy evaluation could be a key tar-
get for this type of data collection. In this scenario, a particu-
lar sample of non-transient occupants of a recently constructed
building would be given smartwatches and asked to wear them
for 2-4 weeks. These data could then be used to supplement the
systems installed to characterise whether there are blind spots
in terms of sensors not picking up comfort-inﬂuencing phe-
nomenon that is not being measured. For example, it’s rare to
measure mean radiant temperature in most buildings; therefore
hot spots might exist that are undetectable by thermostats and
might be a result of inadequate shading or control of shading
systems. To adapt the presented methodology to this context is
straightforward as the two-week time frame of the experiment
is similar. The current method involved asking each participant
to wear the smartwatch until 100 data points were recorded.
In a real-world setting, a similar approach could be deployed.
At that point, perhaps the occupant could choose to return the
device and rely on the data of co-workers for comfort predic-
tion or continue to wear it and help crowdsource the data for
others. It is strongly recommended that these deployments use
automated indoor localisation to put the feedback in the spatial
context without user intervention.
5.1.2. Potential for spatial recommendation systems and im-
pact on activity-based workspace design
A less typical application for intensive longitudinal data
might be the development of spatial recommendation engines
for occupants in activity-based workspaces. In these spaces, an
occupant doesn’t have a constant workspace but instead ﬁnds
a space that matches their immediate needs. This paradigm
could prove to be an integral part of future working style, es-
pecially in light of social distancing due to global pandemics
such as COVID-19 that forces a less conventional spatial work-
ing arrangement. This recommendation engine might work in
a way that an occupant’s comfort tendencies could be matched
with the comfort zone of the building. For example, those that
prefer warmer spaces can be recommended to work in areas
that have a higher percentage of prefer cooler votes. Previous
work in this direction showed progress using a platform known
as Spacematch . Smart watch-based longitudinal feedback
could enhance the model development process for this type of
The aspect of testing group-based models in this study is es-
sential for this context as building owners can’t expect all oc-
cupants to be willing to wear or use devices. And those that
do agree will likely have a limited amount of patience for giv-
ing feedback over long periods. This paper tested the ability to
cluster occupants such that it was not necessary for everyone in
an oﬃce to wear a smartwatch. The only requirement for this
type of system to work is that each new employee would wear
a smartwatch during a two-week data collection phase, which
is suﬃcient to build their comfort preference tendency history
as described in Section 4.1. The experiment also showed that
not everyone in an oﬃce space needed to be using the smart-
watch application all the time. In this particular experiment,
Near Body Temperature
Without test subject’s data
(occupant without a watch)
With test subject’s data
(occupant with a watch)
Number of users added to the training set
Occupant without a watch has similar
accuracy as an occupant with a watch
Occupant without a watch has similar
accuracy as an occupant with a watch
Comfort prediction using the best performing
Model has single occupant data:
Individual comfort model
Model has all occupant data:
Grouped comfort model
σ: σ: σ: σ: σ: σ:
σ: σ: σ: σ: σ: σ:
σ: σ: σ: σ: σ: σ:
σ: Standard Deviation
Figure 8: Left: Comparison of prediction F1-micro-score between grouped and individual comfort models using data from diﬀerent feature sets. The feature set that
excluded environmental sensor data for the thermal model had the highest F1-score, while minimal diﬀerences in F1-score were noted between feature sets of the
visual and aural models. Right: The accuracy in predicting the comfort of an individual as further participants are added to the training set. The blue line includes
the test participants training set in the training data, and the orange line excludes the test the participants training data meaning that it depends on crowdsourced
feedback from other occupants.
Zone 1 - Outdoor Seating Zone 2 - Office
Figure 9: Comfort prediction for two zones for an average occupant over a week. The grey circles indicate votes that were given for each category, and the shaded-
out sections indicate times where no data were present. These time-series predictions can be used to detect anomalies, such as the mid-day peak for a warmer
preference for the oﬃce, or the general discomfort in the outdoor seating area. Note that there was an absence of data in these zones between the hours of 22:00 -
7:00, and on the weekend. This lack of data caused inaccurate predictions as seen in the square-shaped peaks in the oﬃce.
six occupants were suﬃcient, on average, to crowdsource the
prediction for the remaining 24. This value is not generalisable
amongst all buildings and would change depending on the dif-
ferent comfort tendencies the building occupants might present.
The higher the variation in comfort preferences, the greater the
number of the occupants needed to crowdsource the data.
In terms of oﬃce space design, the collection of intensive
longitudinal preference data could facilitate ﬂoor plan design
decisions. Understanding the breakdown of comfort needs ac-
cording to the tendencies of the occupants would enable archi-
tects to design or retroﬁt buildings with diﬀerent comfort zones
to match the diﬀerent types of people. For example, if the zones
with more cooling were popular and being used to their capac-
ity, then the ﬂoor plans or systems control could respond to by
creating more spaces of that type to increase the probability that
a person feels comfortable.
5.1.3. Integration into building control systems
Intensive longitudinal data has the opportunity to inﬂuence
the control and automation systems of buildings through the use
of preference feedback data in the control logic. Most building
control systems rely on optimising a set-point temperature that
is considered comfortable for the average occupant or comfort
standard . In that scenario, discomfort instead of comfort
is evaluated as the current diﬀerence of the environment ther-
mostat and the HVAC system set-temperature , occupancy
density estimation, or via more traditional ways such as PMV
. While some of these approaches have dealt with single-
occupant oﬃces or Personal Comfort Systems (PCS), there is
a distinction between controlling the actual HVAC system and
allowing the occupant to control their immediate space. PCS
systems are those that locally condition the occupant indepen-
dent of the centralised HVAC system . The intensive longi-
tudinal data and the models developed in this study could help
the controls ﬁeld take the next step forward in occupant-centred
building controls through the use of reinforcement learning
. The feedback mechanism in reinforcement control is gen-
erally the standard occupant-building interface such as switch
or thermostat . Intensive longitudinal data could be used
to enhance that interaction by focusing on ﬁnding the motiva-
tions of those control actions. This work is a strong focus of
the occupant-centric building operations in the IEA Annex 79
5.2. Prediction models are only as good as the training data
The primary limitation of the presented approach was that
it would only work where data were present. As seen in Fig-
ure 9, there were errors in the prediction when data were ab-
sent, i.e., no historical data collected at similar time windows
such as the middle of the night. Furthermore, since there was
a reliance on other subjects’ historical preferences, i.e., crowd-
sourcing preferences, to evaluate environments, an oﬃce space
that was rarely used would have a poor prediction of occupant
comfort. Classical comfort models based on sensor data do not
have this issue as spaces that are not used can still be charac-
terised by the measured data. Furthermore, this particular study
was conducted in Singapore, which doesn’t have seasons and
has minimal variability in temperature. For seasonal countries,
the day of the year would be an added feature that may take up
to a year worth of data to train. Further work could investigate
the opportunity of using sensor data to characterise a space and
then continuously reﬁne the comfort prediction by crowdsourc-
ing the occupants’ preference on said space.
This paper presents how micro ecological momentary assess-
ments of subjective comfort can generate suﬃciently large in-
tensive longitudinal data for occupant comfort prediction and
enhancement that can supplement objective environmental sen-
sor data, and empirical comfort models. Results of an imple-
mentation of the platform on 30 occupants showed the segmen-
tation and variation of indoor occupant comfort tendencies and
highlighted the shortcomings of one-size-ﬁts-all comfort mod-
els that are commonly applied in real buildings. Furthermore,
the use of a smartwatch enabled data collection at a suﬃcient
frequency to build time-series models of indoor spaces. These
models could be used to detect building anomalies, serve as
building data for subjective driven building control, or be used
to recommend spaces that best match the comfort preference
tendencies of each occupant. The optimum technological set-
up uses a smartwatch for subjective data collection, combined
with a method for localising an occupant in the building. This
localisation may be achieved by asking the occupant directly
through the smartwatch, or through Bluetooth or WiFi signals.
Author contribution statement
PJ: hardware, software, infrastructure development, experi-
mental design, implementation and lead author of the paper;
MQ: software, infrastructure development, data analysis, ma-
chine learning lead and author of the paper; MA: software, in-
frastructure development, and author of the paper; CM: fund-
ing, project leadership, experimental design, the corresponding
author of the paper.
The Singapore Ministry of Education (MOE)
(R296000181133 and R296000214114) and the National
University of Singapore (R296000158646) provided support
for the development and implementation of this research.
This research contributes to the body of work for the Interna-
tional Energy Agency (IEA) Energy in Building and Communi-
ties (EBC) Annex 79 - Occupant-Centric Building Design and
Data availability statement
Segments of the raw data and analysis code used for this
study are available in an open-access Github repository that in-
cludes further documentation12.
 M. Frontczak, S. Schiavon, J. Goins, E. Arens, H. Zhang, P. Wargocki,
Quantitative relationships between occupant satisfaction and satisfaction
aspects of indoor environmental quality and building design, Indoor air
22 (2012) 119–131.
 I. Sakellaris, D. Saraga, C. Mandin, C. Roda, S. Fossati, Y. De Kluizenaar,
P. Carrer, S. Dimitroulopoulou, V. Mihucz, T. Szigeti, et al., Perceived in-
door environment and occupants’ comfort in european “modern” oﬃce
buildings: The oﬃcair study, International journal of environmental re-
search and public health 13 (2016) 444.
 P. O. Fanger, et al., Thermal comfort. analysis and applications in envi-
ronmental engineering., Thermal comfort. Analysis and applications in
environmental engineering. (1970).
 R. De Dear, G. S. Brager, Developing an adaptive model of thermal com-
fort and preference, ASHRAE Transactions, Vol 104 (1998).
 I. Asadi, I. Hussein, K. Palanisamy, W. Conference, M. Comfort, R. Cum-
berland, E. Use, C. Environmental, M. Engineering, V. Mesiano, R. Su-
laiman, S. N. Kamaruzzaman, T. Ramos, S. Dedesko, J. A. Siegel, J. A.
Gilbert, B. Stephens, I. Asadi, N. Mahyuddin, P. Shaﬁgh, E. M. d. A.
Vieira, L. B. da Silva, E. L. de Souza, A survey of evaluation methods
used for holistic comfort assessment, PLoS ONE 953-954 (2016) 1513–
 H. Tang, Y. Ding, B. Singer, Interactions and comprehensive eﬀect of
indoor environmental quality factors on occupant satisfaction, Building
and Environment 167 (2020).
 C. Henry, B. Emery, Eﬀect of spiced food on metabolic rate., Human
nutrition. Clinical nutrition 40 (1986) 165–168.
 R. Swaminathan, R. King, J. Holmﬁeld, R. Siwek, M. Baker, J. Wales,
Thermic eﬀect of feeding carbohydrate, fat, protein and mixed meal in
lean and obese subjects, The American journal of clinical nutrition 42
 T. Webster, F. Bauman, G. Anwar, CBE Portable Wireless Monitoring
System (PWMS): UFAD Systems Commissioning Cart Design Speciﬁ-
cations and Operating Manual, Internal Report, Center for the Built En-
vironment, UC Berkeley (2007) 4.
 J. H. Choi, V. Loftness, A. Aziz, Post-occupancy evaluation of 20 oﬃce
buildings as basis for future IEQ standards and guidelines, in: Energy and
Buildings, volume 46, pp. 167–175.
 H. Kim, Methodology for Rating a Building’s Overall Performance based
on the ASHRAE/CIBSE/USGBC Performance Measurement Protocols
for Commercial Buildings, Journal of Chemical Information and Model-
ing 53 (2013) 1689–1699.
 T. Parkinson, A. Parkinson, R. de Dear, Continuous IEQ monitoring sys-
tem: Context and development, Building and Environment 149 (2019)
 J. F. Nicol, M. Wilson, A critique of European Standard EN 15251:
Strengths, weaknesses and lessons for future standards, Building Re-
search and Information 39 (2011) 183–193.
 S. Schiavon, B. Yang, Y. Donner, V.-C. Chang, W. W. Nazaroﬀ, Thermal
comfort, perceived air quality, and cognitive performance when person-
ally controlled air movement is used by tropically acclimatized persons,
Indoor air 27 (2017) 690–702.
 S. G. Hodder, K. Parsons, The eﬀects of solar radiation on thermal com-
fort, International journal of biometeorology 51 (2007) 233–250.
 K. Kr¨
auchi, How is the circadian rhythm of core body temperature regu-
lated?, Clinical Autonomic Research 12 (2002) 147–149.
 G. Chinazzo, J. Wienold, M. Andersen, Daylight aﬀects human thermal
perception, Scientiﬁc reports 9 (2019) 1–15.
12https://github.com/buds- lab/humans-as- a-sensor-for- buildings
 E. Halawa, J. van Hoof, V. Soebarto, The impacts of the thermal radia-
tion ﬁeld on thermal comfort, energy consumption and control—a critical
overview, Renewable and Sustainable Energy Reviews 37 (2014) 907–
 T. Fukazawa, G. Havenith, Diﬀerences in comfort perception in relation
to local and whole body skin wettedness, European journal of applied
physiology 106 (2009) 15–24.
 B. Kingma, A. Frijns, W. van Marken Lichtenbelt, The thermoneutral
zone: implications for metabolic studies, Front Biosci (Elite Ed) 4 (2012)
 P. Tikuisis, M. B. Ducharme, The eﬀect of postural changes on body
temperatures and heat balance, European journal of applied physiology
and occupational physiology 72 (1996) 451–459.
 A. P. Gagge, J. Stolwijk, J. Hardy, Comfort and thermal sensations and
associated physiological responses at various ambient temperatures, En-
vironmental research 1 (1967) 1–20.
 G. A. Gaesser, G. A. Brooks, Muscular eﬃciency during steady-rate ex-
ercise: eﬀects of speed and work rate, Journal of applied physiology 38
 G. Havenith, K. Kuklane, J. Fan, S. Hodder, Y. Ouzzahra, K. Lundgren,
Y. Au, D. L. Loveday, A database of static clothing thermal insulation
and vapor permeability values of non-western ensembles for use in ashrae
standard 55, iso 7730, and iso 9920 ch-15-018 (rp-1504) (2015).
 J. M. Johnson, D. L. Kellogg Jr, Thermoregulatory and thermal control
in the human cutaneous circulation, Front Biosci (Schol Ed) 2 (2010)
 H. Zhang, A. Hedge, Laptop heat and models of user thermal discomfort,
in: Proceedings of the Human Factors and Ergonomics Society Annual
Meeting, volume 58, SAGE Publications Sage CA: Los Angeles, CA, pp.
 S. Karjalainen, Thermal comfort and gender: a literature review, Indoor
air 22 (2012) 96–109.
 H.-W. Huang, W.-C. Wang, C.-C. K. Lin, Inﬂuence of age on thermal
thresholds, thermal pain thresholds, and reaction time, Journal of Clinical
Neuroscience 17 (2010) 722–726.
 G. Havenith, I. Holm´
er, K. Parsons, Personal factors in thermal comfort
assessment: clothing properties and metabolic heat production, Energy
and buildings 34 (2002) 581–591.
 S. M. Frank, S. N. Raja, C. F. Bulcao, D. S. Goldstein, Relative contri-
bution of core and cutaneous temperatures to thermal comfort and auto-
nomic responses in humans, Journal of Applied physiology 86 (1999)
 J. A. Boulant, Role of the preoptic-anterior hypothalamus in thermoreg-
ulation and fever, Clinical infectious diseases 31 (2000) S157–S161.
 M. Cabanac, Physiological role of pleasure, Science 173 (1971) 1103–
 G. C. Brainard, J. P. Haniﬁn, J. M. Greeson, B. Byrne, G. Glickman,
E. Gerner, M. D. Rollag, Action spectrum for melatonin regulation in
humans: evidence for a novel circadian photoreceptor, Journal of Neuro-
science 21 (2001) 6405–6412.
 R. Perez, P. Ineichen, R. Seals, J. Michalsky, R. Stewart, Modeling day-
light availability and irradiance components from direct and global irra-
diance, Solar energy 44 (1990) 271–289.
 P. Leather, M. Pyrgas, D. Beale, C. Lawrence, Windows in the workplace:
Sunlight, view, and occupational stress, Environment and behavior 30
 Q. Dai, L. Hao, Y. Lin, Z. Cui, Spectral optimization simulation of white
light based on the photopic eye-sensitivity curve, Journal of Applied
Physics 119 (2016) 053103.
 A. I. Slater, P. R. Boyce, Illuminance uniformity on desks: Where is the
limit?, Lighting research & technology 22 (1990) 165–174.
 R. A. Baron, M. S. Rea, S. G. Daniels, Eﬀects of indoor lighting (illu-
minance and spectral distribution) on the performance of cognitive tasks
and interpersonal behaviors: The potential mediating role of positive af-
fect, Motivation and emotion 16 (1992) 1–33.
 A. J. Wilkins, I. Nimmo-Smith, A. I. Slater, L. Bedocs, Fluorescent light-
ing, headaches and eyestrain, Lighting Research & Technology 21 (1989)
 A. Main, A. Dowson, M. Gross, Photophobia and phonophobia in mi-
graineurs between attacks, Headache: The Journal of Head and Face Pain
37 (1997) 492–495.
 J. Yin, S. Zhu, P. MacNaughton, J. G. Allen, J. D. Spengler, Physiological
and cognitive performance of exposure to biophilic indoor environment,
Building and Environment 132 (2018) 255–262.
 R. G. Hopkinson, Glare from daylighting in buildings, Applied er-
gonomics 3 (1972) 206–215.
 M. Pierrette, E. Parizet, P. Chevret, J. Chatillon, Noise eﬀect on com-
fort in open-space oﬃces: development of an assessment questionnaire,
Ergonomics 58 (2015) 96–106.
 R. Job, Community response to noise: A review of factors inﬂuencing
the relationship between noise exposure and reaction, The Journal of the
Acoustical Society of America 83 (1988) 991–1001.
 J. Kim, R. De Dear, Workspace satisfaction: The privacy-communication
trade-oﬀin open-plan oﬃces, Journal of Environmental Psychology 36
 D. Templeton, D. Saunders, Acoustic design, Elsevier, 2014.
 S. Y. Lee, J. Brand, Can personal control over the physical environment
ease distractions in oﬃce workplaces?, Ergonomics 53 (2010) 324–335.
 A. Kjellberg, B. Sk¨
om, Noise annoyance during the performance of
diﬀerent nonauditory tasks, Perceptual and motor skills 73 (1991) 39–49.
 S. P. Banbury, D. C. Berry, Oﬃce noise and employee concentration:
Identifying causes of disruption and potential improvements, Ergonomics
48 (2005) 25–37.
 T. Cheung, S. Schiavon, T. Parkinson, P. Li, G. Brager, Analysis of
the accuracy on pmv–ppd model using the ashrae global thermal comfort
database ii, Building and Environment (2019).
 A. A. Stone, S. Shiﬀman, A. A. Atienza, L. Nebeling, A. Stone, S. Shiﬀ-
man, A. Atienza, L. Nebeling, Historical roots and rationale of ecologi-
cal momentary assessment (ema), The science of real-time data capture:
Self-reports in health research (2007) 3–10.
 S. Intille, C. Haynes, D. Maniar, A. Ponnada, J. Manjourides, µema:
Microinteraction-based ecological momentary assessment (ema) using a
smartwatch, in: Proceedings of the 2016 ACM International Joint Con-
ference on Pervasive and Ubiquitous Computing, ACM, pp. 1124–1128.
 D. Wang, M. T. Amin, S. Li, T. Abdelzaher, L. Kaplan, S. Gu, C. Pan,
H. Liu, C. C. Aggarwal, R. Ganti, X. Wang, P. Mohapatra, B. Szymanski,
H. Le, Using humans as sensors: an estimation-theoretic perspective, in:
Proceedings of the 13th international symposium on Information process-
ing in sensor networks, IPSN ’14, IEEE Press, 2014, pp. 35–46.
 M. Avvenuti, M. G. C. A. Cimino, S. Cresci, A. Marchetti, M. Tesconi, A
framework for detecting unfolding emergencies using humans as sensors,
Springerplus 5 (2016) 43.
 M. Vielberth, F. Menges, G. Pernul, Human-as-a-security-sensor for har-
vesting threat intelligence, Cybersecurity 2 (2019) 23.
 D. Heinzerling, S. Schiavon, T. Webster, E. Arens, Indoor environmental
quality assessment models: A literature review and a proposed weighting
and classiﬁcation scheme 70 (2013) 210–222.
 M. Ncube, S. Riﬀat, Developing an indoor environment quality tool for
assessment of mechanically ventilated oﬃce buildings in the UK - A pre-
liminary study, Building and Environment 53 (2012) 26–33.
 L. T. Wong, K. W. Mui, P. S. Hui, A multivariate-logistic model for
acceptance of indoor environmental quality (IEQ) in oﬃces, Building
and Environment 43 (2008) 1–6.
 A. C. Lai, K. W. Mui, L. T. Wong, L. Y. Law, An evaluation model for
indoor environmental quality (IEQ) acceptance in residential buildings,
Energy and Buildings 41 (2009) 930–936.
 R. Cohen, M. Standeven, B. Bordass, A. Leaman, Assessing building
performance in use 1: The Probe process, Building Research and Infor-
mation 29 (2001) 85–102.
 T. Webster, E. Arens, G. Anwar, J. Bonnell, F. Bauman, C. Brown, Ufad
commissioning cart: Design speciﬁcations and operating manual (2007).
 M. Jin, S. Liu, S. Schiavon, C. Spanos, Automated mobile sensing:
Towards high-granularity agile indoor environmental quality monitoring,
Building and Environment 127 (2018) 268–276.
 S. R. Porter, M. E. Whitcomb, W. H. Weitzer, Multiple surveys of stu-
dents and survey fatigue, New Directions for Institutional Research 2004
 S. Liu, S. Schiavon, H. P. Das, M. Jin, C. J. Spanos, Personal ther-
mal comfort models with wearable sensors, Build. Environ. 162 (2019)
 A. Aryal, B. Becerik-Gerber, A comparative study of predicting indi-
vidual thermal sensation and satisfaction using wrist-worn temperature
sensor, thermal camera and ambient temperature sensor, Build. Environ.
160 (2019) 106223.
 A. K. Clear, S. Mitchell Finnigan, P. Olivier, R. Comber, ThermoKiosk:
Investigating Roles for Digital Surveys of Thermal Experience in Work-
place Comfort Management, Proc. of CHI (2018) 1–12.
 L. Engelen, F. Held, Understanding the oﬃce: Using ecological momen-
tary assessment to measure activities, posture, social interactions, mood,
and work performance at the workplace, Buildings 9 (2019) 54.
 B. Monnot, E. Wilhelm, G. Piliouras, Y. Zhou, D. Dahlmeier, H. Y. Lu,
W. Jin, Inferring activities and optimal trips: Lessons from singapore’s
national science experiment, in: Complex Systems Design & Manage-
ment Asia, Springer International Publishing, 2016, pp. 247–264.
 E. Wilhelm, Y. Zhou, N. Zhang, J. Kee, G. Loh, N. Tippenhauer, Sensg:
Large-scale deployment of wearable sensors for trip and transport mode
logging, Technical Report, 2016.
 F. Benita, G. Bansal, B. Tunc¸er, Public spaces and happiness: Evidence
from a large-scale ﬁeld experiment, Health Place 56 (2019) 9–18.
 V. K. Ojha, D. Griego, S. Kuliga, M. Bielik, P. Buˇ
s, C. Schaeben,
L. Treyer, M. Standfest, S. Schneider, R. K¨
onig, D. Donath, G. Schmitt,
Machine learning approaches to understand the inﬂuence of urban envi-
ronments on human’s physiological response, Inf. Sci. 474 (2019) 154–
 M. S. Rahaman, J. Liono, Y. Ren, J. Chan, S. Kudo, T. Rawling, F. D.
Salim, An Ambient-Physical system to infer concentration in open-plan
workplace, IEEE Internet of Things Journal (2020) 1–1.
 T. Sood, P. Janssen, C. Miller, Spacematch: Using environmental prefer-
ences to match occupants to suitable activity-based workspaces, Frontiers
in Built Environment 6 (2020) 113.
 T. Sood, M. Quintana, P. Jayathissa, M. AbdelRahman, C. Miller, The
SDE4 learning trail: Crowdsourcing occupant comfort feedback at a net-
zero energy building, J. Phys. Conf. Ser. 1343 (2019) 012141.
 P. Jayathissa, M. Quintana, T. Sood, N. Narzarian, C. Miller, Is your
clock-face cozie? a smartwatch methodology for the in-situ collection
of occupant comfort data, CISBAT - Climate Resilient Cities - Energy
Eﬃciency and Renewables in the Digital Era (2019).
 M. M. Abdelrahman, P. Jayathissa, C. Miller, YAK: An Indoor Position-
ing App for Spatial-Temporal Indoor Environmental Quality Research
 J. Kim, Y. Zhou, S. Schiavon, P. Raftery, G. Brager, Personal comfort
models: predicting individuals’ thermal preference using occupant heat-
ing and cooling behavior and machine learning, Building and Environ-
ment 129 (2018) 96–106.
 M. Luo, J. Xie, Y. Yan, Z. Ke, P. Yu, Z. Wang, J. Zhang, Comparing ma-
chine learning algorithms in predicting thermal sensation using ASHRAE
Comfort Database II, Energy and Buildings 210 (2020) 109776.
 J. Kim, S. Schiavon, G. Brager, Personal comfort models–a new paradigm
in thermal comfort for occupant-centric environmental control, Building
and Environment 132 (2018) 114–124.
 D. Enescu, A review of thermal comfort models and indicators for indoor
environments, Renewable and Sustainable Energy Reviews 79 (2017)
 L. Barrios, W. Kleiminger, The Comfstat - Automatically sensing thermal
comfort for smart thermostats, 2017 IEEE International Conference on
Pervasive Computing and Communications, PerCom 2017 (2017) 257–
 J. Y. Park, Z. Nagy, Comprehensive analysis of the relationship between
thermal comfort and building control research - A data-driven literature
review, Renewable and Sustainable Energy Reviews 82 (2018) 2664–
 H. Zhang, E. Arens, Y. Zhai, A review of the corrective power of per-
sonal comfort systems in non-neutral ambient environments, Building
and Environment 91 (2015) 15–41.
 J. Y. Park, M. M. Ouf, B. Gunay, Y. Peng, W. O’Brien, M. B. Kjærgaard,
Z. Nagy, A critical review of ﬁeld implementations of occupant-centric
building controls, Build. Environ. 165 (2019) 106351.
 J. Y. Park, T. Dougherty, H. Fritz, Z. Nagy, LightLearn: An adaptive and
occupant centered controller for lighting based on reinforcement learning,
Build. Environ. 147 (2019) 397–414.
 W. O’Brien, A. Wagner, M. Schweiker, A. Mahdavi, J. Day, M. B. Kjær-
gaard, S. Carlucci, B. Dong, F. Tahmasebi, D. Yan, T. Hong, H. B. Gunay,
Z. Nagy, C. Miller, C. Berger, Introducing IEA EBC annex 79: Key chal-
lenges and opportunities in the ﬁeld of occupant-centric building design
and operation, Build. Environ. 178 (2020) 106738.
 C. Duarte Roa, S. Schiavon, T. Parkinson, Targeted occupant surveys : A
novel method to eﬀectively relate occupant feedback with environmental
conditions, Preprint (2020).
 A. Lipczynska, S. Schiavon, L. T. Graham, Thermal comfort and self-
reported productivity in an oﬃce with ceiling fans in the tropics, Building
and Environment 135 (2018) 202–212.
 M. Quintana, C. Miller, Poster Abstract: Towards Class-Balancing Hu-
man Comfort Datasets with GANs, in: BuildSys ’19 Proceedings of the
6th ACM International Conference on Systems for Energy-Eﬃcient Built
Environments, New York, NY, USA.
 M. M. Abdelrahman, A. Chong, C. Miller, Build2Vec: Building Repre-
sentation in Vector Space, in: SimAUD 2020, Online, pp. 101–104.