Next Article in Journal
Sustainable Performance of a Modular Building System Made of Built-Up Cold-Formed Steel Beams
Next Article in Special Issue
New Approaches to Modelling Occupant Comfort
Previous Article in Journal
Predicting Indoor Temperature Distribution Based on Contribution Ratio of Indoor Climate (CRI) and Mobile Sensors
Previous Article in Special Issue
Determination of Thermal Comfort Zones through Comparative Analysis between Different Characterization Methods of Thermally Dissatisfied People
 
 
Article
Peer-Review Record

Monitoring and Predicting Occupant’s Sleep Quality by Using Wearable Device OURA Ring and Smart Building Sensors Data (Living Laboratory Case Study)

Buildings 2021, 11(10), 459; https://doi.org/10.3390/buildings11100459
by Elena Malakhatka 1,*, Anas Al Rahis 2, Osman Osman 2 and Per Lundqvist 1
Reviewer 1: Anonymous
Reviewer 2: Anonymous
Reviewer 3: Anonymous
Buildings 2021, 11(10), 459; https://doi.org/10.3390/buildings11100459
Submission received: 1 August 2021 / Revised: 27 September 2021 / Accepted: 27 September 2021 / Published: 7 October 2021
(This article belongs to the Special Issue New Approaches to Modelling Occupant Comfort)

Round 1

Reviewer 1 Report

The topic of the research is very interesting. However, the paper is verbose and should be reorganized.

  1. Introduction

More comprehensive review is needed on the ICT application on built environment.

 

  1. Research goals and objectives

It is a bit verbose and should be shortened.

 

  1. Background

Line 174, “Ta” should be “TA”

In fact this part can be moved to the introduction section and be more concise.

 

  1. Methodology

This section also need to be more concise and the method used for analysis needs to be clear.

 

  1. Implementation

What are the percentages for training and validation? And how about the results?

 

  1. Results and Analysis

It should focus on the results and analysis. The explanation on each item should be moved to previous section.

 

  1. Conclusion

 

Please present only the major findings.

 

 

Reference

Please follow the submission guideline on the format of the reference

  1. Introduction

More comprehensive review is needed on the ICT application on built environment.

 

  1. Research goals and objectives

It is a bit verbose and should be shortened.

 

  1. Background

Line 174, “Ta” should be “TA”

In fact this part can be moved to the introduction section and be more concise.

 

  1. Methodology

This section also need to be more concise and the method used for analysis needs to be clear.

 

  1. Implementation

What are the percentages for training and validation? And how about the results?

 

  1. Results and Analysis

It should focus on the results and analysis. The explanation on each item should be moved to previous section.

 

  1. Conclusion

 

Please present only the major findings.

 

 

Reference

Please follow the submission guideline on the format of the reference

Author Response

  • Introduction
More comprehensive review is needed on the ICT application in the built environment. 

Text added (46-82):

Nowadays, the importance of maintaining comfortable indoor thermal environments not only at daytime, but also at night-time in spaces such as bedrooms of residences, guest rooms in hotels and wards in hospitals, is growing significantly. Current thermal comfort theories and standards are mainly concerned with people in waking state. However, many problems regarding the thermal environment are found within a few studies [5,6,7], pushing out the need to investigate the thermal environment and thermal comfort for sleeping people. Many factors, such as health states, emotional states, bedding conditions, and thermal environments affect sleep quality, with thermal environment being one of the most important factors [8,9]. Some Physiological parameters such as skin temperature and heart rate variability are found to be related to thermal comfort in waking people [10, 11]. Measurements of these indicators concurrently along with sleep to monitor human thermal comfort state are needed in future research. An increasing proportion of the population is tracking their health using wearable technology, with sleep being a prime parameter of interest. Part of the motivation behind tracking sleep is due to the recognition of sleep as an essential aspect of physical health (e.g., weight control, immune health, blood-sugar regulation) [12, 13], as well as of mental and cognitive brain health (e.g., learning, memory, concentration, productivity mood, anxiety, depression) [14, 15]. As such, wearable devices offer the promise of a daily feedback tool guiding personal health insights and, thus, behavioral change that could contribute to a longer healthspan and lifespan. However, for wearable devices to become broadly adopted, the correct form-factor becomes key to maintain adherence [16,17]. This is similarly true of the utility of the type and accuracy of sensory data that such devices provide to the user, and whether that data is real-world meaningful to them [18,19].
In [20] correctly highlighted, to research an individual level indoor comfort is required, three primary categories of variables are 1) environmental information, 2)  occupant behavior,  and 3)  physiological signals. This makes it necessary to connect data from both: wearable devices and built environment sensors. Recent attempts [21,22] applied commercial wearable sensors together with environmental sensors (e.g., temperature, air speed) to predict the comfort of each individual occupant highlighted few important limitations in such studies: subjects involved in the studies were restrained in a climate-controlled laboratory environment for a short period of time, usually in hours [23,24,24], the feasibility and accuracy of personal thermal comfort models developed under real-life conditions are still unclear due to the very complex end users’ behaviors. From literature review we can see that the models developed directly from lab data [25, 26] usually have higher prediction power as compared to those from the real environment [27, 28], resulting in ~90% vs ~70%. Thus, the first problem we are trying to approach in our explorative case study is conduct the study in the real-life context environment. 

  • Research goals and objectives
It is a bit verbose and should be shortened.

IMPROVED
  • Background
Line 174, “Ta” should be “TA”

In fact this part can be moved to the introduction section and be more concise.

IMPROVED
  • Methodology
This section also needs to be more concise and the method used for analysis needs to be clear.

IMPROVED

The methodology of this study involved several steps: (1) relevant literature screening and problems identification, (2) the context analysis of living laboratiry infrastructure and wearable device usability (3) collection of wearable device data with regards to physical activity and sleep patterns (4) data storing and processing, (4) data modeling, and (4) performance evaluation. The research process is represented at Figure 3 below. 
  • Implementation
What are the percentages for training and validation? And how about the results? 

The validation set was 10% of the dataset, and the training was 90%. The overall entries were 141. 
  • Results and Analysis
It should focus on the results and analysis. The explanation on each item should be moved to the previous section.

IMPROVED
  • Conclusion
Please present only the major findings.

IMPROVED



Reviewer 2 Report

In this paper, the Authors presented an explorative study aimed to assess the sleep quality at KTH Live-in-Lab using the OURA ring and smart sensors. They collected data from 3 tenants at KTH-Live-in-Lab, applied a Total Data Quality Management approach and discussed their dataset. Then, they developed an ANN model for the prediction of tenants' sleep quality. 

I found this topic very interesting, as well as some Authors' considerations, weven if this is a preliminary study. I recommend the Authors to modify their manuscript (1) improving compactness and readability, and, if feasible, (2) discussing more in details the results, in particular those regarding the collected data and the proposed ANN model.

Other aspects:
-Although to my understanding there are probably not many alternatives in the market, I recommend the Authors to add a detailed technical motivation regarding their choice to use OURA.
-The Authors should clarify how the three subjects involved in the experiments were selected and which are the different features of their dwellings (if any).
-Trivial motivations should be removed and substituted with technical reasons (e.g., line 288 "Choosing Matlab was because we had some experience with it, and it was readily availa-288 ble to us")
-Some format aspects are inconsistent with the journal template (e.g., figure "3.3.2", the equation in line 566).
-The quality of the figures has to be improved. Figures 6 and 7 are difficult to read: I recommend the Authors to switch x-axis and y-axis and to adopt the same ranges in all charts to ensure an easy comparison.
-The Authors should use "°C" or "Celsius degrees" instead of "degrees" (line 490).

Author Response

(1) improving compactness and readability, and, if feasible

IMPROVED

(2) discussing more in detail, in particular those regarding the collected data and the proposed ANN model.

IMPROVED

Other aspects:

(3) Although to my understanding there are probably not many alternatives in the market, I recommend the Authors to add a detailed technical motivation regarding their choice to use OURA.

Text added:

Nowadays, the importance of maintaining comfortable indoor thermal environments not only at daytime, but also at night-time in spaces such as bedrooms of residences, guest rooms in hotels and wards in hospitals, is growing significantly. Current thermal comfort theories and standards are mainly concerned with people in waking state. However, many problems regarding the thermal environment are found within a few studies [5,6,7], pushing out the need to investigate the thermal environment and thermal comfort for sleeping people. Many factors, such as health states, emotional states, bedding conditions, and thermal environments affect sleep quality, with thermal environment being one of the most important factors [8,9]. Some Physiological parameters such as skin temperature and heart rate variability are found to be related to thermal comfort in waking people [10, 11]. Measurements of these indicators concurrently along with sleep to monitor human thermal comfort state are needed in future research. An increasing proportion of the population is tracking their health using wearable technology, with sleep being a prime parameter of interest. Part of the motivation behind tracking sleep is due to the recognition of sleep as an essential aspect of physical health (e.g., weight control, immune health, blood-sugar regulation) [12, 13], as well as of mental and cognitive brain health (e.g., learning, memory, concentration, productivity mood, anxiety, depression) [14, 15]. As such, wearable devices offer the promise of a daily feedback tool guiding personal health insights and, thus, behavioral change that could contribute to a longer healthspan and lifespan. However, for wearable devices to become broadly adopted, the correct form-factor becomes key to maintain adherence [16,17]. This is similarly true of the utility of the type and accuracy of sensory data that such devices provide to the user, and whether that data is real-world meaningful to them [18,19].
In [20] correctly highlighted, to research an individual level indoor comfort is required, three primary categories of variables are 1) environmental information, 2)  occupant behavior,  and 3)  physiological signals. This makes it necessary to connect data from both: wearable devices and built environment sensors. Recent attempts [21,22] applied commercial wearable sensors together with environmental sensors (e.g., temperature, air speed) to predict the comfort of each individual occupant highlighted few important limitations in such studies: subjects involved in the studies were restrained in a climate-controlled laboratory environment for a short period of time, usually in hours [23,24,24], the feasibility and accuracy of personal thermal comfort models developed under real-life conditions are still unclear due to the very complex end users’ behaviors. From literature review we can see that the models developed directly from lab data [25, 26] usually have higher prediction power as compared to those from the real environment [27, 28], resulting in ~90% vs ~70%. Thus, the first problem we are trying to approach in our explorative case study is conduct the study in the real-life context environment. 
Several studies [27, 28] also suggest there exists a high potential for developing new models to predict human thermal sensation using artificial neural networks and additional factors that can be individually, unobtrusively, and dynamically measured using wearables. A number of additional studies have been conducted to investigate the use of wearable devices, wireless sensors, and mobile applications for identifying thermal comfort of building occupants and their location over time. Despite existing off the shelf wearables providing some sleep indicators, such as the sleep duration, the number of awakes or the time to fall asleep, the specialized scientific sleep literature uses other indicators that feature sleep and sleep behaviour in a more precise way [29]. For example, Heart Rate [30], respiration [31] or temperature [32] are very well correlated to sleep and can be collected by off the shelf wearables. 
The current popularity of wearables for tracking physical activity and sleep, including actigraphy devices, can foster the development of new advanced data analytics, and evaluate the feasibility of predicting sleep quality. However, availability of sensors in wearables does not necessarily mean that the corresponding data can be collected from them, because quite frequently the wearable vendors con- strain or limit the access to raw data. For example, in some of the Fitbit devices accelerometer and altimeter raw data is not available for developers, just for the vendor to calculate indicators of the start and end of the sleep periods. In [33] were identified other issues to collect data from off the shelf wearables: battery duration, differences on data models, duration of tokens to authorize the collection of data, etc. In addition to raw sensor data, wearable vendors also provide more elaborated information. 

(4) Trivial motivations should be removed and substituted with technical reasons (e.g., line 288 "Choosing Matlab was because we had some experience with it, and it was readily availa ble to us")

IMPROVED

(6) Some format aspects are inconsistent with the journal template (e.g., figure "3.3.2", the equation in line 566).

IMPROVED

(7) The quality of the figures has to be improved. Figures 6 and 7 are difficult to read: I recommend the Authors to switch x-axis and y-axis and to adopt the same ranges in all charts to ensure an easy comparison.

IMPROVED

(8) The Authors should use "°C" or "Celsius degrees" instead of "degrees" (line 490).

IMPROVED

 

 

Reviewer 3 Report

This paper reports an interesting research. There are a few comments as below:
- It is necessary to re-write the abstract, as the current version didn't present the main method and results etc, while it reports many unnecessary potential application.
- It is not clear what is OURA ring for many readers. It is better to explain it when it firstly appears.
- The overall paper structure is a bit confusing. Suggest to integrate section 1 and 3, while then lead to the conclusion of research motivations, and goals/objectives.
- And why particularly using ANN as one of objectives? What about the other methods? Should there be an extensive literature review before it, to propose the research question?
- Research motivation is not well generated in section 3. It is not clear why the authors did this research. Is it only because KTH has such facility and resource?
- It is not clear why only choose OURA ring, what about the other types sensors?
- Method is not clear either, for instance section 4.3. It lacks of a clear illustration of research methodology.
- In general, I think the overall paper mentioned too many KTH related resources, where it is not appropriate for a scientific paper. The authors can acknowledge this resource in the end of the paper, but in the content, it should be purely scientific.

Author Response

(1)  It is necessary to re-write the abstract, as the current version didn't present the main method and results etc, while it reports many unnecessary potential applications.

Today’s commercially-off-the-shelf (COST) wearable devices can unobtrusively capture a number of important parameters that may be used to measure indoor comfort of building occupants, including ambient air temperature, relative humidity, skin temperature, perspiration rate, and heart rate. These data could be used not only for improving personal wellbeing, but for adjusting a better indoor environment condition. In this study we have focused specifically on the sleeping phase. The main purpose of this work was to use the data from wearable devices and smart me-ters to improve sleep quality of the residents living at KTH Live-in-Lab. The wearable device we used was the OURA ring which specializes in sleep monitoring. In general, the data quality showed good potential for the modelling phase. For the modelling phase, we had to make some choices, such as the programming language and the AI algorithm that is the best fit for our project. Nevertheless, the potentials that this type of case studies might bring in the nearest future is sig-nificant. First, to make a personal bio data related studies more transparent. Secondly, the tenants will have a better sleep quality in their everyday life if they have an accurate prediction of the sleeping scores and ability to adjust the built environment. Also, using knowledge about end users can help to the building owners design better building systems and services related to the end-user’s wellbeing. 

(2)  It is not clear what the OURA ring is for many readers. It is better to explain it when it first appears.

Wearable technology (Crabtree and Rhodes 1998; K Tehrani 2014) refers to electronic devices and systems incorporated in some part of our body or clothes. These systems can be used for different purposes, particularly to monitor physiological and environmental data.

The new wave of fitness trackers is growing [XX]. New multisensory devices are able to collect a broad range of users’ biosignals. The user-friendly consumer products may provide the opportunity for sleep researchers to obtain a more detailed overview of sleep and physiological changes during sleep. However, validation of these commercial devices both in and outside of the laboratory is first required.

Standard actigraphy is a well-established measure of an individual’s sleep-wake patterns (Sadeh, 2011). Although not measuring brain sleep states, actigraphy has the advantage of being relatively low-cost, nonintrusive, and easy to use (Ancoli-Israel et al., 2003), which allows for the tracking of individuals’ sleep patterns over prolonged periods of time in non laboratory settings. Compared to PSG, actigraphy has high sensitivity (ability to detect sleep) although specificity (ability to detect wakefulness) is lower (Marino et al., 2013; Sadeh, 2011), with a wide range of accuracy, depending on the amount of nighttime wakefulness (Paquet, Kawinska, & Carrier, 2007), the algorithms used, and the particular population studied (Van de Water, Holmes, & Hurley, 2011). 

A novel, multisensory device that claims to be able to distinguish sleep stages, including REM sleep, has recently come on the market. The Oura ring (Figure X) is a scientifically validated, wearable sleep tracker which objectively estimates go-to-bed time and sleep stages based on nocturnal PPG (250 Hz), 3-D accelerometer (50 Hz) and min by-min skin temperature [5]. The associated Oura App also displays an optimal bedtime window for those users that are considered very good sleepers according to the Oura Sleep Score metrics.

The ŌURA ring detects pulse rate, variation in interbeat intervals (IBIs) and pulse amplitude from the finger optical pulse waveform. The ring also measures motion and body temperature. Ōuraring (Oulu, Finland) claims to use these physiological signals (a combination of motion, heart rate, heart rate variability, and pulse wave variability amplitude) in combination with sophisticated machine learning-based methods to calculate deep (PSG N3), light (PSG N1 + N2) and rapid-eye-movement (REM) sleep in addition to sleep–wake states. [XX]

We selected sensors for this study based on three criteria: (1) accuracy, (2) raw data access for research support, and (3) convenience to wear 24/7, especially while sleeping.  

(3) The overall paper structure is a bit confusing. Suggest to integrate sections 1 and 3, which then lead to the conclusion of research motivations, and goals/objectives.

IMPROVED

(4) Research motivation is not well generated in section 3. It is not clear why the authors did this research. Is it only because KTH has such facilities and resources?

Nowadays, the importance of maintaining comfortable indoor thermal environments not only at daytime, but also at night-time in spaces such as bedrooms of residences, guest rooms in hotels and wards in hospitals, is growing significantly. Current thermal comfort theories and standards are mainly concerned with people in waking state. However, many problems regarding the thermal environment are found within a few studies [5,6,7], pushing out the need to investigate the thermal environment and thermal comfort for sleeping people. Many factors, such as health states, emotional states, bedding conditions, and thermal environments affect sleep quality, with thermal environment being one of the most important factors [8,9]. Some Physiological parameters such as skin temperature and heart rate variability are found to be related to thermal comfort in waking people [10, 11]. Measurements of these indicators concurrently along with sleep to monitor human thermal comfort state are needed in future research. An increasing proportion of the population is tracking their health using wearable technology, with sleep being a prime parameter of interest. Part of the motivation behind tracking sleep is due to the recognition of sleep as an essential aspect of physical health (e.g., weight control, immune health, blood-sugar regulation) [12, 13], as well as of mental and cognitive brain health (e.g., learning, memory, concentration, productivity mood, anxiety, depression) [14, 15]. As such, wearable devices offer the promise of a daily feedback tool guiding personal health insights and, thus, behavioral change that could contribute to a longer healthspan and lifespan. However, for wearable devices to become broadly adopted, the correct form-factor becomes key to maintain adherence [16,17]. This is similarly true of the utility of the type and accuracy of sensory data that such devices provide to the user, and whether that data is real-world meaningful to them [18,19].

In [20] correctly highlighted, to research an individual level indoor comfort is required, three primary categories of variables are 1) environmental information, 2)  occupant behavior,  and 3)  physiological signals. This makes it necessary to connect data from both: wearable devices and built environment sensors. Recent attempts [21,22] applied commercial wearable sensors together with environmental sensors (e.g., temperature, air speed) to predict the comfort of each individual occupant highlighted few important limitations in such studies: subjects involved in the studies were restrained in a climate-controlled laboratory environment for a short period of time, usually in hours [23,24,24], the feasibility and accuracy of personal thermal comfort models developed under real-life conditions are still unclear due to the very complex end users’ behaviors. From literature review we can see that the models developed directly from lab data [25, 26] usually have higher prediction power as compared to those from the real environment [27, 28], resulting in ~90% vs ~70%. Thus, the first problem we are trying to approach in our explorative case study is conduct the study in the real-life context environment.

Several studies [27, 28] also suggest there exists a high potential for developing new models to predict human thermal sensation using artificial neural networks and additional factors that can be individually, unobtrusively, and dynamically measured using wearables. A number of additional studies have been conducted to investigate the use of wearable devices, wireless sensors, and mobile applications for identifying thermal comfort of building occupants and their location over time. Despite existing off the shelf wearables providing some sleep indicators, such as the sleep duration, the number of awakes or the time to fall asleep, the specialized scientific sleep literature uses other indicators that feature sleep and sleep behaviour in a more precise way [29]. For example, Heart Rate [30], respiration [31] or temperature [32] are very well correlated to sleep and can be collected by off the shelf wearables.

The current popularity of wearables for tracking physical activity and sleep, including actigraphy devices, can foster the development of new advanced data analytics, and evaluate the feasibility of predicting sleep quality. However, availability of sensors in wearables does not necessarily mean that the corresponding data can be collected from them, because quite frequently the wearable vendors con- strain or limit the access to raw data. For example, in some of the Fitbit devices accelerometer and altimeter raw data is not available for developers, just for the vendor to calculate indicators of the start and end of the sleep periods. In [33] were identified other issues to collect data from off the shelf wearables: battery duration, differences on data models, duration of tokens to authorize the collection of data, etc. In addition to raw sensor data, wearable vendors also provide more elaborated information.

Focusing on sleep, there are some indicators provided by vendors, currently. The more common ones are obtained from accelerometer raw data values using actigraphy techniques [34]. Standard actigraphy is a well-established measure of an individual’s sleep-wake patterns [35]. Although not measuring brain sleep states, actigraphy has the advantage of being relatively low-cost, nonintrusive, and easy to use [34], which allows for the tracking of individuals’ sleep patterns over prolonged periods of time in non laboratory settings. The wearable raw accelerometer data is collected and transferred to a smartphone that process it to estimate the time slept by a certain user [36,37,38]. By the way, the use of actigraphy techniques and accelerometer data in smartphones is not new, apps such as “Sleep as Android” [39] already provided this functionality using the smartphone accelerometer data directly. Instead, wearables are directly wear by the person and as a result they may register user movements in a better way. Main wearable vendors also use actigraphy techniques and algorithms to provide a sleep efficiency indicator.

 

(5)  It is not clear why only chose the OURA ring, but what about the other types of sensors?

A novel, multisensory device that claims to be able to distinguish sleep stages, including REM sleep, has recently come on the market. The Oura ring is a scientifically validated, wearable sleep tracker which objectively estimates go-to-bed time and sleep stages based on nocturnal PPG (250 Hz), 3-D accelerometer (50 Hz) and min by-min skin temperature [40]. The associated Oura App also displays an optimal bedtime window for those users that are considered very good sleepers according to the Oura Sleep Score metrics.

(6) Method is not clear either, for instance section 4.3. It lacks a clear illustration of research methodology.

The methodology of this study involved several steps: (1) the collection of wearable data with regards to physical activity and sleep patterns, (2) data processing and representation, (3) data modeling, and (4) performance evaluation. The following subsections explain each of these steps.

(7) In general, I think the overall paper mentioned too many KTH related resources, where it is not appropriate for a scientific paper. The authors can acknowledge this resource at the end of the paper, but in the content, it should be purely scientific. - 

IMPROVED

 

Round 2

Reviewer 1 Report

The conclusion section is still too long and the quality of figures can be imroved. The position of the caption for Fig. 5 is not right.

Author Response

All suggestions were implemented

Reviewer 2 Report

I consider the revised version of this manuscript largely improved. Some minor aspects to fix are reported below.

Minor typos and comments:
- line 185: "physiccal" should be "physical"
- line 221: please, add the correct reference instead of "[XX]"
- line 313: the caption of figure 5 is not under the corresponding figure
- figures 9-10: quality and readability of these figures should be improved. If feasible, I suggest also to adopt the same range for the horizontal axis.
- figure 12: the caption of the horizontal axis should be just "day number".
- reference list requires corrections.

Author Response

All suggestions were implemented

Reviewer 3 Report

The authors have responded well. The paper can be accepted.

Author Response

All suggestions were implemented

Back to TopTop