<?xml version='1.0' encoding='UTF-8'?><metadata xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:dcterms="http://purl.org/dc/terms/" xmlns="http://dublincore.org/documents/dcmi-terms/"><dcterms:title>Replication Data for: Automatic time in bed detection from hip-worn accelerometers for large epidemiological studies: The Tromsø Study</dcterms:title><dcterms:identifier>https://doi.org/10.18710/VP5DMU</dcterms:identifier><dcterms:creator>Henriksen, André</dcterms:creator><dcterms:creator>Weitz, Marc</dcterms:creator><dcterms:creator>Svartdal, Frode</dcterms:creator><dcterms:creator>Grimsgaard, Sameline</dcterms:creator><dcterms:creator>Hartvigsen, Gunnar</dcterms:creator><dcterms:creator>Hopstock, Laila Arnesdatter</dcterms:creator><dcterms:publisher>DataverseNO</dcterms:publisher><dcterms:issued>2024-10-31</dcterms:issued><dcterms:modified>2024-10-31T10:57:52Z</dcterms:modified><dcterms:description>&lt;p>&lt;b>Dataset description&lt;/b>&lt;/p>
&lt;p>16 participants wore an Actigraph w-GT3X on their right hip together with two consumer-based wearables, a Polar Vantage (Polar Electro Oy, Kempele, Finland) watch and an Oura (Oura Health Oy, Oulo, Finland]) ring. This data, as summarized in this repository, has been used to validate an algorithm to detect time in bed. For more information, see the publication's abstract below.&lt;/p>

&lt;p>This dataset consists of 20 files: "00_ReadMe.txt", "calibration_error.txt", "data_protection_impact_assessment.pdf", "wearable_data.csv" and 16 raw acceleration data files ("participant00.csv to participant15.csv").&lt;/p>
&lt;ul>
&lt;li>"00_ReadMe.txt": Contains a detailed information about the dataset&lt;/li>
&lt;li>"calibration_error.txt": Contains the estimated calibration errors, correction coefficients, and success information for the 16 raw acceleration data files.&lt;/li>
&lt;li>"data_protection_impact_assessment.pdf": sets out the legal and ethical grounds for open publication of the dataset.&lt;/li>
&lt;li>"wearable_data.csv": Contains daily sleep duration values from a Polar watch and the Oura ring for the 16 participants&lt;/li>
&lt;li>Each of the 16 raw acceleration data files (participantXX.csv") contains the triaxial raw acceleration data at a 100hz sampling frequency.&lt;/li>
&lt;/ul></dcterms:description><dcterms:description>&lt;p>&lt;b>Article abstract&lt;/b>&lt;/p>
&lt;p>Accelerometers are frequently used to assess physical activity in large epidemiological studies. They can monitor movement patterns and cycles over several days under free-living conditions and are usually either worn on the wrist or the hip. While wrist-worn accelerometers have been frequently used to additionally assess sleep and time in bed behavior, hip-worn accelerometers have been widely neglected for this task due to their primary focus on physical activity. Here, we present a new method with the objective to identify the time in bed to enable further analysis options for large-scale studies using hip-placement like time in bed or sedentary time analyses. We introduced new and accelerometer specific data augmentation methods, such as mimicking a wrongly worn accelerometer, additional noise, and random croping, to improve training and generalization performance. Subsequently, we trained a neural network model on a sample from the population-based Tromsø Study and evaluated it on two additional datasets. Our algorithm achieved an accuracy of 94% on the training data, 92% on unseen data from the same population and comparable results to consumer-wearable data obtained from a demographically different population. Generalization performance was overall good, however, we found that on a few particular days or participants, the trained model fundamentally over- or underestimated time in bed (e.g., predicted all or nothing as time in bed). Despite these limitations, we anticipate our approach to be a starting point for more sophisticated methods to identify time in bed or at some point even sleep from hip-worn acceleration signals. This can enable the re-use of already collected data, for example, for longitudinal analyses where sleep-related research questions only recently got into focus or sedentary time needs to be estimated in 24h wear protocols. &lt;/p></dcterms:description><dcterms:subject>Computer and Information Science</dcterms:subject><dcterms:subject>Medicine, Health and Life Sciences</dcterms:subject><dcterms:subject>ActiGraph</dcterms:subject><dcterms:subject>Accelerometry</dcterms:subject><dcterms:subject>Time in bed</dcterms:subject><dcterms:subject>Hip</dcterms:subject><dcterms:subject>Raw data</dcterms:subject><dcterms:subject>Consumer Wearables</dcterms:subject><dcterms:language>English</dcterms:language><dcterms:isReferencedBy>Weitz, M., Syed, S., Hopstock, L. A., Morseth, B., Henriksen, A., &amp; Horsch, A. (2024). Automatic time in bed detection from hip-worn accelerometers for large epidemiological studies: The Tromsø Study. Under review.</dcterms:isReferencedBy><dcterms:isReferencedBy>Henriksen, A., Svartdal, F., Grimsgaard, S., Hartvigsen, G., &amp; Hopstock, L. A. (2022). Polar Vantage and Oura Physical Activity and Sleep Trackers: Validation and Comparison Study. JMIR Formative Research, 6(5), e27248., doi, 10.2196/27248, https://doi.org/10.2196/27248</dcterms:isReferencedBy><dcterms:date>2024-10-31</dcterms:date><dcterms:contributor>Henriksen, André</dcterms:contributor><dcterms:dateSubmitted>2024-10-23</dcterms:dateSubmitted><dcterms:temporal>2019-02-20</dcterms:temporal><dcterms:temporal>2019-06-26</dcterms:temporal><dcterms:type>Observational data</dcterms:type><dcterms:spatial>Norway</dcterms:spatial><dcterms:license>CC0 1.0</dcterms:license></metadata>