As a guest user you are not logged in or recognized by your IP address. You have
access to the Front Matter, Abstracts, Author Index, Subject Index and the full
text of Open Access publications.
Smartphones offer new opportunities to monitor health-related behaviours in the real world. This allows researchers to go beyond traditional data collection methods, such as interviews and questionnaires that suffer from recall bias and low spatio-temporal resolution. In this study, we present an experiment that uses advanced analytical methods to identify daily activities relevant to assess social functioning, from geolocation data. Twenty-one healthy volunteers used a smartphone to continuously record their GPS location for up to 10 days. Participants also completed a diary to record their daily activities that was used as ground truth. Using clustering algorithms and semantic enrichment methods we were able to predict these activities from the GPS data with a precision of 0.75 (standard deviation [SD] 0.13) and a recall of 0.60 (SD 0.11). Although performed on a limited sample, our study shows potential for continuous, and passive geolocation-based monitoring of patient behaviour in mental health.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.