@inproceedings{PryssJohnReichertetal.2019, author = {R{\"u}diger Pryss and Dennis John and Manfred Reichert and Burkhard Hoppenstedt and Lukas Schmid and Winfried Schlee and Myra Spiliopoulou and Johannes Schobel and Robin Kraft and Marc Schickler and Berthold Langguth and thomas Probst}, title = {Machine Learning Findings on Geospatial Data of Users from theTrackYourStress mHealth Crowdsensing Platform}, series = {2019 IEEE 20th International Conference on Information Reuse and Integration for Data Science (IRI)}, publisher = {IEEE}, address = {New York}, organization = {IEEE}, doi = {10.1109/IRI.2019.00061}, pages = {350 -- 355}, year = {2019}, abstract = {Mobile apps are increasingly utilized to gather data for various healthcare aspects. Furthermore, mobile apps are used to administer interventions (e.g., breathing exercises)to individuals. In this context, mobile crowdsensing constitutes a technology, which is used to gather valuable medical databased on the power of the crowd and the offered computationalcapabilities of mobile devices. Notably, collecting data withmobile crowdsensing solutions has several advantages comparedto traditional assessment methods when gathering data overtime. For example, data is gathered with high ecological validity, since smartphones can be unobtrusively used in everyday life. Existing approaches have shown that based on these advantages new medical insights, for example, for the tinnitus disease, can be revealed. In the work at hand, data of a developed mHealth crowdsensing platform that assesses the stress level and fluctuations of the platform users in daily life was investigated. More specifically, data of 1797 daily measurements on GPS and stress-related data in 77 users were analyzed. Using this data source, machine learning algorithms have been applied with the goalto predict stress-related parameters based on the GPS data of the platform users. Results show that predictions become possible that (1) enable meaningful interpretations as well as (2) indicate the directions for further investigations. In essence, the findings revealed first insights into the stress situation of individuals over time in order to improve their quality of life. Altogether, the work at hand shows that mobile crowdsensing can be valuably utilized in the context of stress on one hand. On the other, machine learning algorithms are able to utilize geospatial data of stress measurements that was gathered by a crowdsensing platform with the goal to improve the quality of life of its participating crowd users.}, language = {en} }