… on stress and smartphone usage and sensor data. Our results show significant correlations
between stress and smartphone … and further studies on smartphone based stress prediction. …

… are based on a study of 28 workers, monitored over 6 weeks through their smartphones …
Table III shows the stress prediction accuracy obtained through the 10-fold cross-validation …

… in the prediction of human … stress with two classes (”Stressed” and ”Not-Stressed”) as a
Machine Learning classification task which is based on passive sensor data from smartphones. …

… Furthermore, we compare the prediction accuracy between several sets of features to
determine whether our proposed method, comprising a combination of features, can successfully …

… perception of stress and stress responses, … stressful or not) from every user. To address
these problems, we propose a novel unsupervised stress detector, based on using a smartphone …

… based on human-smartphone interaction analysis makes several advancements in the
state of the art of stress … interaction; combining the different prediction models (cf, Section 3). …

… individually to estimate the prediction accuracy. Using only smartphone features, we get
an … of collecting as much smartphone data as possible, extracting features based on state-of-the…

… In conclusion, this suggests that stress prediction using only smartphone user data did
not … perceived stress levels among Dutch students, based on their smartphone usage logs? …

… by smartphones. Through an empirical study, this paper proposes an automatic and non-intrusive
stress detection framework based on smartphone … 2) Online prediction: We can get …

… -based multi-channel thermistor was able to detect a significant decrease in temperature of
the nasal area as relative to the forehead in mentally stressful … a better prediction of the stress …