Stress Detection via Keyboard Typing Behaviors by Using Smartphone Sensors and Machine Learning Techniques.

Stress is one of the biggest problems in modern society. It may not be possible for people to perceive if they are under high stress or not. It is important to detect stress early and unobtrusively. In this context, stress detection can be considered as a classification problem. In this study, it was investigated the effects of stress by using accelerometer and gyroscope sensor data of the writing behavior on a smartphone touchscreen panel. For this purpose, smartphone data including two states (stress and calm) were collected from 46 participants. The obtained sensor signals were divided into 5, 10 and 15 s interval windows to create three different data sets and 112 different features were defined from the raw data. To obtain more effective feature subsets, these features were ranked by using Gain Ratio feature selection algorithm. Afterwards, writing behaviors were classified by C4.5 Decision Trees, Bayesian Networks and k-Nearest Neighbor methods. As a result of the experiments, 74.26%, 67.86%, and 87.56% accuracy classification results were obtained respectively.

Seasonal affective disorder in eight groups in Turkey: a cross-national perspective.

OBJECTIVE: Previous estimates of the prevalence of seasonal affective disorder (SAD) in community-based samples generally originated from western countries. We report prevalence rates in eight groups from four latitudes in Turkey. METHOD: Seasonal Pattern Assessment Questionnaire (SPAQ) was distributed to the community-based samples from eight different locations at four latitudes in Turkey. The prevalence rates of winter SAD and subsyndromal SAD (S-SAD) were estimated for the four groups at the same latitudes by using SPAQ responses. RESULTS: We distributed 3229 SPAQs, had an overall response rate of 54.16% and 1749 SPAQs were included in the analyses. Seasonality was reported as a problem by 549 subjects (31.57%) of our 1749 respondents. Prevalence of winter SAD and S-SAD are estimated as 4.86 and 8.35%, respectively, for the whole group. Prevalence rates were determined for each center and for four latitudes (two centers at the same latitude were grouped as one). In Adana-Gaziantep (lt. 37), Izmir-Elazig (lt. 38), Eskisehir-Ankara (lt. 39) and Trabzon-Edirne (lt. 41), the prevalence rates for winter SAD were 6.66, 2.25, 8.00 and 3.76%, respectively. CONCLUSIONS: Our prevalence estimates of winter SAD are similar to those found in previous community-based studies at the same latitudes; no correlation was found between latitude and prevalence of winter SAD, which could be related to the sampling methodology or to the fact that there were only 5 degrees of difference between the latitudes.