Detecting stress in computer users, while technically challenging, is of the utmost importance in the workplace, especially now that remote working scenarios are becoming ubiquitous. In this context, cost-effective, subject-independent systems are needed that can be embedded in consumer devices and classify users’ stress in a reliable and unobtrusive fashion. Leveraging keyboard and mouse dynamics is particularly appealing in this context as it exploits readily available sensors. However, available studies are mostly performed in laboratory conditions, and there is a lack of on-field investigations in closer-to-real-world settings. In this study, keyboard and mouse data from 62 volunteers were experimentally collected in-the-wild using a purpose-built Web application, designed to induce stress by asking each subject to perform 8 computer tasks under different stressful conditions. The application of Multiple Instance Learning (MIL) to Random Forest (RF) classification allowed the devised system to successfully distinguish 3 stress-level classes from keyboard (76% accuracy) and mouse (63% accuracy) data. Classifiers were further evaluated via confusion matrix, precision, recall, and F1-score.

In this paper a Radial Basis Function (RBF) neural network is proposed to obtain the 24-hr forecast of the solar irradiation on the horizontal plane in the city of Ancona, Italy. This information is used to estimate the production of a PhotoVoltaic (PV) plant in order to provide the 'Gestore dei Servizi Energetici' (the main italian provider of energy services) with the power production profile of the next day. The company Energy Resources SPA has experimentally tested the proposed solution by a 14 KWp PV plant and a lithium battery pack. The battery pack is used to store the exceding power produced or to supply the lack of power compared with the reference.