HappyStudent

Abstract

In the past few years, the idea of the “Internet of Things” has been developing rapidly, with sensors and machines communicating with each other through the Internet. These new technologies can be used to support new types of Cyber-Physical systems(CPS). Even though CPS consider humans as a part of itself, they still treat them as external element, with unpredictable behavior. In order to serve human needs better, they have to take into account all sorts of psychological and emotional states. Smartphones present an excellent opportunity to do so, seen as they contain several sensors that allow us to collect information about user movement, location, their environment, and interaction with other people. This type of mobile device usually accompanies the user anywhere he goes throughout the day. We have taken this opportunity and tried to create apps that can infer human emotions and help people by giving them suggestions that may improve their mood. These apps are HappySPEAK and WeDoCare. We also tested and analyzed the system on which these were built upon: HappyWalk. All of these apps are based on the Happy System architecture. HappySPEAK aims to further improve this platform by detecting if the user is isolated and give suggestions that may help him overcome it. Migrants are the perfect candidates to use this, seeing that it is common for them to come alone to a new country in order to provide for their families. WeDoCare aims to detect violent attacks against users, and aims to help them by alerting other people that an attack is happening, show danger zones and alternate paths to avoid them. The rest of the report will focus on the Software Engineering part, implementation of these apps and what we can do to further improve them. We will also present all of the performance and emotion detection test results and analyze them thoroughly to expose our findings. Everything described in this report reflects the work done in the 2015/2016 school year.