Police officers are exposed to many potentially traumatising and stressful situations, but they do not always find the right mental health help they need. In this thesis, conversational agent Robyn is developed to help officers keep an eye on their mental well-being and find help when needed. An evaluation approach is also presented. The conversational agent applies the Stress First Aid method to determine stress indicators together with the officer. The design of the agent followed the guidelines for Stress First Aid. The agent uses text input and output and went through an iterative design process using expert feedback. The experts provided feedback on both text and structure of the conversation. Based on their input, informal language was chosen for the presentation of the agent. The lessons for similar projects drawn from this design process are managing expectations from users, scoping broad questions, getting feedback from users on wording and not to push people when discussing suicide. The proposed evaluation would determine if the agent is effective at improving people's awareness of their mental well-being status. This is done by comparing perceived mental well-being before and after interaction to reported mental well-being. To achieve this, a survey to measure perceived mental well-being was developed. The evaluation also provides insight in what aspects of the agent need the most improvement in future iterations.

Elderly care residences often have falling incidents, sometimes with dire consequences. This project aims to implement a method for detecting when people fall, an issue that has seen much research and practical implementations already. In contrast to other work, this project aims to create a non-intrusive, non-wearable solution through the use of cameras. It extends an existing patient monitoring system developed by Eya Solutions, a start-up in the medical field. Their system monitors patients and is composed of embedded systems (clients), a back-end with a database, and a web-based dashboard (the front-end) for administrators, caretakers and users. Our client wants to extend their system by introducing: (i) a video processing component which performs face recognition, (ii) functionality for indoor positioning of people, (iii) functionality to automatically determine near-optimal placement of cameras, and (iv) automatic detection of fall incidents. To understand the relevant research, we survey the field investigating five key research topics: (i) object detection, (ii) fall detection, (iii) facial recognition, (iv) floor plan modelling, and (v) camera placement optimisation. The first part of the project is detecting fall incidents in video footage. By means of image processing (in particular, subsequent frame subtraction), our system detects objects in the foreground and tracks these between frames. Based on the properties of such objects, namely size and shape, we detect fall incidents. The second part of the project is the floor plan editor. This editor is integrated into the existing dashboard, where administrators can model the building. Eya Solutions wishes to provide the product to customers as a complete package, including (i) showing where fall incidents have occurred, and (ii) how and where to place cameras. Our system allows administrators to edit the floor while allowing caretakers to see the modelled floor and see where falls are detected. Considering (ii), it is desirable to generate a configuration where the number of cameras is low while the view coverage is high. Our contribution includes a genetic algorithm which can generate automatically a suitable configuration. Alternatively, cameras can be placed manually by the administrator.