This report details the design and implementation of a subsystem providing a web-based platform for smartwatch data acquisition. A smartwatch application is developed to read out the accelerometer, gyroscope and heart rate sensor on the smartwatch and transmit the sensor data to the platform. A platform is developed to receive the data and store it in a database. Recordings can be downloaded from the platform to use in research of human activity. The platform presents the type of activity the smartwatch user is doing using machine learning models, by integrating the other subsystem. Multiple tests have been performed to analyse and improve the performance of the system. The battery life of the smartwatch has been tested using various settings in the smartwatch application to determine the most power-efficient settings.

In this report, the analysis and design of a system that extracts keyframes from videos is detailed. The need for such a sub-module stems from the similarity of frames in a video. To aid in reducing the computation time of the content based video search engine, the Keyframe Extraction Module reduces the amount of frames by discarding frames that are similar in information. Determining what frames can be considered similar is one of the main challenges, as there are many ways of assigning values to how much frames differ. In the past decades, many research has been done on keyframe extraction and video summarization and many methods are proposed to form keyframe selections, varying in what is considered salient information and varying in computation time. The most challenging part of the design is that there is a time constraint present, which called for a proper analysis in what methods are suitable. After all, this limitation when creating video summaries is often not a large topic in research papers.This report will cover Shot Detection techniques along with various Keyframe Extraction methods that can be categorized in clustering, visual content, fixed selection and uniform sampling. Furthermore, evaluation methods like the Fidelity measure for the performance of particular methods are also addressed, as determining how well a keyframe selection is is not trivial. It is concluded that out of the techniques analyzed, a combination of VSUMM clustering and histogram matching along with histogram-based shot based detection with a CFAR threshold and pre-sampling is most suitable for the general case under a time constraint. Future work could include looking at hierarchical clustering methods and optimizing the Shot Boundary Detection module following the most recent papers.

This document reports details the development of a solid stool detection system. On behalf of Momo Medical - a TU Delft-based startup company - a device for detecting defecates by elderly people has been designed. The goal of the detection system is to detect solid stools by elderly patients wearing a diaper and to notify the nurses in a nursing home accordingly. The project has been organized and conducted in two groups: Hardware & Software. Our group has been in charge of the hardware. The other group has been responsible for the software. The main focus in this report will be the hardware design of the system. This report contains: the analysis of the problem, the development of a solution, the design and the evaluation of the device in test. The developed device detects methane by means of multiple gas sensors, since methane is the main gas component released while defecating. Several iterations making a suited printed circuit board and case have been carried out, while taking aspects like safety, reliability and noise performance into account. The report concludes with a summary of main results and an outline of future work.

The design, production and testing of the Bluetooth Ultrasimple Gamepad, or BUG for short, is laid out in this report. In the current market, most of the controllers available are multi-button controllers with analogue sticks. These controllers are expensive and can not be used for many web browser games which rely on a keyboard input to work. In order for these controllers to work, a video game or self developed app can be used, but this can be difficult or expensive for many users. In the implementation of the BUG, the controller was made to be used by a single hand, having a clear ”main” button, an intuitive reconfiguration scheme and to have Bluetooth connection which is present in a lot of laptops and PCs currently in use. With this approach, the user can have a cheap, simple and comfortable alternative to existing gamepads. It can be stated
that, although not for everybody, the BUG is a good and fun alternative for users. This can be seen because the general user experience is rated at 5 out of 5 points by 50% of the participants, 4 out of 5 by 46.7% of the participants and only 1, or 3.3% of the participants has given a rating of 2 out of 5.