The process of visualizing n-D data presents the user with four problems: finding a hyperdimensional graphics package capable of rendering n-D data, finding a suitable presentation technique supported by the package that allows insight to be gained, using the provided user interface to interact with the presentation technique to explore the information in the data, and finding a way to share the information gained with others. Many graphics packages have been written to solve the first problem. However, existing packages do not sufficiently solve the other three problems. A hyperdimensional graphics package that sufficiently solves all these problems simplifies the user experience and allows the user to explore, interact with, and share the data. I have implemented a package that solves all four problems. The package is able to render n-D data through appropriate encapsulation of presentation techniques and their associated visual cues. Through the use of an extensible plugin system, presentation techniques can be easily added and accommodated. Desirable features are supported by the user interface to allow the user to interact easily with the data. Sharing of visualizations and annotations are included to allow users to share information with one another. By providing a hyperdimensional graphics package that easily accommodates presentation techniques and includes desirable features, including those that are rarely or never supported, the user benefits from tools that allow improved interaction with multivariate data to extract information and share it with others.

eHealth is a recently emerging practice at the intersection between the ICT and healthcare fields where computing and communication technology is used to improve the traditional healthcare processes or create new opportunities to provide better health services, and eHealth can be considered under the umbrella of the Internet of Things. A common practice in eHealth is the use of machine learning for a computer-aided diagnosis, where an algorithm would be fed some biomedical signal to provide a diagnosis, in the same way a trained radiologist would do. This work considers the task of Atrial Fibrillation detection and proposes a novel range of algorithms to achieve energy-efficiency. Based on our working hypothesis, that computationally simple operations and low-precision data types are key for energy-efficiency, we evaluate various algorithms in the context of resource-restrained health-monitoring wearable devices. Finally, we assess the sustainability dimension of the proposed solution.

This thesis demonstrates a technique for developing efficient applications interpreting spacial deep learning output using Hyper Dimensional Computing (HDC), also known as Vector Symbolic Architecture (VSA). As a part of the application demonstration, a novel preprocessing technique for motion using state machines and spacial semantic pointers will be explained. The application will be evaluated and run on a Google Coral edge TPU interpreting real time inference of a compressed object detection model.