Bayesian Optimization (BO) has demonstrated significant utility across numerous applications. However, due to it being designed as a universal optimizer, its performance can often be suboptimal in specialized environments. To overcome this issue, research has been conducted into the application of transfer learning for enhancing BO performance in these specialized contexts. This paper describes the research done into evaluating the MetaBO algorithm in some specific environments. MetaBO innovates by substituting the acquisition function component in BO with a neural network that serves as an acquisition function, trained via a reinforcement learning framework. Although the results indicate that the algorithm's performance is not optimal in the environments tested, these limitations are ascribed to elements of the implementation rather than the concept of the algorithm itself. Consequently, further research is necessary to refine the implementation process and fully exploit the potential of the MetaBO algorithm.

To make open door policies easier in nursing homes, it is important to have a smart system that can check whether access is allowed for the person trying to enter some place or not. This thesis documents how an access control system has been built, for Momo Medical, to be used at a nursing home. It sheds light on hardware considerations made and the software written for the final product. All the knowledge gathered and the time spent has led to a final product that with minor tweaks can be used in the existing infrastructure of Momo Medical but also without the presence of it. There are however still improvements left to be made for the final product to be commercially appealing.