Dynamic BLE-based fingerprinting for location-aware smart homes

We have seen an ever-expanding set of location-aware services and devices become broadly available over the past years. Despite these promising applications and thorough research, indoor localization remains a very challenging topic and (near) perfect accuracy continues to be an open research challenge. In this paper, we acknowledge the growth and potential of smart home environments and focus on the usage of Bluetooth Low Energy (BLE) for wireless indoor positioning in such cases. This is in contrast with existing work around BLE that more focuses on use-cases in large public areas or buildings. In particular, we compare the applicability of different distance functions for the fingerprinting localization method and propose a dynamic approach of selecting the most suited distance function. Furthermore, we investigate the impact on the quality of the fingerprints by looking at directional fingerprints and search space restrictions. Finally, we discuss the design and usage of a real-life location-aware smart home application, where a user controls the lights in a room through gestures.