Machine Learning
Bluetooth Discovery Time with Multiple Inquirers
HICSS '06 Proceedings of the 39th Annual Hawaii International Conference on System Sciences - Volume 09
Redundancy and coverage detection in sensor networks
ACM Transactions on Sensor Networks (TOSN)
Bluetooth Inquiry Time Characterization and Selection
IEEE Transactions on Mobile Computing
Indoor localization based on response rate of bluetooth inquiries
Proceedings of the first ACM international workshop on Mobile entity localization and tracking in GPS-less environments
Human-Computer Interaction
Accurate GSM indoor localization
UbiComp'05 Proceedings of the 7th international conference on Ubiquitous Computing
A context management framework for supporting context-aware distributed applications
IEEE Communications Magazine
Bluetooth Tracking without Discoverability
LoCA '09 Proceedings of the 4th International Symposium on Location and Context Awareness
Bayesian Fusion for Indoor Positioning Using Bluetooth Fingerprints
Wireless Personal Communications: An International Journal
Hi-index | 0.00 |
Ubiquitous computing environments typically contain a large number and a large variety of networked sensors that are often embedded in the environment. As these networks grow in size and complexity, their management becomes increasingly costly, for instance in terms of equipment, software, and people. One way to keep these costs under control is to automate some or all of the management aspects in the system, reducing or even removing the need for human interaction. In this paper, we focus on automatically managing Bluetooth networks for indoor localization, which we consider a specific class of ubiquitous computing systems because they usually rely on many Bluetooth devices scattered throughout a particular building. We will discuss algorithms that help reducing the number of active devices needed in a network, while maintaining a comparable localization accuracy compared to the "full" network. The algorithms enable the most "valuable" Bluetooth devices in the network and will disable the others. The main advantage is that this reduces the need for network planning, which reduces the costs of operating the system. Another advantage is that it reduces the amount of energy used by the network and the mobile devices being located. We evaluate the real-world performance of our algorithms through experiments carried out with a running system in a realistic environment. We found that our algorithms can reduce a network to approximately half the original size while still retaining an accuracy level comparable to the original "full" network.