Unsupervised Learning for Solving RSS Hardware Variance Problem in WiFi Localization
Mobile Networks and Applications
| Hi-index | 0.00 |
Recent localization research has focused on improving the accuracy of pinpointing the physical location of a target. We think that the energy efficiency and the quality of the localization services (QoLS) are equally important properties of localization systems. We refer to the QoLS as the timely supply of the location information to the applications. Energy efficiency and quality are seemingly two contradictive goals in terms of determining the rate of triggering the localization systems to perform the necessary computation and communication. In that, a lower location sampling rate contributes to a lower level of energy consumption but in the meantime compromises the timeliness of acquiring the location information. Opting for energy efficient and quality localization services, we propose a mobility-aware mechanism that adapts the sampling rate to the target mobility. Results from our simulations confirm that the adaptive sampling approach is promising and effective.