Mining channel state information from bluetooth low energy RSSI for robust object-to-object ranging

In the world of smart objects, device-ranging and localization using Bluetooth Low Energy (BLE) is becoming popular due to its attractive energy performance, wide platform support and low costs. There has been sufficient motivation on statistical analysis of Channel State Information of Received Signal Strength Indicator (RSSI) data for more effective ranging-based models. However, there has been no ubiquitous solution which is both receiver-agnostic and does not require alteration in the advertisement protocol or packet structure of BLE. In this paper, we propose a truly unsupervised approach for channel-annotation of RSSI data received by a stationary receiver object. Given a sequence of RSSI observations and a discoverable receiver channel-switching policy, we determine the period and hence the time spent by the receiver in an individual channel. Then, we propose a sliding-window based algorithm which utilizes two well-established Likelihood-Ratio algorithms - KLIEP and uLSIF - for extracting Channel State Information of retrospective RSSI observation data. We believe this work lays the foundation of motivating future work in completely unsupervised methods for object-to-object ranging and localization.