Mining channel state information from bluetooth low energy RSSI for robust object-to-object ranging
Citations
2 citations
Cites methods from "Mining channel state information fr..."
..., hopping) and each channel has its own characteristics, we want to explore techniques such as channel separation [12] and leverage different channels separately to improve the accuracy....
[...]
Cites background from "Mining channel state information fr..."
...My recent work towards the goal above - to model systems for human-human interaction analysis [1] - deals with RSSI based ranging models for heterogeneous Bluetooth Low Energy (BLE) devices, particularly smartphones and BLE Beacons....
[...]
Cites background from "Mining channel state information fr..."
...In [12], it is stated that RCPI overcomes these limitations by providing a quantized, comparative measure of power level for all channels/rates and among all PHYs and STAs....
[...]
References
788 citations
"Mining channel state information fr..." refers methods in this paper
...For Unsupervised CSI accuracy, we use a similar variant of the Mean Root Mean Square (MRMS) period difference (known period = 15s or 150 observations) - as given in [1]....
[...]
...Unsupervised segmentation algorithms [1] have been used to segment time series data, thus finding change points based on data features, and are essentially attractive because they may handle a variety of different situations without requiring prior training for each situation....
[...]
785 citations
"Mining channel state information fr..." refers methods in this paper
...It is similar to KLIEP in terms of the objective, i.e., to estimate the density ratio directly, albeit with different loss functions. uLSIF utilizes the same density-ratio model as KLIEP (refer eq....
[...]
...The Kullback-Leibler Importance Estimation Procedure (KLIEP)[9] algorithm directly estimates the density ratio ŵ such that the Kullback-Leibler divergence from the true test window density pt(o) to its estimate, i.e. ŵ(oti;α)pr(oti), is minimized....
[...]
...The error in the trivial KLIEP algorithm can be countered by setting a tolerance on the samples actually used for computing mK , which can be set at 80-90% of nc (i.e. ≈ 40-50 observations)....
[...]
...KLIEP utilizes log loss while uLSIF utilizes the squared loss....
[...]
...We employ direct-density ratio estimators using KLIEP and uLSIF to detect and annotate CSI....
[...]
736 citations
"Mining channel state information fr..." refers background in this paper
...al in [3] report the mean levels of the three separated signals to be varied : (C37: -63....
[...]
...Several studies [3, 8] have explored BLE localization using device-ranging....
[...]
492 citations
"Mining channel state information fr..." refers background or methods in this paper
...6 in [7], where λ > 0 is the regularization parameter, which is chosen by cross-validation....
[...]
...The uLSIF (Unconstrained Least-Squares Importance Fitting) [7] algorithm uses Pearson (PE) divergence as a dissimilarity measure....
[...]
277 citations