Received-Signal-Strength Threshold Optimization Using Gaussian Processes

Abstract

There is a big trend nowadays to use event-triggered proximity report for indoor positioning. This paper presents a generic received-signal-strength (RSS) threshold optimization framework for generating informative proximity reports. The proposed framework contains five main building blocks, namely the deployment information, RSS model, positioning metric selection, optimization process and management. Among others, we focus on Gaussian process regression (GPR) based RSS models and positioning metric computation. The optimal RSS threshold is found through minimizing the best achievable localization root-mean-square-error formulated with the aid of fundamental lower bound analysis. Computational complexity is compared for different RSS models and different fundamental lower bounds. The resulting optimal RSS threshold enables enhanced performance of new fashioned low-cost and low-complex proximity report based positioning algorithms. The proposed framework is validated with real measurements collected in an office area where Bluetooth-low-energy (BLE) beacons are deployed.

Existing System

Localization Scheme.

Proposed System

We have introduced a generic framework of RSS threshold optimization for indoor sensor networks. With the aid of this framework, we can obtain the most informative proximity report by means of optimizing the overall localization accuracy in a deployment area. Two pivotal building elements of this work are the RSS model and the fundamental lower bound. We have tested both the full GPR based model and an online GPR based model. In this work, we extend the multiple RSS thresholds tuning. The performance metric to be optimized is selected to be the overall positioning root-mean-square-error (RMSE) represented in terms of the Cram´er-Rao bound or Barankin bound. The former bound is suitable to benchmark estimation performance for medium and large scale sensor networks, while the latter bound is more suitable to benchmark small scale sensor networks. Moreover, we introduce advanced Gaussian process regression (GPR) based RSS models, perform detailed performance analyses and validate the results with more real data. Lastly, we incorporate the derived fundamental lower bounds and the advanced GPR based RSS models into RSS thresholds optimization. To give a quick overview, the proposed generic framework for selecting a set of reasonable RSS thresholds for proximity report based positioning.

Architecture

BLOCK DIAGRAM