Application of backpropagation neural networks to both stages of fingerprinting based WIPS

• Published in: 2016 Fourth International Conference on Ubiquitous Positioning, Indoor Navigation and Location Based Services (UPINLBS) pp. 207 - 217
• Main Authors: Caifa Zhou, Wieser, Andreas
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.11.2016
• Subjects: Backpropagation; Buildings; Euclidean distance; Neural networks; Position measurement; Training; Transmission line measurements
• DOI: 10.1109/UPINLBS.2016.7809973

We propose a scheme to employ backpropagation neural networks (BPNNs) for both stages of fingerprinting-based indoor positioning using WLAN/WiFi signal strengths (FWIPS): radio map construction during the offline stage, and localization during the online stage. Given a training radio map (TRM), i.e., a set of coordinate vectors and associated WLAN/WiFi signal strengths of the available access points, a BPNN can be trained to output the expected signal strengths for any input position within the region of interest (BPNN-RM). This can be used to provide a continuous representation of the radio map and to filter, densify or decimate a discrete radio map. Correspondingly, the TRM can also be used to train another BPNN to output the expected position within the region of interest for any input vector of recorded signal strengths and thus carry out localization (BPNN-LA). Key aspects of the design of such artificial neural networks for a specific application are the selection of design parameters like the number of hidden layers and nodes within the network, and the training procedure. Summarizing extensive numerical simulations, based on real measurements in a testbed, we analyze the impact of these design choices on the performance of the BPNN and compare the results in particular to those obtained using the κ nearest neighbors (κNN) and weighted κ nearest neighbors approaches to FWIPS. The results indicate that BPNN-RM can help to reduce the workload for radio map generation significantly by allowing to sample the signal strengths at significantly less positions during the offline phase while still obtaining equal or even slightly better accuracy during the online stage as when directly applying the sampled radio map to (weighted) κNN. In the scenario analyzed within the paper the workload can be reduced by almost 90%. We also show that a BPNN-LA with only 1 hidden layer outperforms networks with more hidden layers and yields positioning accuracy comparable to or even slightly better than κNN but with less computational burden during the online stage.