Large-Scale Location-Aware Services in Access: Hierarchical Building/Floor Classification and Location Estimation using Wi-Fi Fingerprinting Based on Deep Neural Networks

TL;DR

This paper explores using deep neural networks for hierarchical indoor localization via Wi-Fi fingerprinting, demonstrating promising results in building/floor classification and floor-level location estimation on a university campus.

Contribution

It introduces a novel DNN architecture with stacked autoencoders for hierarchical classification and demonstrates a prototype system for indoor localization using real RSS data.

Findings

DNN-based methods achieve near state-of-the-art accuracy.

The proposed architecture reduces feature space and improves scalability.

Preliminary results validate the effectiveness of deep learning for indoor localization.

Abstract

One of key technologies for future large-scale location-aware services in access is a scalable indoor localization technique. In this paper, we report preliminary results from our investigation on the use of deep neural networks (DNNs) for hierarchical building/floor classification and floor-level location estimation based on Wi-Fi fingerprinting, which we carried out as part of a feasibility study project on Xi'an Jiaotong-Liverpool University (XJTLU) Campus Information and Visitor Service System. To take into account the hierarchical nature of the building/floor classification problem, we propose a new DNN architecture based on a stacked autoencoder for the reduction of feature space dimension and a feed-forward classifier for multi-label classification with argmax functions to convert multi-label classification results into multi-class classification ones. We also describe the demonstration of a prototype DNN-based indoor localization system for floor-level location estimation using real received signal strength (RSS) data collected at one of the buildings on the XJTLU campus. The preliminary results for both building/floor classification and floor-level location estimation clearly show the strengths of DNN-based approaches, which can provide near state-of-the-art performance with less parameter tuning and higher scalability.