# Hierarchical Multi-Building And Multi-Floor Indoor Localization Based On Recurrent Neural Networks

arXiv: https://arxiv.org/abs/2112.12478 · HTML: https://mlsanity.com/paper/2112.12478/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 19 references that are in the map.
- First posted on arXiv 23 Dec 2021.

## Builds on (most cited first, 5 of 5)

- [A Survey of Indoor Localization Systems and Technologies](https://mlsanity.com/paper/1709.01015/) (2017)
- [A Scalable Deep Neural Network Architecture for Multi-Building and Multi-Floor Indoor Localization Based on Wi-Fi Fingerprinting](https://mlsanity.com/paper/1712.01990/) (2017)
- [Low-effort place recognition with WiFi fingerprints using deep learning](https://mlsanity.com/paper/1611.02049/) (2016)
- [Large-Scale Location-Aware Services in Access: Hierarchical Building/Floor Classification and Location Estimation using Wi-Fi Fingerprinting Based on Deep Neural Networks](https://mlsanity.com/paper/1710.00951/) (2017)
- [Hybrid Building/Floor Classification and Location Coordinates Regression Using A Single-Input and Multi-Output Deep Neural Network for Large-Scale Indoor Localization Based on Wi-Fi Fingerprinting](https://mlsanity.com/paper/1810.05868/) (2018)

## Built on by (most cited first, 8 of 8)

- [Federated Learning based Hierarchical 3D Indoor Localization](https://mlsanity.com/paper/2303.00450/) (2023)
- [Multi-Output Gaussian Process-Based Data Augmentation for Multi-Building and Multi-Floor Indoor Localization](https://mlsanity.com/paper/2202.01980/) (2022)
- [MetaGraphLoc: A Graph-based Meta-learning Scheme for Indoor Localization via Sensor Fusion](https://mlsanity.com/paper/2411.17781/) (2024)
- [Hierarchical Stage-Wise Training of Linked Deep Neural Networks for Multi-Building and Multi-Floor Indoor Localization Based on Wi-Fi RSSI Fingerprinting](https://mlsanity.com/paper/2407.13288/) (2024)
- [On the Multidimensional Augmentation of Fingerprint Data for Indoor Localization in A Large-Scale Building Complex Based on Multi-Output Gaussian Process](https://mlsanity.com/paper/2211.10642/) (2022)
- [Mean Teacher based SSL Framework for Indoor Localization Using Wi-Fi RSSI Fingerprinting](https://mlsanity.com/paper/2407.13303/) (2024)
- [Decentralized Indoor Localization Based on A Sparse Gaussian Process with Reduced-Dimensional Inputs for Real-Time Sensing and Training on IoT Devices](https://mlsanity.com/paper/2409.00078/) (2024)
- [Graph-Based Floor Separation Using Node Embeddings and Clustering of WiFi Trajectories](https://mlsanity.com/paper/2505.08088/) (2025)

## Abstract (arXiv)

There has been an increasing tendency to move from outdoor to indoor lifestyle in modern cities. The emergence of big shopping malls, indoor sports complexes, factories, and warehouses is accelerating this tendency. In such an environment, indoor localization becomes one of the essential services, and the indoor localization systems to be deployed should be scalable enough to cover the expected expansion of those indoor facilities. One of the most economical and practical approaches to indoor localization is Wi-Fi fingerprinting, which exploits the widely-deployed Wi-Fi networks using mobile devices (e.g., smartphones) without any modification of the existing infrastructure. Traditional Wi-Fi fingerprinting schemes rely on complicated data pre/post-processing and time-consuming manual parameter tuning. In this paper, we propose hierarchical multi-building and multi-floor indoor localization based on a recurrent neural network (RNN) using Wi-Fi fingerprinting, eliminating the need of complicated data pre/post-processing and with less parameter tuning. The RNN in the proposed scheme estimates locations in a sequential manner from a general to a specific one (e.g., building->floor->location) in order to exploit the hierarchical nature of the localization in multi-building and multi-floor environments. The experimental results with the UJIIndoorLoc dataset demonstrate that the proposed scheme estimates building and floor with 100% and 95.24% accuracy, respectively, and provides three-dimensional positioning error of 8.62 m, which outperforms existing deep neural network-based schemes.