# SURIMI: Supervised Radio Map Augmentation with Deep Learning and a Generative Adversarial Network for Fingerprint-based Indoor Positioning

arXiv: https://arxiv.org/abs/2207.06120 · HTML: https://mlsanity.com/paper/2207.06120/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 27 references that are in the map.
- First posted on arXiv 13 Jul 2022.

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

- [Empirical Evaluation of Rectified Activations in Convolutional Network](https://mlsanity.com/paper/1505.00853/) (2015)
- [AF-DCGAN: Amplitude Feature Deep Convolutional GAN for Fingerprint Construction in Indoor Localization Systems](https://mlsanity.com/paper/1804.05347/) (2018)
- [Towards Ubiquitous Indoor Positioning: Comparing Systems across Heterogeneous Datasets](https://mlsanity.com/paper/2109.09436/) (2021)
- [Autonomous WiFi Fingerprinting for Indoor Localization](https://mlsanity.com/paper/1911.11825/) (2019)
- [High-Accuracy Ranging and Localization with Ultra-Wideband Communications for Energy-Constrained Devices](https://mlsanity.com/paper/2104.11042/) (2021)

## Built on by (most cited first, 2 of 2)

- [AI-driven Wireless Positioning: Fundamentals, Standards, State-of-the-art, and Challenges](https://mlsanity.com/paper/2501.14970/) (2025)
- [Generative AI Meets Wireless Sensing: Towards Wireless Foundation Model](https://mlsanity.com/paper/2509.15258/) (2025)

## Abstract (arXiv)

Indoor Positioning based on Machine Learning has drawn increasing attention both in the academy and the industry as meaningful information from the reference data can be extracted. Many researchers are using supervised, semi-supervised, and unsupervised Machine Learning models to reduce the positioning error and offer reliable solutions to the end-users. In this article, we propose a new architecture by combining Convolutional Neural Network (CNN), Long short-term memory (LSTM) and Generative Adversarial Network (GAN) in order to increase the training data and thus improve the position accuracy. The proposed combination of supervised and unsupervised models was tested in 17 public datasets, providing an extensive analysis of its performance. As a result, the positioning error has been reduced in more than 70% of them.