Self-Supervised Learning for User Localization

TL;DR

This paper introduces a self-supervised learning approach using autoencoders to improve user localization accuracy with CSI data, especially when labeled data is scarce, demonstrating promising results on a large-scale dataset.

Contribution

It pioneers the use of self-supervised pretraining with autoencoders for user localization based on CSI, reducing reliance on labeled data and enhancing performance.

Findings

Effective feature extraction from unlabeled data using AE models

Improved localization accuracy with limited labeled data

Successful application on large-scale, real-world dataset

Abstract

Machine learning techniques have shown remarkable accuracy in localization tasks, but their dependency on vast amounts of labeled data, particularly Channel State Information (CSI) and corresponding coordinates, remains a bottleneck. Self-supervised learning techniques alleviate the need for labeled data, a potential that remains largely untapped and underexplored in existing research. Addressing this gap, we propose a pioneering approach that leverages self-supervised pretraining on unlabeled data to boost the performance of supervised learning for user localization based on CSI. We introduce two pretraining Auto Encoder (AE) models employing Multi Layer Perceptrons (MLPs) and Convolutional Neural Networks (CNNs) to glean representations from unlabeled data via self-supervised learning. Following this, we utilize the encoder portion of the AE models to extract relevant features from labeled data, and finetune an MLP-based Position Estimation Model to accurately deduce user locations. Our experimentation on the CTW-2020 dataset, which features a substantial volume of unlabeled data but limited labeled samples, demonstrates the viability of our approach. Notably, the dataset covers a vast area spanning over 646x943x41 meters, and our approach demonstrates promising results even for such expansive localization tasks.