Domain Adversarial Graph Convolutional Network Based on RSSI and Crowdsensing for Indoor Localization

Article Computer Science, Information Systems

A survey of deep learning approaches for WiFi-based indoor positioning

Xu Feng et al.

Summary: WiFi fingerprinting is a popular method for indoor positioning, and deep learning has emerged as a more accurate alternative in recent years. This survey reviews deep learning methods for WiFi fingerprinting and finds that despite new WiFi signal measures, RSS remains competitive and simple neural networks can outperform more complex ones in certain environments.

JOURNAL OF INFORMATION AND TELECOMMUNICATION (2022)

Add to Collection

Article Telecommunications

Multi-Level Federated Graph Learning and Self-Attention Based Personalized Wi-Fi Indoor Fingerprint Localization

Zheshun Wu et al.

Summary: In this letter, a multi-level federated graph learning and self-attention based personalized indoor localization method is proposed to address the problem of data sharing without privacy disclosure and achieve better personalized accuracy by capturing intrinsic features of RSS and learning aggregation manner of shared information. Experimental results demonstrate higher personalized localization accuracy compared to personalized federated learning methods.

IEEE COMMUNICATIONS LETTERS (2022)

Add to Collection

Article Computer Science, Information Systems

Indoor Localization Fusing WiFi With Smartphone Inertial Sensors Using LSTM Networks

Mingyang Zhang et al.

Summary: This study proposes a novel smartphone-based indoor localization algorithm that integrates WiFi and PDR features, utilizing time-series data sets and LSTM networks for accurate positioning. Experimental results demonstrate the algorithm's high accuracy and robustness in indoor and extreme environments.

IEEE INTERNET OF THINGS JOURNAL (2021)

Add to Collection

Article Computer Science, Information Systems

DAFI: WiFi-based Device-free Indoor Localization via Domain Adaptation

Hang Li et al.

Summary: The study introduces a localization method called DAFI, which addresses the issue of fingerprint inconsistency caused by environmental changes in WiFi systems using domain adaptation techniques, achieving up to 14.2% improvement in real-world experiments.

PROCEEDINGS OF THE ACM ON INTERACTIVE MOBILE WEARABLE AND UBIQUITOUS TECHNOLOGIES-IMWUT (2021)

Add to Collection

Article Acoustics