Learning Domain-Invariant Model for WiFi-Based Indoor Localization
- 5 August 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 23 (12) , 13898-13913
Abstract
WiFi-based indoor localization has gained widespread attention due to the pervasive availability of WiFi Access Points (APs). While signal processing-based methods can achieve decimeter-level localization, their performance is constrained by the limited spatial resolution of WiFi systems, especially in complex environments with strong interference. By contrast, deep learning-based methods have achieved impressive performance even in complex environments, which however often fail to generalize to new environments. In this paper, we propose a novel framework to learn domain-invariant model for WiFi-based indoor localization, which maintains impressive performance across different environments. The key insight is to design a deep learning-based WiFi localization system through the perspective of signal processing. Specifically, we let the neural network estimate APs-centered polar coordinates to avoid fitting the coordinates of APs strongly correlated with the environment, enabling us to obtain the domain-invariant model. To unleash the potential of neural networks in regressing high-precision parameters, we design a beamforming layer to integrate the knowledge of signal processing. Furthermore, we propose a multi-task learning scheme to further improve localization accuracy. Extensive experiments on diverse datasets have demonstrated that the localization performance of our method outperforms state-of-the-art methods and demonstrates superiority under cross-domain conditions.Keywords
Funding Information
- National Key R&D Programmes (2022YFC2503405)
- National Natural Science Foundation of China (62201542, 62172381)
- National Key R&D Programmes (2022YFC08698000)
- China Postdoctoral Science Foundation (GZC20241660)
- Fundamental Research Funds for the Central Universities
This publication has 60 references indexed in Scilit:
- MTrack: Tracking Multiperson Moving Trajectories and Vital Signs With Radio SignalsIEEE Internet of Things Journal, 2020
- SpeedNet: Indoor Speed Estimation With Radio SignalsIEEE Internet of Things Journal, 2020
- WiFi Vision: Sensing, Recognition, and Detection With Commodity MIMO-OFDM WiFiIEEE Internet of Things Journal, 2020
- End-To-End Multi-Task Learning With Attention2019
- BreathTrack: Tracking Indoor Human Breath Status via Commodity WiFiIEEE Internet of Things Journal, 2019
- TRIEDS: Wireless Events Detection Through the WallIEEE Internet of Things Journal, 2017
- Deep Residual Learning for Image Recognition2016
- Enabling Heterogeneous Connectivity in Internet of Things: A Time-Reversal ApproachIEEE Internet of Things Journal, 2016
- Deep learningNature, 2015
- Multitask LearningMachine Learning, 1997