Device-independent Wi-Fi fingerprinting indoor localization model based on domain adaptation

Device-independent Wi-Fi fingerprinting indoor localization model based on domain adaptation

Blog Article

In real-world large-scale deployments of indoor localization, Wi-Fi fingerprinting approaches suffer from device Twin Panel Headboard diversity problem which impacts the localization accuracy significantly.A device-independent Wi-Fi fingerprint indoor localization model DeviceTransfer was proposed.Based on the domain adaptation theory of deep learning, the device type of the smartphone was taken as the domain, the task-related and device-independent Wi-Fi data features were extracted through adversarial training, and the learned source domain location information was transferred to the target domain.

Pre-training and joint training were employed to improve model training stability and to accelerate convergence.The performance of DeviceTransfer was evaluated Plugs using four types of smartphones in two real-world indoor environments: a school building and a shopping mall.The experimental results show that DeviceTransfer effectively extracts device-independent Wi-Fi fingerprint features.

Using only one type of phone to collect Wi-Fi fingerprints, online localization using other types still achieves high localization accuracy, thus reducing localization cost significantly.