Adaptive radio map reconstruction via adversarial wireless fingerprint learning

Weina Jiang, Qun Niu, Suining He, Ning Liu

Abstract: Wi-Fi signals play an essential role in indoor location-based services. However, the Wi-Fi radio map is vulnerable to deployment changes, leading to significant localization errors. Therefore, surveyors must regularly carry out a labor-intensive and time-consuming site survey to keep the radio map up-to-date. To address this, we propose a radio map reconstruction framework (RMRec), which adopts adversarial learning to efficiently reconstruct the latest radio map with new signal samples collected at a small portion of reference points (RPs). The reconstruction model we built reveals the inherent spatial relations of the Wi-Fi signals in a large-scale building structure and by which the coarse-grained radio map is mapped into the corresponding fine-grained one, thus reducing the cost of the site survey significantly. The adversarial mechanism in RMRec enhances the textural features of the updated radio map, consequently improving the localization service. Meanwhile, we employ the scene-constrained downsample method and the CutPaste data augmentation to improve our model’s reconstruction accuracy and transferability. Besides, we design a non-uniform sampling strategy to reduce the site survey cost by allocating different selection rates for each subarea according to its anti-noise ability for location service. Experimental results demonstrate that RMRec can precisely reconstruct radio maps with 25\(\%\) new samples and exceeds an average of 18.83\(\%\) over the state-of-the-art methods in reconstruction accuracy. In addition, RMRec is also efficient for changed access points (APs), newly deployed APs, and scene changes.