A Few-Shot Learning-Based Semi-Supervised Method to Enhance NLOS Recognition Accuracy Across Multiple Locations by Cross-Spatiotemporal Information

• Published in: IEEE transactions on instrumentation and measurement 2024, Vol.73, p.1-14
• Main Authors: Zeng, Kungan, Li, Zhenni, Xie, Shengli, Wang, Qianming, Chen, Wuhui, Zheng, Zibin
• Format: Article
• Language: English
• Subjects: Accuracy; Artificial neural networks; Current measurement; Feature extraction; Few-shot learning; Global navigation satellite system; Heterogeneity; Interference; Machine learning; Modules; multipath interference; Neural networks; Recognition; Satellites; self-attention mechanism; Semi-supervised learning; Siamese networks; spatial heterogeneity; Target recognition
• ISSN: 0018-9456; 1557-9662
• DOI: 10.1109/TIM.2024.3440416

Machine learning (ML)-based Global Navigation Satellite System (GNSS) signal recognition has been considered an efficient way to mitigate multipath error in positioning estimation. However, because of the spatial heterogeneity of nonline-of-sight (NLOS) interference, existing NLOS signal recognition methods struggle to achieve satisfactory accuracy across multiple locations. In particular, current methods achieve limited recognition accuracy on target domains containing unfamiliar environments. This study proposes a few-shot learning-based semi-supervised GNSS NLOS recognition method using cross-spatiotemporal information, which can achieve high-precision recognition for multiple target domains containing unfamiliar environments only requiring a limited number of labeled samples. First, we propose a self-attention mechanism-based cross-spatiotemporal information (SAM-CSI) module that captures the environmental characteristics used to model the spatial heterogeneity of NLOS interference. Next, to avoid the need for numerous labeled samples in training the model, we introduce a Siamese neural network-based few-shot learning (SNN-FSL) architecture to perform NLOS recognition using a similarity metric instead of label prediction. We then develop a semi-supervised NLOS recognition method by integrating the SAM-CSI module with the SNN-FSL architecture to enable high-precision recognition in target domains containing unfamiliar environments. Finally, we conducted comparison and few-shot learning experiments using real-world datasets, which demonstrated that our proposed method could achieve over 90% recognition accuracy in target domains containing unfamiliar environments after 50-shot learning. It represented an improvement of over 19% compared with existing methods.