@article{Qin2025, 
author = {Yahang Qin and Zhenni Li and Shengli Xie and Bo Li and Ming Liu and Victor Kuzin},
title = {Non-Line-of-Sight Multipath Classification Method for BDS Using Convolutional Sparse Autoencoder with LSTM},
year = {2025},
journal = {Tsinghua Science and Technology},
volume = {30},
number = {1},
pages = {68-86},
keywords = {convolutional sparse autoencoder, BeiDou Navigation Satellite System (BDS), long short-term memory (LSTM), multipath classification},
url = {https://www.sciopen.com/article/10.26599/TST.2024.9010004},
doi = {10.26599/TST.2024.9010004},
abstract = {Multipath signal recognition is crucial to the ability to provide high-precision absolute-position services by the BeiDou Navigation Satellite System (BDS). However, most existing approaches to this issue involve supervised machine learning (ML) methods, and it is difficult to move to unsupervised multipath signal recognition because of the limitations in signal labeling. Inspired by an autoencoder with powerful unsupervised feature extraction, we propose a new deep learning (DL) model for BDS signal recognition that places a long short-term memory (LSTM) module in series with a convolutional sparse autoencoder to create a new autoencoder structure. First, we propose to capture the temporal correlations in long-duration BeiDou satellite time-series signals by using the LSTM module to mine the temporal change patterns in the time series. Second, we develop a convolutional sparse autoencoder method that learns a compressed representation of the input data, which then enables downscaled and unsupervised feature extraction from long-duration BeiDou satellite series signals. Finally, we add an  l1/2 regularizer to the objective function of our DL model to remove redundant neurons from the neural network while ensuring recognition accuracy. We tested our proposed approach on a real urban canyon dataset, and the results demonstrated that our algorithm could achieve better classification performance than two ML-based methods (e.g., 11% better than a support vector machine) and two existing DL-based methods (e.g., 7.26% better than convolutional neural networks).}
}