An Efficient Convolutional Denoising Autoencoder-Based BDS NLOS Detection Method in Urban Forest Environments
The BeiDou Navigation Satellite System (BDS) provides real-time absolute location services to users around the world and plays a key role in the rapidly evolving field of autonomous driving. In complex urban environments, the positioning accuracy of BDS often suffers from large deviations due to non...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-03-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/24/6/1959 |
| _version_ | 1797239345810243584 |
|---|---|
| author | Yahang Qin Zhenni Li Shengli Xie Haoli Zhao Qianming Wang |
| author_facet | Yahang Qin Zhenni Li Shengli Xie Haoli Zhao Qianming Wang |
| author_sort | Yahang Qin |
| collection | DOAJ |
| description | The BeiDou Navigation Satellite System (BDS) provides real-time absolute location services to users around the world and plays a key role in the rapidly evolving field of autonomous driving. In complex urban environments, the positioning accuracy of BDS often suffers from large deviations due to non-line-of-sight (NLOS) signals. Deep learning (DL) methods have shown strong capabilities in detecting complex and variable NLOS signals. However, these methods still suffer from the following limitations. On the one hand, supervised learning methods require labeled samples for learning, which inevitably encounters the bottleneck of difficulty in constructing databases with a large number of labels. On the other hand, the collected data tend to have varying degrees of noise, leading to low accuracy and poor generalization performance of the detection model, especially when the environment around the receiver changes. In this article, we propose a novel deep neural architecture named convolutional denoising autoencoder network (CDAENet) to detect NLOS in urban forest environments. Specifically, we first design a denoising autoencoder based on unsupervised DL to reduce the long time series signal dimension and extract the deep features of the data. Meanwhile, denoising autoencoders improve the model’s robustness in identifying noisy data by introducing a certain amount of noise into the input data. Then, an MLP algorithm is used to identify the non-linearity of the BDS signal. Finally, the performance of the proposed CDAENet model is validated on a real urban forest dataset. The experimental results show that the satellite detection accuracy of our proposed algorithm is more than 95%, which is about an 8% improvement over existing machine-learning-based methods and about 3% improvement over deep-learning-based approaches. |
| first_indexed | 2024-04-24T17:50:04Z |
| format | Article |
| id | doaj.art-f9c8008e22264b09984300aac607acb3 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-24T17:50:04Z |
| publishDate | 2024-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-f9c8008e22264b09984300aac607acb32024-03-27T14:04:14ZengMDPI AGSensors1424-82202024-03-01246195910.3390/s24061959An Efficient Convolutional Denoising Autoencoder-Based BDS NLOS Detection Method in Urban Forest EnvironmentsYahang Qin0Zhenni Li1Shengli Xie2Haoli Zhao3Qianming Wang4School of Automation, Guangdong University of Technology, Guangzhou 510006, ChinaSchool of Automation, Guangdong University of Technology, Guangzhou 510006, China111 Center for Intelligent Batch Manufacturing Based on IoT Technology (GDUT), Guangzhou 510006, ChinaSchool of Automation, Guangdong University of Technology, Guangzhou 510006, ChinaTaidou Microelectronics Technology Co., Ltd., Guangzhou 510006, ChinaThe BeiDou Navigation Satellite System (BDS) provides real-time absolute location services to users around the world and plays a key role in the rapidly evolving field of autonomous driving. In complex urban environments, the positioning accuracy of BDS often suffers from large deviations due to non-line-of-sight (NLOS) signals. Deep learning (DL) methods have shown strong capabilities in detecting complex and variable NLOS signals. However, these methods still suffer from the following limitations. On the one hand, supervised learning methods require labeled samples for learning, which inevitably encounters the bottleneck of difficulty in constructing databases with a large number of labels. On the other hand, the collected data tend to have varying degrees of noise, leading to low accuracy and poor generalization performance of the detection model, especially when the environment around the receiver changes. In this article, we propose a novel deep neural architecture named convolutional denoising autoencoder network (CDAENet) to detect NLOS in urban forest environments. Specifically, we first design a denoising autoencoder based on unsupervised DL to reduce the long time series signal dimension and extract the deep features of the data. Meanwhile, denoising autoencoders improve the model’s robustness in identifying noisy data by introducing a certain amount of noise into the input data. Then, an MLP algorithm is used to identify the non-linearity of the BDS signal. Finally, the performance of the proposed CDAENet model is validated on a real urban forest dataset. The experimental results show that the satellite detection accuracy of our proposed algorithm is more than 95%, which is about an 8% improvement over existing machine-learning-based methods and about 3% improvement over deep-learning-based approaches.https://www.mdpi.com/1424-8220/24/6/1959denoising autoencoderBDSNLOStime series featuresurban forest |
| spellingShingle | Yahang Qin Zhenni Li Shengli Xie Haoli Zhao Qianming Wang An Efficient Convolutional Denoising Autoencoder-Based BDS NLOS Detection Method in Urban Forest Environments Sensors denoising autoencoder BDS NLOS time series features urban forest |
| title | An Efficient Convolutional Denoising Autoencoder-Based BDS NLOS Detection Method in Urban Forest Environments |
| title_full | An Efficient Convolutional Denoising Autoencoder-Based BDS NLOS Detection Method in Urban Forest Environments |
| title_fullStr | An Efficient Convolutional Denoising Autoencoder-Based BDS NLOS Detection Method in Urban Forest Environments |
| title_full_unstemmed | An Efficient Convolutional Denoising Autoencoder-Based BDS NLOS Detection Method in Urban Forest Environments |
| title_short | An Efficient Convolutional Denoising Autoencoder-Based BDS NLOS Detection Method in Urban Forest Environments |
| title_sort | efficient convolutional denoising autoencoder based bds nlos detection method in urban forest environments |
| topic | denoising autoencoder BDS NLOS time series features urban forest |
| url | https://www.mdpi.com/1424-8220/24/6/1959 |
| work_keys_str_mv | AT yahangqin anefficientconvolutionaldenoisingautoencoderbasedbdsnlosdetectionmethodinurbanforestenvironments AT zhennili anefficientconvolutionaldenoisingautoencoderbasedbdsnlosdetectionmethodinurbanforestenvironments AT shenglixie anefficientconvolutionaldenoisingautoencoderbasedbdsnlosdetectionmethodinurbanforestenvironments AT haolizhao anefficientconvolutionaldenoisingautoencoderbasedbdsnlosdetectionmethodinurbanforestenvironments AT qianmingwang anefficientconvolutionaldenoisingautoencoderbasedbdsnlosdetectionmethodinurbanforestenvironments AT yahangqin efficientconvolutionaldenoisingautoencoderbasedbdsnlosdetectionmethodinurbanforestenvironments AT zhennili efficientconvolutionaldenoisingautoencoderbasedbdsnlosdetectionmethodinurbanforestenvironments AT shenglixie efficientconvolutionaldenoisingautoencoderbasedbdsnlosdetectionmethodinurbanforestenvironments AT haolizhao efficientconvolutionaldenoisingautoencoderbasedbdsnlosdetectionmethodinurbanforestenvironments AT qianmingwang efficientconvolutionaldenoisingautoencoderbasedbdsnlosdetectionmethodinurbanforestenvironments |