Signal Denoising Method Combined With Variational Mode Decomposition, Machine Learning Online Optimization and the Interval Thresholding Technique
The signal-to-noise ratio of lidar signals decreases rapidly with an increase in distance, which seriously affects the application of lidar detection technology. Variational mode decomposition (VMD) has performed optimality in dealing with noise, but the number of modes, K, and the penalty parameter...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9285233/ |
| _version_ | 1818379556750360576 |
|---|---|
| author | Zhenxing Liu Jianhua Chang Hongxu Li Luyao Zhang Sicheng Chen |
| author_facet | Zhenxing Liu Jianhua Chang Hongxu Li Luyao Zhang Sicheng Chen |
| author_sort | Zhenxing Liu |
| collection | DOAJ |
| description | The signal-to-noise ratio of lidar signals decreases rapidly with an increase in distance, which seriously affects the application of lidar detection technology. Variational mode decomposition (VMD) has performed optimality in dealing with noise, but the number of modes, K, and the penalty parameter, α, must be preset. Therefore, a novel lidar signal denoising method that combines VMD with machine learning online optimization (MLOO) and the interval thresholding (IT) technique, named VMD-MLOO-IT, is proposed in this article. The proposed method defines new fitness functions to evaluate the result of VMD-based denoising, and selects the optimal parameters by the model which development by MLOO. In addition, IT is used to deal with the recovered signal. The experimental results demonstrate the superiority of the presented method over the other empirical mode decomposition-based and VMD-based denoising methods. |
| first_indexed | 2024-12-14T02:04:40Z |
| format | Article |
| id | doaj.art-e043ce4b173649f684de011e2d10e48d |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-14T02:04:40Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-e043ce4b173649f684de011e2d10e48d2022-12-21T23:20:55ZengIEEEIEEE Access2169-35362020-01-01822348222349410.1109/ACCESS.2020.30431829285233Signal Denoising Method Combined With Variational Mode Decomposition, Machine Learning Online Optimization and the Interval Thresholding TechniqueZhenxing Liu0https://orcid.org/0000-0003-3685-3825Jianhua Chang1https://orcid.org/0000-0003-4834-2141Hongxu Li2https://orcid.org/0000-0002-6495-2946Luyao Zhang3https://orcid.org/0000-0002-5031-5778Sicheng Chen4https://orcid.org/0000-0001-8209-2639Jiangsu Key Laboratory of Meteorological Observation and Information Processing, Nanjing University of Information Science and Technology, Nanjing, ChinaJiangsu Key Laboratory of Meteorological Observation and Information Processing, Nanjing University of Information Science and Technology, Nanjing, ChinaJiangsu Key Laboratory of Meteorological Observation and Information Processing, Nanjing University of Information Science and Technology, Nanjing, ChinaJiangsu Key Laboratory of Meteorological Observation and Information Processing, Nanjing University of Information Science and Technology, Nanjing, ChinaJiangsu Key Laboratory of Meteorological Observation and Information Processing, Nanjing University of Information Science and Technology, Nanjing, ChinaThe signal-to-noise ratio of lidar signals decreases rapidly with an increase in distance, which seriously affects the application of lidar detection technology. Variational mode decomposition (VMD) has performed optimality in dealing with noise, but the number of modes, K, and the penalty parameter, α, must be preset. Therefore, a novel lidar signal denoising method that combines VMD with machine learning online optimization (MLOO) and the interval thresholding (IT) technique, named VMD-MLOO-IT, is proposed in this article. The proposed method defines new fitness functions to evaluate the result of VMD-based denoising, and selects the optimal parameters by the model which development by MLOO. In addition, IT is used to deal with the recovered signal. The experimental results demonstrate the superiority of the presented method over the other empirical mode decomposition-based and VMD-based denoising methods.https://ieeexplore.ieee.org/document/9285233/LiDAR signal denoisingmachine learning online optimizationGaussian processvariational mode decompositionfitness function |
| spellingShingle | Zhenxing Liu Jianhua Chang Hongxu Li Luyao Zhang Sicheng Chen Signal Denoising Method Combined With Variational Mode Decomposition, Machine Learning Online Optimization and the Interval Thresholding Technique IEEE Access LiDAR signal denoising machine learning online optimization Gaussian process variational mode decomposition fitness function |
| title | Signal Denoising Method Combined With Variational Mode Decomposition, Machine Learning Online Optimization and the Interval Thresholding Technique |
| title_full | Signal Denoising Method Combined With Variational Mode Decomposition, Machine Learning Online Optimization and the Interval Thresholding Technique |
| title_fullStr | Signal Denoising Method Combined With Variational Mode Decomposition, Machine Learning Online Optimization and the Interval Thresholding Technique |
| title_full_unstemmed | Signal Denoising Method Combined With Variational Mode Decomposition, Machine Learning Online Optimization and the Interval Thresholding Technique |
| title_short | Signal Denoising Method Combined With Variational Mode Decomposition, Machine Learning Online Optimization and the Interval Thresholding Technique |
| title_sort | signal denoising method combined with variational mode decomposition machine learning online optimization and the interval thresholding technique |
| topic | LiDAR signal denoising machine learning online optimization Gaussian process variational mode decomposition fitness function |
| url | https://ieeexplore.ieee.org/document/9285233/ |
| work_keys_str_mv | AT zhenxingliu signaldenoisingmethodcombinedwithvariationalmodedecompositionmachinelearningonlineoptimizationandtheintervalthresholdingtechnique AT jianhuachang signaldenoisingmethodcombinedwithvariationalmodedecompositionmachinelearningonlineoptimizationandtheintervalthresholdingtechnique AT hongxuli signaldenoisingmethodcombinedwithvariationalmodedecompositionmachinelearningonlineoptimizationandtheintervalthresholdingtechnique AT luyaozhang signaldenoisingmethodcombinedwithvariationalmodedecompositionmachinelearningonlineoptimizationandtheintervalthresholdingtechnique AT sichengchen signaldenoisingmethodcombinedwithvariationalmodedecompositionmachinelearningonlineoptimizationandtheintervalthresholdingtechnique |