Improved RPCA Method via Fractional Function-Based Structure and Its Application
With the advancement of oil logging techniques, vast amounts of data have been generated. However, this data often contains significant redundancy and noise. The logging data must be denoised before it is used for oil logging recognition. Hence, this paper proposed an improved robust principal compo...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Information |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2078-2489/16/1/69 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832588336754065408 |
|---|---|
| author | Yong-Ke Pan Shuang Peng |
| author_facet | Yong-Ke Pan Shuang Peng |
| author_sort | Yong-Ke Pan |
| collection | DOAJ |
| description | With the advancement of oil logging techniques, vast amounts of data have been generated. However, this data often contains significant redundancy and noise. The logging data must be denoised before it is used for oil logging recognition. Hence, this paper proposed an improved robust principal component analysis algorithm (IRPCA) for logging data denoising, which addresses the problems of various noises in oil logging data acquisition and the limitations of conventional data processing methods. The IRPCA algorithm enhances both the efficiency of the model and the accuracy of low-rank matrix recovery. This improvement is achieved primarily by introducing the approximate zero norm based on the fractional function structure and by adding weighted kernel parametrization and penalty terms to enhance the model’s capability in handling complex matrices. The efficacy of the proposed IRPCA algorithm has been verified through simulation experiments, demonstrating its superiority over the widely used RPCA algorithm. We then present a denoising method tailored to the characteristics of logging data and based on the IRPCA algorithm. This method first involves the segregation of the original logging data to acquire background and foreground information. The background information is subsequently further separated to isolate the factual background and noise, resulting in the denoised logging data. The results indicate that the IRPCA algorithm is practical and effective when applied to the denoising of actual logging data. |
| format | Article |
| id | doaj-art-3d567ccbb36a4603960c19f50c11a35e |
| institution | Kabale University |
| issn | 2078-2489 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Information |
| spelling | doaj-art-3d567ccbb36a4603960c19f50c11a35e2025-01-24T13:35:20ZengMDPI AGInformation2078-24892025-01-011616910.3390/info16010069Improved RPCA Method via Fractional Function-Based Structure and Its ApplicationYong-Ke Pan0Shuang Peng1College of Electronic Science and Technology, National University of Defense Technology, Changsha 410000, ChinaCollege of Electronic Science and Technology, National University of Defense Technology, Changsha 410000, ChinaWith the advancement of oil logging techniques, vast amounts of data have been generated. However, this data often contains significant redundancy and noise. The logging data must be denoised before it is used for oil logging recognition. Hence, this paper proposed an improved robust principal component analysis algorithm (IRPCA) for logging data denoising, which addresses the problems of various noises in oil logging data acquisition and the limitations of conventional data processing methods. The IRPCA algorithm enhances both the efficiency of the model and the accuracy of low-rank matrix recovery. This improvement is achieved primarily by introducing the approximate zero norm based on the fractional function structure and by adding weighted kernel parametrization and penalty terms to enhance the model’s capability in handling complex matrices. The efficacy of the proposed IRPCA algorithm has been verified through simulation experiments, demonstrating its superiority over the widely used RPCA algorithm. We then present a denoising method tailored to the characteristics of logging data and based on the IRPCA algorithm. This method first involves the segregation of the original logging data to acquire background and foreground information. The background information is subsequently further separated to isolate the factual background and noise, resulting in the denoised logging data. The results indicate that the IRPCA algorithm is practical and effective when applied to the denoising of actual logging data.https://www.mdpi.com/2078-2489/16/1/69RPCAoil logging data denoisinglow-rank matrix recoveryfractional function |
| spellingShingle | Yong-Ke Pan Shuang Peng Improved RPCA Method via Fractional Function-Based Structure and Its Application Information RPCA oil logging data denoising low-rank matrix recovery fractional function |
| title | Improved RPCA Method via Fractional Function-Based Structure and Its Application |
| title_full | Improved RPCA Method via Fractional Function-Based Structure and Its Application |
| title_fullStr | Improved RPCA Method via Fractional Function-Based Structure and Its Application |
| title_full_unstemmed | Improved RPCA Method via Fractional Function-Based Structure and Its Application |
| title_short | Improved RPCA Method via Fractional Function-Based Structure and Its Application |
| title_sort | improved rpca method via fractional function based structure and its application |
| topic | RPCA oil logging data denoising low-rank matrix recovery fractional function |
| url | https://www.mdpi.com/2078-2489/16/1/69 |
| work_keys_str_mv | AT yongkepan improvedrpcamethodviafractionalfunctionbasedstructureanditsapplication AT shuangpeng improvedrpcamethodviafractionalfunctionbasedstructureanditsapplication |