Research on the improvement method of imbalance of ground penetrating radar image data
Abstract Ground Penetrating Radar (GPR) has been widely used to detect highway pavement structures. In recent years, deep learning techniques have achieved significant success in image recognition, which is potentially relevant for interpreting ground-penetrating radar data. This is because the vari...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-87123-3 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832585700648681472 |
|---|---|
| author | Ligang Cao Lei Liu Congde Lu Ruimin Chen |
| author_facet | Ligang Cao Lei Liu Congde Lu Ruimin Chen |
| author_sort | Ligang Cao |
| collection | DOAJ |
| description | Abstract Ground Penetrating Radar (GPR) has been widely used to detect highway pavement structures. In recent years, deep learning techniques have achieved significant success in image recognition, which is potentially relevant for interpreting ground-penetrating radar data. This is because the various types of damage develop at different levels and in different quantities. So the number of datasets of various types of road injuries is not balanced. This leads to poor accuracy of deep learning for injury classification. And the cost of collecting a large amount of data in the field is higher. The aim of this paper is to improve classification accuracy at a lower cost relative to field collection, we propose a damage data expansion method based on generative adversarial network, which consists of encoder and a generative adversarial network. We have made a number of improvements to the generator and discriminator, as well as to the newly added encoder. All of these improvements have improved the generation results in terms of metrics. So that the network can stably generate damage samples with a small number of samples to improve the classification network’s accuracy. The effect on accuracy by varying the proportions of different kinds of samples and traditional expansion methods is also explored. The improvement of the classification network accuracy and FlD metrics illustrates the better performance of the proposed method. |
| format | Article |
| id | doaj-art-4119ae74f8d04d3d839c2dc37089f077 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-4119ae74f8d04d3d839c2dc37089f0772025-01-26T12:33:51ZengNature PortfolioScientific Reports2045-23222025-01-0115111410.1038/s41598-025-87123-3Research on the improvement method of imbalance of ground penetrating radar image dataLigang Cao0Lei Liu1Congde Lu2Ruimin Chen3Key Laboratory of Earth Exploration and Information Techniques of Ministry of Education, Chengdu University of TechnologyKey Laboratory of Earth Exploration and Information Techniques of Ministry of Education, Chengdu University of TechnologyKey Laboratory of Earth Exploration and Information Techniques of Ministry of Education, Chengdu University of TechnologyKey Laboratory of Earth Exploration and Information Techniques of Ministry of Education, Chengdu University of TechnologyAbstract Ground Penetrating Radar (GPR) has been widely used to detect highway pavement structures. In recent years, deep learning techniques have achieved significant success in image recognition, which is potentially relevant for interpreting ground-penetrating radar data. This is because the various types of damage develop at different levels and in different quantities. So the number of datasets of various types of road injuries is not balanced. This leads to poor accuracy of deep learning for injury classification. And the cost of collecting a large amount of data in the field is higher. The aim of this paper is to improve classification accuracy at a lower cost relative to field collection, we propose a damage data expansion method based on generative adversarial network, which consists of encoder and a generative adversarial network. We have made a number of improvements to the generator and discriminator, as well as to the newly added encoder. All of these improvements have improved the generation results in terms of metrics. So that the network can stably generate damage samples with a small number of samples to improve the classification network’s accuracy. The effect on accuracy by varying the proportions of different kinds of samples and traditional expansion methods is also explored. The improvement of the classification network accuracy and FlD metrics illustrates the better performance of the proposed method.https://doi.org/10.1038/s41598-025-87123-3Ground Penetrating Radar (GPR)Generative Adversarial Network (GAN)Unbalanced dataset |
| spellingShingle | Ligang Cao Lei Liu Congde Lu Ruimin Chen Research on the improvement method of imbalance of ground penetrating radar image data Scientific Reports Ground Penetrating Radar (GPR) Generative Adversarial Network (GAN) Unbalanced dataset |
| title | Research on the improvement method of imbalance of ground penetrating radar image data |
| title_full | Research on the improvement method of imbalance of ground penetrating radar image data |
| title_fullStr | Research on the improvement method of imbalance of ground penetrating radar image data |
| title_full_unstemmed | Research on the improvement method of imbalance of ground penetrating radar image data |
| title_short | Research on the improvement method of imbalance of ground penetrating radar image data |
| title_sort | research on the improvement method of imbalance of ground penetrating radar image data |
| topic | Ground Penetrating Radar (GPR) Generative Adversarial Network (GAN) Unbalanced dataset |
| url | https://doi.org/10.1038/s41598-025-87123-3 |
| work_keys_str_mv | AT ligangcao researchontheimprovementmethodofimbalanceofgroundpenetratingradarimagedata AT leiliu researchontheimprovementmethodofimbalanceofgroundpenetratingradarimagedata AT congdelu researchontheimprovementmethodofimbalanceofgroundpenetratingradarimagedata AT ruiminchen researchontheimprovementmethodofimbalanceofgroundpenetratingradarimagedata |