Example of data enhancement.
<div><p>Inspection and diagnosis of construction projects involves health monitoring of buildings and related facilities, and the utilization of renewable energy sources, such as solar energy, is critical to the smooth operation of modern construction projects. The detection of solar cel...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | , |
| Published: |
2025
|
| Subjects: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1852015902307909632 |
|---|---|
| author | Jiayue Zhang (7832669) |
| author2 | Xinxin Yi (3932963) Heng Wang (76752) |
| author2_role | author author |
| author_facet | Jiayue Zhang (7832669) Xinxin Yi (3932963) Heng Wang (76752) |
| author_role | author |
| dc.creator.none.fl_str_mv | Jiayue Zhang (7832669) Xinxin Yi (3932963) Heng Wang (76752) |
| dc.date.none.fl_str_mv | 2025-10-09T17:34:35Z |
| dc.identifier.none.fl_str_mv | 10.1371/journal.pone.0333939.g007 |
| dc.relation.none.fl_str_mv | https://figshare.com/articles/figure/Example_of_data_enhancement_/30320166 |
| dc.rights.none.fl_str_mv | CC BY 4.0 info:eu-repo/semantics/openAccess |
| dc.subject.none.fl_str_mv | Cell Biology Neuroscience Space Science Biological Sciences not elsewhere classified Mathematical Sciences not elsewhere classified Information Systems not elsewhere classified xlink "> inspection modern construction projects like linear attention crayfish optimization algorithm crawfish optimization algorithm target detail features solar cell defects renewable energy sources pvelad datasets show hybrid model cmns existing deep learning ultimate detection accuracy solar energy deep learning two datasets image features smooth operation recovery ability network hyperparameters model performance mlla module lightweight characteristics experimental results detection accuracy considerable potential building photovoltaics baseline model |
| dc.title.none.fl_str_mv | Example of data enhancement. |
| dc.type.none.fl_str_mv | Image Figure info:eu-repo/semantics/publishedVersion image |
| description | <div><p>Inspection and diagnosis of construction projects involves health monitoring of buildings and related facilities, and the utilization of renewable energy sources, such as solar energy, is critical to the smooth operation of modern construction projects. The detection of solar cell defects is related to the reliability and efficiency of building photovoltaics and has become an area of interest. Existing deep learning-based solar cell defect detection models significantly improve the accuracy of solar cell defect detection, however, deep learning-based solar cell defect detection models ignore the effect of network hyperparameters on their model performance. In this study, the hybrid model CMNS-YOLO, which combines the crawfish optimization algorithm with the MNS-YOLO model, is proposed to achieve the ultimate detection accuracy. First, Mamba-Like Linear Attention is introduced to design the C2f-MLLA module to improve the target feature representation capability of solar cell sheet defects; second, Bidirectional feature pyramid frequency aware feature fusion network is designed to enhance the recovery ability of target detail features as well as the fusion ability of image features; then ShapeIoU is used to solve the target aspect ratio misalignment problem and construct the improved MNS-YOLO network; finally, COA is utilized to adjust the parameters of the MNS-YOLO network. Experimental results on the PV-Multi-Defect and PVELAD datasets show that compared with the baseline model, the detection accuracy of the proposed model on the two datasets is improved by 6.3% and 2.3% while maintaining the lightweight characteristics of the model. Therefore, the proposed method has considerable potential in the field of solar cell defect detection.</p></div> |
| eu_rights_str_mv | openAccess |
| id | Manara_9b0ef4d36bce97c8daeec7767d0bca01 |
| identifier_str_mv | 10.1371/journal.pone.0333939.g007 |
| network_acronym_str | Manara |
| network_name_str | ManaraRepo |
| oai_identifier_str | oai:figshare.com:article/30320166 |
| publishDate | 2025 |
| repository.mail.fl_str_mv | |
| repository.name.fl_str_mv | |
| repository_id_str | |
| rights_invalid_str_mv | CC BY 4.0 |
| spelling | Example of data enhancement.Jiayue Zhang (7832669)Xinxin Yi (3932963)Heng Wang (76752)Cell BiologyNeuroscienceSpace ScienceBiological Sciences not elsewhere classifiedMathematical Sciences not elsewhere classifiedInformation Systems not elsewhere classifiedxlink "> inspectionmodern construction projectslike linear attentioncrayfish optimization algorithmcrawfish optimization algorithmtarget detail featuressolar cell defectsrenewable energy sourcespvelad datasets showhybrid model cmnsexisting deep learningultimate detection accuracysolar energydeep learningtwo datasetsimage featuressmooth operationrecovery abilitynetwork hyperparametersmodel performancemlla modulelightweight characteristicsexperimental resultsdetection accuracyconsiderable potentialbuilding photovoltaicsbaseline model<div><p>Inspection and diagnosis of construction projects involves health monitoring of buildings and related facilities, and the utilization of renewable energy sources, such as solar energy, is critical to the smooth operation of modern construction projects. The detection of solar cell defects is related to the reliability and efficiency of building photovoltaics and has become an area of interest. Existing deep learning-based solar cell defect detection models significantly improve the accuracy of solar cell defect detection, however, deep learning-based solar cell defect detection models ignore the effect of network hyperparameters on their model performance. In this study, the hybrid model CMNS-YOLO, which combines the crawfish optimization algorithm with the MNS-YOLO model, is proposed to achieve the ultimate detection accuracy. First, Mamba-Like Linear Attention is introduced to design the C2f-MLLA module to improve the target feature representation capability of solar cell sheet defects; second, Bidirectional feature pyramid frequency aware feature fusion network is designed to enhance the recovery ability of target detail features as well as the fusion ability of image features; then ShapeIoU is used to solve the target aspect ratio misalignment problem and construct the improved MNS-YOLO network; finally, COA is utilized to adjust the parameters of the MNS-YOLO network. Experimental results on the PV-Multi-Defect and PVELAD datasets show that compared with the baseline model, the detection accuracy of the proposed model on the two datasets is improved by 6.3% and 2.3% while maintaining the lightweight characteristics of the model. Therefore, the proposed method has considerable potential in the field of solar cell defect detection.</p></div>2025-10-09T17:34:35ZImageFigureinfo:eu-repo/semantics/publishedVersionimage10.1371/journal.pone.0333939.g007https://figshare.com/articles/figure/Example_of_data_enhancement_/30320166CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/303201662025-10-09T17:34:35Z |
| spellingShingle | Example of data enhancement. Jiayue Zhang (7832669) Cell Biology Neuroscience Space Science Biological Sciences not elsewhere classified Mathematical Sciences not elsewhere classified Information Systems not elsewhere classified xlink "> inspection modern construction projects like linear attention crayfish optimization algorithm crawfish optimization algorithm target detail features solar cell defects renewable energy sources pvelad datasets show hybrid model cmns existing deep learning ultimate detection accuracy solar energy deep learning two datasets image features smooth operation recovery ability network hyperparameters model performance mlla module lightweight characteristics experimental results detection accuracy considerable potential building photovoltaics baseline model |
| status_str | publishedVersion |
| title | Example of data enhancement. |
| title_full | Example of data enhancement. |
| title_fullStr | Example of data enhancement. |
| title_full_unstemmed | Example of data enhancement. |
| title_short | Example of data enhancement. |
| title_sort | Example of data enhancement. |
| topic | Cell Biology Neuroscience Space Science Biological Sciences not elsewhere classified Mathematical Sciences not elsewhere classified Information Systems not elsewhere classified xlink "> inspection modern construction projects like linear attention crayfish optimization algorithm crawfish optimization algorithm target detail features solar cell defects renewable energy sources pvelad datasets show hybrid model cmns existing deep learning ultimate detection accuracy solar energy deep learning two datasets image features smooth operation recovery ability network hyperparameters model performance mlla module lightweight characteristics experimental results detection accuracy considerable potential building photovoltaics baseline model |