Overcoming Overfitting Challenges with HOG Feature Extraction and XGBoost-Based Classification for Concrete Crack Monitoring
This study proposes a method that combines Histogram of Oriented Gradients (HOG) feature extraction and Extreme Gradient Boosting (XGBoost) classification to resolve the challenges of concrete crack monitoring. The purpose of the study is to address the common issue of overfitting in machine learnin...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Polish Academy of Sciences
2023-09-01
|
| Series: | International Journal of Electronics and Telecommunications |
| Subjects: | |
| Online Access: | https://journals.pan.pl/Content/128298/PDF/22-23-4181-Barkiah-sk.pdf |
| _version_ | 1797729151711444992 |
|---|---|
| author | Ida Barkiah Yuslena Sari |
| author_facet | Ida Barkiah Yuslena Sari |
| author_sort | Ida Barkiah |
| collection | DOAJ |
| description | This study proposes a method that combines Histogram of Oriented Gradients (HOG) feature extraction and Extreme Gradient Boosting (XGBoost) classification to resolve the challenges of concrete crack monitoring. The purpose of the study is to address the common issue of overfitting in machine learning models. The research uses a dataset of 40,000 images of concrete cracks and HOG feature extraction to identify relevant patterns. Classification is performed using the ensemble method XGBoost, with a focus on optimizing its hyperparameters. This study evaluates the efficacy of XGBoost in comparison to other ensemble methods, such as Random Forest and AdaBoost. XGBoost outperforms the other algorithms in terms of accuracy, precision, recall, and F1-score, as demonstrated by the results. The proposed method obtains an accuracy of 96.95% with optimized hyperparameters, a recall of 96.10%, a precision of 97.90%, and an F1-score of 97%. By optimizing the number of trees hyperparameter, 1200 trees yield the greatest performance. The results demonstrate the efficacy of HOG-based feature extraction and XGBoost for accurate and dependable classification of concrete fractures, overcoming the overfitting issues that are typically encountered in such tasks. |
| first_indexed | 2024-03-12T11:25:55Z |
| format | Article |
| id | doaj.art-2861a204f0304d2da5eb8ce2964963d7 |
| institution | Directory Open Access Journal |
| issn | 2081-8491 2300-1933 |
| language | English |
| last_indexed | 2024-03-12T11:25:55Z |
| publishDate | 2023-09-01 |
| publisher | Polish Academy of Sciences |
| record_format | Article |
| series | International Journal of Electronics and Telecommunications |
| spelling | doaj.art-2861a204f0304d2da5eb8ce2964963d72023-09-01T08:56:54ZengPolish Academy of SciencesInternational Journal of Electronics and Telecommunications2081-84912300-19332023-09-01vol. 69No 3571577https://doi.org/10.24425/ijet.2023.146509Overcoming Overfitting Challenges with HOG Feature Extraction and XGBoost-Based Classification for Concrete Crack MonitoringIda Barkiah0Yuslena Sari1Department of Civil Engineering, Universitas Lambung, Mangkurat, IndonesiaDepartment of Information Technology, Universitas Lambung Mangkurat, IndonesiaThis study proposes a method that combines Histogram of Oriented Gradients (HOG) feature extraction and Extreme Gradient Boosting (XGBoost) classification to resolve the challenges of concrete crack monitoring. The purpose of the study is to address the common issue of overfitting in machine learning models. The research uses a dataset of 40,000 images of concrete cracks and HOG feature extraction to identify relevant patterns. Classification is performed using the ensemble method XGBoost, with a focus on optimizing its hyperparameters. This study evaluates the efficacy of XGBoost in comparison to other ensemble methods, such as Random Forest and AdaBoost. XGBoost outperforms the other algorithms in terms of accuracy, precision, recall, and F1-score, as demonstrated by the results. The proposed method obtains an accuracy of 96.95% with optimized hyperparameters, a recall of 96.10%, a precision of 97.90%, and an F1-score of 97%. By optimizing the number of trees hyperparameter, 1200 trees yield the greatest performance. The results demonstrate the efficacy of HOG-based feature extraction and XGBoost for accurate and dependable classification of concrete fractures, overcoming the overfitting issues that are typically encountered in such tasks.https://journals.pan.pl/Content/128298/PDF/22-23-4181-Barkiah-sk.pdfhogxgboostclassificationfeature extractionconcrete crack monitoring |
| spellingShingle | Ida Barkiah Yuslena Sari Overcoming Overfitting Challenges with HOG Feature Extraction and XGBoost-Based Classification for Concrete Crack Monitoring International Journal of Electronics and Telecommunications hog xgboost classification feature extraction concrete crack monitoring |
| title | Overcoming Overfitting Challenges with HOG Feature Extraction and XGBoost-Based Classification for Concrete Crack Monitoring |
| title_full | Overcoming Overfitting Challenges with HOG Feature Extraction and XGBoost-Based Classification for Concrete Crack Monitoring |
| title_fullStr | Overcoming Overfitting Challenges with HOG Feature Extraction and XGBoost-Based Classification for Concrete Crack Monitoring |
| title_full_unstemmed | Overcoming Overfitting Challenges with HOG Feature Extraction and XGBoost-Based Classification for Concrete Crack Monitoring |
| title_short | Overcoming Overfitting Challenges with HOG Feature Extraction and XGBoost-Based Classification for Concrete Crack Monitoring |
| title_sort | overcoming overfitting challenges with hog feature extraction and xgboost based classification for concrete crack monitoring |
| topic | hog xgboost classification feature extraction concrete crack monitoring |
| url | https://journals.pan.pl/Content/128298/PDF/22-23-4181-Barkiah-sk.pdf |
| work_keys_str_mv | AT idabarkiah overcomingoverfittingchallengeswithhogfeatureextractionandxgboostbasedclassificationforconcretecrackmonitoring AT yuslenasari overcomingoverfittingchallengeswithhogfeatureextractionandxgboostbasedclassificationforconcretecrackmonitoring |