A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Efficient data dimensionality reduction method for improving road crack classification algorithms
Automatic crack classification plays an essential role in road maintenance. Using many features for the classification is inefficient for implementing embedded systems with low computational resources makes it difficult. Therefore, this work proposes a new data dimensionality reduction (DDR) for crack classification algorithms (DDR4CC). DDR4CC reduces the required information about the cracks to only four features. Using these features, the images can be classified into longitudinal, transverse, and alligator cracks or healthy pavement. DDR4CC is compared with eight DDR methods, and the reduced set of features is analyzed using five different classification algorithms. Besides, five different datasets, generated by a combination of several public datasets, are used. We are proposing a simple DDR method with high interpretability of the data, obtaining very fast computation and high accuracy. Experiments show that DDR4CC enhances the results of the classification algorithms, providing almost perfect classifiers with a minimum computation time.
Efficient data dimensionality reduction method for improving road crack classification algorithms
Automatic crack classification plays an essential role in road maintenance. Using many features for the classification is inefficient for implementing embedded systems with low computational resources makes it difficult. Therefore, this work proposes a new data dimensionality reduction (DDR) for crack classification algorithms (DDR4CC). DDR4CC reduces the required information about the cracks to only four features. Using these features, the images can be classified into longitudinal, transverse, and alligator cracks or healthy pavement. DDR4CC is compared with eight DDR methods, and the reduced set of features is analyzed using five different classification algorithms. Besides, five different datasets, generated by a combination of several public datasets, are used. We are proposing a simple DDR method with high interpretability of the data, obtaining very fast computation and high accuracy. Experiments show that DDR4CC enhances the results of the classification algorithms, providing almost perfect classifiers with a minimum computation time.
Efficient data dimensionality reduction method for improving road crack classification algorithms
Rodriguez‐Lozano, Francisco J. (author) / Gámez‐Granados, Juan C. (author) / Palomares, Jose M. (author) / Olivares, Joaquín (author)
Computer‐Aided Civil and Infrastructure Engineering ; 38 ; 2339-2354
2023-11-01
16 pages
Article (Journal)
Electronic Resource
English
Dimensionality Reduction Based on Tensor Modeling for Classification Methods
| Online Contents | 2009
Practical Method for Solving Some Problems of Classification and Dimensionality Reduction
| British Library Online Contents | 1994
UL-Isomap based nonlinear dimensionality reduction for hyperspectral imagery classification
| Online Contents | 2014
Locality-Preserving Dimensionality Reduction and Classification for Hyperspectral Image Analysis
| Online Contents | 2012
Laplacian Eigenmaps-Based Polarimetric Dimensionality Reduction for SAR Image Classification
| Online Contents | 2012