Open Access

Deep CNN and twin support vector machine based model for detecting potholes in road network

Mohit Misra

Mohit Misra

Department of Electronics and Communication Engineering, Faculty of Engineering and Technology, SRM Institute of Science and TechnologyGhaziabad, India
Orcid profile
Search for this author on
Sciendo|Google Scholar
Misra, Mohit
, 
Saptarshi Gupta

Saptarshi Gupta

Department of Electronics and Communication Engineering, Faculty of Engineering and Technology, SRM Institute of Science and TechnologyGhaziabad, India
Orcid profile
Search for this author on
Sciendo|Google Scholar
Gupta, Saptarshi
 and 
Shailesh Tiwari

Shailesh Tiwari

School of Computer Science Engineering & Technology, Bennett UniversityGreater Noida, India
Orcid profile
Search for this author on
Sciendo|Google Scholar
Tiwari, Shailesh
  
Aug 11, 2025
Deep CNN and twin support vector machine based model for detecting potholes in road network's Cover Image
About this article
Previous Article
Next Article
Cite
Download Cover
Article Category: Research Article
Published Online: Aug 11, 2025
Received: Apr 14, 2025
DOI: https://doi.org/10.2478/ijssis-2025-0099
Keywords
© 2025 Mohit Misra et al., published by Sciendo
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Figure 1:

Illustrates the proposed pothole detection model based on deep CNN and TSVM. CNN, convolutional neural network; TSVM, twin support vector machine.
Illustrates the proposed pothole detection model based on deep CNN and TSVM. CNN, convolutional neural network; TSVM, twin support vector machine.

Figure 2:

Proposed deep CNN-based feature extractor model. CNN, convolutional neural network.
Proposed deep CNN-based feature extractor model. CNN, convolutional neural network.

Figure 3:

Depicts the confusion matrix of proposed deep CNN-TPSVM model. CNN, convolutional neural network; TPSVM, twin parametric support vector machine.
Depicts the confusion matrix of proposed deep CNN-TPSVM model. CNN, convolutional neural network; TPSVM, twin parametric support vector machine.

Figure 4:

Depicts the confusion matrix of other existing models.
Depicts the confusion matrix of other existing models.

Figure 5:

Comparative analysis of the results using proposed deep CNN-TPSVM model and existing models based on different performance parameters. CNN, convolutional neural network; TPSVM, twin parametric support vector machine.
Comparative analysis of the results using proposed deep CNN-TPSVM model and existing models based on different performance parameters. CNN, convolutional neural network; TPSVM, twin parametric support vector machine.

Figure 6:

Demonstrates the accuracy rate of the proposed deep CNN-TPSVM model based on training and validation sets. CNN, convolutional neural network; TPSVM, twin parametric support vector machine.
Demonstrates the accuracy rate of the proposed deep CNN-TPSVM model based on training and validation sets. CNN, convolutional neural network; TPSVM, twin parametric support vector machine.

Figure 7:

Demonstrates the loss rate of the proposed deep CNN-TPSVM model based on training and validation sets. CNN, convolutional neural network; TPSVM, twin parametric support vector machine.
Demonstrates the loss rate of the proposed deep CNN-TPSVM model based on training and validation sets. CNN, convolutional neural network; TPSVM, twin parametric support vector machine.

Figure 8:

Depicts the AUC of proposed deep CNN-TPSVM model and other existing techniques. CNN, convolutional neural network; TPSVM, twin parametric support vector machine.
Depicts the AUC of proposed deep CNN-TPSVM model and other existing techniques. CNN, convolutional neural network; TPSVM, twin parametric support vector machine.

Depicts the simulation results of the proposed deep CNN-TPSVM model and other existing models

Technique Accuracy (%) Recall (%) Precision (%) F1-score (%)
ANN 79.73 87.32 85.82 86.56
SVM 82.60 88.83 88.01 90.31
VGG16 84.43 90.58 88.82 90.99
VGG19 87.65 91.97 91.55 93.87
InceptionV3 90.06 92.55 94.87 95.69
DBN model 93.04 94.30 96.31 96.92
Proposed deep CNN-TPSVM Model 96.12 98.13 97.79 97.96
Language:
English
Publication timeframe:
1 times per year
Journal Subjects:
Engineering, Introductions and Overviews, Engineering, other
Journal RSS Feed