Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Comprehensive and Comparative Analysis between Transfer Learning and Custom Built VGG and CNN-SVM Models for Wildfire Detection

Aditya V. Jonnalagadda, Hashim A. Hashim, Andrew Harris

TL;DR

Three purpose-built models - Visual Geometry Group (VGG)-7, VGG-10, and Convolutional Neural Network (CNN)-Support Vector Machine (SVM) CNN-SVM -are rigorously compared with three pretrained models in addressing the intricacies of the wildfire detection problem.

Abstract

Contemporary Artificial Intelligence (AI) and Machine Learning (ML) research places a significant emphasis on transfer learning, showcasing its transformative potential in enhancing model performance across diverse domains. This paper examines the efficiency and effectiveness of transfer learning in the context of wildfire detection. Three purpose-built models -- Visual Geometry Group (VGG)-7, VGG-10, and Convolutional Neural Network (CNN)-Support Vector Machine(SVM) CNN-SVM -- are rigorously compared with three pretrained models -- VGG-16, VGG-19, and Residual Neural Network (ResNet) ResNet101. We trained and evaluated these models using a dataset that captures the complexities of wildfires, incorporating variables such as varying lighting conditions, time of day, and diverse terrains. The objective is to discern how transfer learning performs against models trained from scratch in addressing the intricacies of the wildfire detection problem. By assessing the performance metrics, including accuracy, precision, recall, and F1 score, a comprehensive understanding of the advantages and disadvantages of transfer learning in this specific domain is obtained. This study contributes valuable insights to the ongoing discourse, guiding future directions in AI and ML research. Keywords: Wildfire prediction, deep learning, machine learning fire, detection

Comprehensive and Comparative Analysis between Transfer Learning and Custom Built VGG and CNN-SVM Models for Wildfire Detection

TL;DR

Three purpose-built models - Visual Geometry Group (VGG)-7, VGG-10, and Convolutional Neural Network (CNN)-Support Vector Machine (SVM) CNN-SVM -are rigorously compared with three pretrained models in addressing the intricacies of the wildfire detection problem.

Abstract

Contemporary Artificial Intelligence (AI) and Machine Learning (ML) research places a significant emphasis on transfer learning, showcasing its transformative potential in enhancing model performance across diverse domains. This paper examines the efficiency and effectiveness of transfer learning in the context of wildfire detection. Three purpose-built models -- Visual Geometry Group (VGG)-7, VGG-10, and Convolutional Neural Network (CNN)-Support Vector Machine(SVM) CNN-SVM -- are rigorously compared with three pretrained models -- VGG-16, VGG-19, and Residual Neural Network (ResNet) ResNet101. We trained and evaluated these models using a dataset that captures the complexities of wildfires, incorporating variables such as varying lighting conditions, time of day, and diverse terrains. The objective is to discern how transfer learning performs against models trained from scratch in addressing the intricacies of the wildfire detection problem. By assessing the performance metrics, including accuracy, precision, recall, and F1 score, a comprehensive understanding of the advantages and disadvantages of transfer learning in this specific domain is obtained. This study contributes valuable insights to the ongoing discourse, guiding future directions in AI and ML research. Keywords: Wildfire prediction, deep learning, machine learning fire, detection

Paper Structure

This paper contains 18 sections, 3 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Computer Vision and Language Models
  3. Pretrained Models vs Custom Built Models
  4. Contributions
  5. Structure
  6. Problem Formulation
  7. Dataset and Preprocessing
  8. Methodology
  9. Custom Built CNN-SVM
  10. Custom Built VGG-7 and VGG-10
  11. Pretrained VGG-16 and VGG-19
  12. Pretrained ResNet
  13. Results
  14. Software, Libraries Used, and Dataset
  15. Compartive Results
  16. ...and 3 more sections

Figures (3)

  • Figure 1: Sample of images in the training dataset. These images include synthetic images created by data augmentation techniques like rotation, translation, scaling, brightness adjustment, and the introduction of Gaussian noise (for more details visit jonnalagadda2024segnet).
  • Figure 2: (a) Working principle (schematic) of transfer learning and (b) Sample Images from ImageNet dataset deng2009imagenet.
  • Figure 3: Comparative analysis and performance measures presenting training and validation accuracy versus training and validation loss of the proposed (a) VGG-7, (b) VGG-10, (c) CNN-SVM, (d) VGG-16, (e) VGG-19, and (f) ResNet101.