notesum.ai

Published at November 12

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

cs.CV

cs.AI

Released Date: November 12, 2024

Authors: Aditya V. Jonnalagadda¹, Hashim A. Hashim¹, Andrew Harris¹

Aff.: ¹Institution not provided

Arxiv: http://arxiv.org/abs/2411.08171v1

	Custom $\%$			Pretrained $\%$
	VGG-7	VGG-10	CNN-SVM	VGG-16	VGG-19	ResNet 101
Training Accuracy	$99.33$	$98.78$	$99.1$	$100\%$	$100$	$100$
Training Loss	$0.014$	$0.029$	$0.022$	$0$	$0$	$0$
Validation Accuracy	$99.32$	$99.3$	$98.4$	$99.99$	$98.98$	$89.98$
Recall	$97.84$	$97.54$	$98.46$	$99.69$	$99.38$	$92.61$
Accuracy	$96.54$	$96.72$	$96.91$	$99.45$	$99.09$	$92.73$
Precision	$96.36$	$96.94$	$96.38$	$99.38$	$99.08$	$94.95$