DeepFire: A Novel Dataset and Deep Transfer Learning Benchmark for Forest Fire Detection

Table 6

Comparative evaluation.

Metrics	LR	SVM	Proposed approach
Prediction accuracy	0.9026	0.9131	0.9500
ER	0.0973	0.0868	0.0500
Precision	0.9090	0.9025	0.9572
Recall	0.8947	0.9263	0.9421
F1	0.9017	0.9158	0.9496