Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

A flowchart for methodology.

More »

Fig 1 Expand

Fig 2.

Architecture of YOLOv10 [24].

More »

Fig 2 Expand

Table 1.

Description and recommended ranges of key YOLO hyperparameters.

More »

Table 1 Expand

Fig 3.

GWO Strategy [36].

More »

Fig 3 Expand

Fig 4.

Pedal Scent Marking and Sniffing Behaviors of Brown-Bears, (a) Pedal Marks in an Area.

(b-d) A brown-Bear Stretching to its Pedal Marks [39].

More »

Fig 4 Expand

Fig 5.

The Flowchart of the Hybrid GWO-BBOA Optimization Process.

More »

Fig 5 Expand

Fig 6.

Pseudocode of the proposed Hybrid GWO-BBOA algorithm.

More »

Fig 6 Expand

Table 2.

Performance results of the YOLOv10s model on the Arson Detection Dataset.

More »

Table 2 Expand

Fig 7.

Evolution of training losses and evaluation metrics (precision, recall, mAP@0.5, mAP@0.5:0.95) over 100 epochs.

More »

Fig 7 Expand

Table 3.

Performance results of YOLO v10 versions on arson dataset.

More »

Table 3 Expand

Table 4.

Parameters selected.

More »

Table 4 Expand

Table 5.

Performance results of YOLOv10s using different optimization algorithms on the arson detection dataset.

More »

Table 5 Expand

Fig 8.

Visual comparison of YOLOv10 arson detection results.

(A) Ground truth annotations for fire/arson events. (B) Predicted bounding boxes generated by YOLOv10 optimized with the proposed GWO-BBOA algorithm.

More »

Fig 8 Expand

Table 6.

Pairwise T-test results comparing the proposed GWO-BBOA with PSO, GWO, and BBOA.

More »

Table 6 Expand

Table 7.

Presents a comparison between our study, Abbod et al. and Singh et al.

More »

Table 7 Expand

Fig 9.

Visualized results for a single arson scene, showing (A) the original image, (B) YOLO v10 bounding‑box, and (C) Grad‑CAM heatmap overlay.

More »

Fig 9 Expand