Nekhil R / Fire Detection with sensor fusion Public
Target: Cortex-M7 216MHz Clone this project

Test data

Set confidence thresholds
Model variants
Test 'Unoptimized (float32)' model Test 'Quantized (int8)' model
Set the 'expected outcome' for each sample to the desired outcome to automatically score the impulse.
Sample name Expected outcome Length Accuracy Result
Fire.3k9f7pus Fire 10s 100% 7 Fire
Show classification Show in data acquisition
Fire.3k9f5nmg Fire 10s 100% 7 Fire
Show classification Show in data acquisition
Fire.3k9f19pd Fire 10s 100% 7 Fire
Show classification Show in data acquisition
Fire.3k9eub4l Fire 10s 100% 7 Fire
Show classification Show in data acquisition
Fire.3k9eqec1 Fire 10s 100% 7 Fire
Show classification Show in data acquisition
Fire.3k9ejsdd Fire 10s 14% 6 No fire, 1 Fire
Show classification Show in data acquisition
No fire.3k9e1kag No fire 10s 100% 7 No fire
Show classification Show in data acquisition
No fire.3k9dkmek No fire 10s 100% 7 No fire
Show classification Show in data acquisition
No fire.3k9dfap9 No fire 10s 100% 7 No fire
Show classification Show in data acquisition
No fire.3k9depqu No fire 10s 100% 7 No fire
Show classification Show in data acquisition
No fire.3k9de9hr No fire 10s 100% 7 No fire
Show classification Show in data acquisition
No fire.3k9dc6n0 No fire 10s 100% 7 No fire
Show classification Show in data acquisition

Model testing output

Results

Model version:
Accuracy
92.86%

Confusion matrix

Loading...

Feature explorer

Loading...
Help & documentation Get help on the forum Send feedback Contact sales
Join us
Terms of Service Privacy policy