Forest Guard (Gunshot Detection) - Model testing

Edge Impulse Experts / Forest Guard (Gunshot Detection) Public

Target: Cortex-M4F 80MHz Clone this project

This lists all test data. You can manage this data through Data acquisition.

Test data

Set the 'expected outcome' for each sample to the desired outcome to automatically score the impulse.

Apply filters

Sample name	Expected outcome	Length	Accuracy	Result
643tg2is.s6	Gun	1s	100%	Gun	Show classification Show in data acquisition Show in feature explorer
643tg2is.s5	Gun	1s	100%	Gun	Show classification Show in data acquisition Show in feature explorer
643tg2is.s4	Gun	1s	100%	Gun	Show classification Show in data acquisition Show in feature explorer
643tg2is.s3	Gun	1s	100%	Gun	Show classification Show in data acquisition Show in feature explorer
643tg2is.s2	Gun	1s	100%	Gun	Show classification Show in data acquisition Show in feature explorer
643tg2is.s1	Gun	1s	100%	Gun	Show classification Show in data acquisition Show in feature explorer
8hefxy8w.s5	Gun	1s	100%	Gun	Show classification Show in data acquisition Show in feature explorer
8hefxy8w.s4	Gun	1s	100%	Gun	Show classification Show in data acquisition Show in feature explorer
8hefxy8w.s3	Gun	1s	100%	Gun	Show classification Show in data acquisition Show in feature explorer
8hefxy8w.s2	Gun	1s	100%	Gun	Show classification Show in data acquisition Show in feature explorer
8hefxy8w.s1	Gun	1s	100%	Gun	Show classification Show in data acquisition Show in feature explorer
f6dcjqul.s8	Gun	1s	100%	Gun	Show classification Show in data acquisition Show in feature explorer
f6dcjqul.s7	Gun	1s	100%	Gun	Show classification Show in data acquisition Show in feature explorer
f6dcjqul.s6	Gun	1s	100%	Gun	Show classification Show in data acquisition Show in feature explorer
f6dcjqul.s5	Gun	1s	100%	Gun	Show classification Show in data acquisition Show in feature explorer
f6dcjqul.s4	Gun	1s	100%	Gun	Show classification Show in data acquisition Show in feature explorer
f6dcjqul.s3	Gun	1s	100%	Gun	Show classification Show in data acquisition Show in feature explorer
f6dcjqul.s2	Gun	1s	100%	Gun	Show classification Show in data acquisition Show in feature explorer
f6dcjqul.s1	Gun	1s	100%	Gun	Show classification Show in data acquisition Show in feature explorer
qsxo5wct.s8	Noice	1s	100%	Noice	Show classification Show in data acquisition Show in feature explorer
qsxo5wct.s7	Noice	1s	100%	Noice	Show classification Show in data acquisition Show in feature explorer
qsxo5wct.s6	Noice	1s	100%	Noice	Show classification Show in data acquisition Show in feature explorer
qsxo5wct.s5	Noice	1s	100%	Noice	Show classification Show in data acquisition Show in feature explorer
qsxo5wct.s4	Noice	1s	100%	Noice	Show classification Show in data acquisition Show in feature explorer
qsxo5wct.s3	Noice	1s	100%	Noice	Show classification Show in data acquisition Show in feature explorer
qsxo5wct.s2	Noice	1s	100%	Noice	Show classification Show in data acquisition Show in feature explorer
qsxo5wct.s1	Noice	1s	100%	Noice	Show classification Show in data acquisition Show in feature explorer
2jot1sxs.s7	Noice	1s	100%	Noice	Show classification Show in data acquisition Show in feature explorer
2jot1sxs.s6	Noice	1s	0%	uncertain	Show classification Show in data acquisition Show in feature explorer
2jot1sxs.s5	Noice	1s	100%	Noice	Show classification Show in data acquisition Show in feature explorer
2jot1sxs.s4	Noice	1s	100%	Noice	Show classification Show in data acquisition Show in feature explorer
2jot1sxs.s3	Noice	1s	100%	Noice	Show classification Show in data acquisition Show in feature explorer
2jot1sxs.s2	Noice	1s	100%	Noice	Show classification Show in data acquisition Show in feature explorer
2jot1sxs.s1	Noice	1s	100%	Noice	Show classification Show in data acquisition Show in feature explorer

Model testing output

Results

Accuracy

97.06%

Metrics for Classifier

Metric	Value
Area under ROC Curve	1.00
Weighted average Precision	1.00
Weighted average Recall	1.00
Weighted average F1 score	1.00

Confusion matrix

Feature explorer

These users will be notified over email when this job finishes.

	Name
	Mukesh Sankhla

Test data

Model variants

Apply filters

Sample length (ms)

Sample frequency (Hz)