yuki / Road-Surface-Recognition Public
Target: xiao nRF52840 sense Clone this project

Test data

Set 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.

Apply filters

Sample name Expected outcome Length Accuracy Result
smooth-flat-30km_h.s7 smooth 5s 38% 5 uncertain, 3 smooth
Show classification Show in data acquisition Show in feature explorer
smooth-flat-30km_h.s2 smooth 5s 0% 4 medium, 4 uncertain
Show classification Show in data acquisition Show in feature explorer
medium-pavement-4.s5 medium 5s 38% 4 uncertain, 3 medium, 1 rough
Show classification Show in data acquisition Show in feature explorer
medium-pavement-12.s2 rough 5s 0% 8 medium
Show classification Show in data acquisition Show in feature explorer
unpaved-road(grass)-1.s2 rough 5s 0% 8 uncertain
Show classification Show in data acquisition Show in feature explorer
sprint-5.s9 sprint 5s 100% 8 sprint
Show classification Show in data acquisition Show in feature explorer
sprint-5.s4 sprint 5s 100% 8 sprint
Show classification Show in data acquisition Show in feature explorer
sprint-4.s4 sprint 5s 0% 7 medium, 1 uncertain
Show classification Show in data acquisition Show in feature explorer
sprint-3.s7 sprint 5s 50% 4 sprint, 3 uncertain, 1 medium
Show classification Show in data acquisition Show in feature explorer
sprint-3.s2 sprint 5s 100% 8 sprint
Show classification Show in data acquisition Show in feature explorer
sprint-2.s2 sprint 5s 100% 9 sprint
Show classification Show in data acquisition Show in feature explorer
sprint-1.s9 sprint 5s 100% 8 sprint
Show classification Show in data acquisition Show in feature explorer
sprint-1.s4 sprint 5s 100% 8 sprint
Show classification Show in data acquisition Show in feature explorer
idle-uphill-1.s5 idle 5s 100% 8 idle
Show classification Show in data acquisition Show in feature explorer
idle-3.s5 idle 5s 100% 8 idle
Show classification Show in data acquisition Show in feature explorer
idle-2.s12 idle 5s 100% 8 idle
Show classification Show in data acquisition Show in feature explorer
idle-2.s7 idle 5s 0% 6 smooth, 2 uncertain
Show classification Show in data acquisition Show in feature explorer
idle-2.s2 idle 5s 100% 8 idle
Show classification Show in data acquisition Show in feature explorer
idle-1.s12 idle 5s 100% 8 idle
Show classification Show in data acquisition Show in feature explorer
idle-1.s9 idle 5s 100% 8 idle
Show classification Show in data acquisition Show in feature explorer
idle-1.s4 idle 5s 100% 8 idle
Show classification Show in data acquisition Show in feature explorer
medium-pavement-7.s6 medium 5s 0% 8 smooth
Show classification Show in data acquisition Show in feature explorer
medium-pavement-7.s1 medium 5s 50% 4 medium, 4 uncertain
Show classification Show in data acquisition Show in feature explorer
smooth-flat-4.s9 smooth 5s 100% 8 smooth
Show classification Show in data acquisition Show in feature explorer
smooth-flat-4.s4 smooth 5s 38% 5 uncertain, 3 smooth
Show classification Show in data acquisition Show in feature explorer
gravel-5.s4 rough 5s 0% 8 medium
Show classification Show in data acquisition Show in feature explorer
gravel-4-small.s1 rough 5s 100% 8 rough
Show classification Show in data acquisition Show in feature explorer
medium-pavement-1.s3 medium 5s 0% 8 uncertain
Show classification Show in data acquisition Show in feature explorer
smooth-flat-3.s6 smooth 5s 100% 8 smooth
Show classification Show in data acquisition Show in feature explorer
smooth-flat-3.s1 smooth 5s 0% 7 uncertain, 1 rough
Show classification Show in data acquisition Show in feature explorer
gravel-3.s7 rough 5s 100% 8 rough
Show classification Show in data acquisition Show in feature explorer
gravel-3.s2 rough 5s 100% 8 rough
Show classification Show in data acquisition Show in feature explorer
medium-pavement-8.s8 medium 5s 50% 4 medium, 4 uncertain
Show classification Show in data acquisition Show in feature explorer
medium-pavement-8.s3 medium 5s 0% 5 uncertain, 3 smooth
Show classification Show in data acquisition Show in feature explorer
smooth-flat-2.s4 smooth 5s 75% 6 smooth, 2 uncertain
Show classification Show in data acquisition Show in feature explorer
gravel-2.s3 rough 5s 50% 4 rough, 4 uncertain
Show classification Show in data acquisition Show in feature explorer
gravel-1.s5 rough 5s 0% 8 uncertain
Show classification Show in data acquisition Show in feature explorer
medium-pavement-9.s15 medium 5s 75% 6 medium, 1 rough, 1 uncertain
Show classification Show in data acquisition Show in feature explorer
medium-pavement-9.s10 medium 5s 0% 6 uncertain, 2 rough
Show classification Show in data acquisition Show in feature explorer
medium-pavement-9.s5 medium 5s 50% 4 medium, 4 uncertain
Show classification Show in data acquisition Show in feature explorer
smooth-flat-1.s10 smooth 5s 100% 8 smooth
Show classification Show in data acquisition Show in feature explorer
smooth-flat-1.s5 smooth 5s 100% 8 smooth
Show classification Show in data acquisition Show in feature explorer
Filter yielded no results, click to adjust the filter

Model testing output

Results

Model version:
Accuracy
59.94%

Metrics for Classifier

Metric Value
Area under ROC Curve 0.94
Weighted average Precision 0.76
Weighted average Recall 0.74
Weighted average F1 score 0.74

Confusion matrix

Loading...

Feature explorer

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