Edge Impulse Inc. / HRV AFIB - Tabular data Public
Target: Cortex-M4F 80MHz 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 Accuracy Result
af.004.npy-25 af 100% 1 af
Show classification Show in data acquisition
nonaf.009.npy-20 nonaf 100% 1 nonaf
Show classification Show in data acquisition
af.017.npy-56 af 100% 1 af
Show classification Show in data acquisition
af.002.npy-20 af 100% 1 af
Show classification Show in data acquisition
af.016.npy-52 af 100% 1 af
Show classification Show in data acquisition
nonaf.003.npy-49 nonaf 100% 1 nonaf
Show classification Show in data acquisition
af.016.npy-83 af 100% 1 af
Show classification Show in data acquisition
nonaf.005.npy-29 nonaf 100% 1 nonaf
Show classification Show in data acquisition
nonaf.013.npy-39 nonaf 100% 1 nonaf
Show classification Show in data acquisition
af.017.npy-16 af 100% 1 af
Show classification Show in data acquisition
nonaf.010.npy-23 nonaf 100% 1 nonaf
Show classification Show in data acquisition
nonaf.016.npy-58 nonaf 100% 1 nonaf
Show classification Show in data acquisition
af.014.npy-43 af 100% 1 af
Show classification Show in data acquisition
nonaf.003.npy-31 nonaf 100% 1 nonaf
Show classification Show in data acquisition
nonaf.007.npy-14 nonaf 100% 1 nonaf
Show classification Show in data acquisition
af.004.npy-59 af 100% 1 af
Show classification Show in data acquisition
nonaf.013.npy-74 nonaf 100% 1 nonaf
Show classification Show in data acquisition
af.013.npy-63 af 100% 1 af
Show classification Show in data acquisition
nonaf.005.npy-75 nonaf 100% 1 nonaf
Show classification Show in data acquisition
af.002.npy-88 af 100% 1 af
Show classification Show in data acquisition
nonaf.008.npy-46 nonaf 100% 1 nonaf
Show classification Show in data acquisition

Model testing output

Results

Model version:
Accuracy
94.99%

Metrics for Classifier

Metric Value
Area under ROC Curve 0.96
Weighted average Precision 0.96
Weighted average Recall 0.96
Weighted average F1 score 0.96

Confusion matrix

afnonafuncertain
af97.3%1.2%1.5%
nonaf6.0%91.9%2.0%
f1 score0.960.95

Feature explorer

Error while loading features: {"response":{"readyState":0,"status":0,"statusText":"error"},"errorThrown":""}
Help & documentation Get help on the forum Send feedback Contact sales
Join us
Terms of Service Privacy policy