Zack Qattan / Brilliant Sole Gesture Recognizer Public

Target: Nordic nRF52840 DK (Cortex-M4F 64MHz) Clone this project

Welcome to Edge Impulse, the largest community of edge AI developers!
This is a public Edge Impulse project, use the navigation bar to see all data and models in this project; or clone to retrain or deploy to any edge device.

Brilliant Sole Gesture Recognizer

About this project

This public Edge Impulse project does not have a README yet. Clone this project to add new data or retrain this project, or to deploy this project to a device.

Data (279 samples)

View all

stomp.576oual1.s7

ID: 1215733528

Label: stomp

Sample length: 700ms

tap.576kk2r4.s11

ID: 1215727947

Label: tap

Sample length: 700ms

stomp.576osv2i.s9

ID: 1215733507

Label: stomp

Sample length: 700ms

tap.576obarf.s3

ID: 1215733439

Label: tap

Sample length: 700ms

tap.576kkfbo.s6

ID: 1215727932

Label: tap

Sample length: 700ms

kick.576kp6ed.s6

ID: 1215727829

Label: kick

Sample length: 700ms

stomp.576ovo78.s3

ID: 1215733696

Label: stomp

Sample length: 700ms

kick.576koqhh.s4

ID: 1215727838

Label: kick

Sample length: 700ms

Model accuracy (Unoptimized (float32))

Validation set

99.2%

Test set

On-device performance (Nordic nRF52840 DK (Cortex-M4F 64MHz), Quantized (int8))

Latency

14 ms.

Peak RAM usage

1.7K

Flash usage

16.6K

Run this model

On any device

Clone project

Dataset summary

Data collected

4m 6s

Sensors

linearAcceleration.x, linearAcceleration.y, linearAcceleration.z, gyroscope.x, gyroscope.y, gyroscope.z @ 50Hz

Labels

idle, kick, stomp, tap

Project info

Project ID	378589
License	Apache 2.0
No. of views	8,379
No. of clones	0