Justin Lutz / Rower Public

Target: Arduino Nano 33 BLE Sense (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.

Rower

Accelerometer

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 (84 samples)

View all

low-spm.json.2vbe08h3

ID: 111134109

Label: low-spm

Sample length: 9s

hi-spm.json.2vbeb306

ID: 111134094

Label: hi-spm

Sample length: 10s

hi-spm.json.2vd1lbem

ID: 111134076

Label: hi-spm

Sample length: 28s

hi-spm.json.2vbecnuj

ID: 111134091

Label: hi-spm

Sample length: 10s

easy.json.2vbdpvko

ID: 111134113

Label: easy

Sample length: 10s

low-spm.json.2vbe8lhp

ID: 111134096

Label: low-spm

Sample length: 9s

low-spm.json.2vd1ido9

ID: 111134074

Label: low-spm

Sample length: 28s

low-spm.json.2vd1jqs6

ID: 111134075

Label: low-spm

Sample length: 28s

Model accuracy (Unoptimized (float32))

Validation set

98.7%

Test set

98.5%

On-device performance (Arduino Nano 33 BLE Sense (Cortex-M4F 64MHz), Quantized (int8))

Latency

7 ms.

Peak RAM usage

3.1K

Flash usage

19.5K

Run this model

On any device

Clone project

Dataset summary

Data collected

18m 26s

Sensors

accX, accY, accZ @ 100Hz

Labels

easy, hi-spm, low-spm

Project info

Project ID	90788
Project version	1
License	No license attached
No. of views	38,064
No. of clones	2