Edge Impulse Inc. / LGBM Random Forest Classification Public

Target: Cortex-M7 216MHz 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.

LGBM Random Forest Classification

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 (223 samples)

View all

updown.22jv1f8m.ingestion-5678c5b4c4-8qp2m

ID: 846161536

Label: updown

Sample length: 3s

updown.updown1.rsi2ij9

ID: 846161528

Label: updown

Sample length: 10s

wave.wave0.rsi2kg2

ID: 846161504

Label: wave

Sample length: 10s

snake.snake3.rsi2h0k

ID: 846161610

Label: snake

Sample length: 10s

unlabeled.updown.2d6tm7sv.ingestion-84569c7f8c-m9xt8

ID: 846161599

Label: -

Sample length: 3s

wave.wave14.rsi2lh9

ID: 846161490

Label: wave

Sample length: 10s

snake.4.12bmk2s1

ID: 846161615

Label: snake

Sample length: 5s

drink.testing.4.12dtf6u3

ID: 846161663

Label: drink

Sample length: 10s

Model accuracy (Unoptimized (float32))

Validation set

99.5%

Test set

96.4%

On-device performance (Cortex-M7 216MHz, Unoptimized (float32))

Latency

6 ms.

Peak RAM usage

5.5K

Flash usage

38.1K

Run this model

Scan QR code or launch in browser

Launch in browser

Dataset summary

Data collected

23m 21s

Sensors

accX, accY, accZ @ 62.5Hz

Labels

drink, fistbump, idle, snake, updown, wave

Project info

Project ID	245576
Project version	3
License	BSD 3-Clause Clear
No. of views	37,036
No. of clones	14