Marcelo Rovai / IESTI01 - Motion Classification - Version 2 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.

IESTI01 - Motion Classification - Version 2

Accelerometer

About this project

The Spectral Analysis Block Calculation can be found in the notebook:

https://github.com/Mjrovai/TinyML4D/blob/main/SciTinyM-2023/Edge_Impulse-Spectral_Analysis_Block/Edge_Impulse_Spectral_Analysis_Block_V3.ipynb

Data (43 samples)

View all

maritime.34cqp6hq.ingestion-65bfb76ddd-n9fzx

ID: 221332761

Label: maritime

Sample length: 10s

idle.34cqvupv.ingestion-65bfb76ddd-vl9kr

ID: 221332784

Label: idle

Sample length: 10s

lift.34cqh2c8.ingestion-65bfb76ddd-vl9kr

ID: 221332770

Label: lift

Sample length: 10s

terrestrial.34cqbe3r.ingestion-65bfb76ddd-zzcf6

ID: 221332756

Label: terrestrial

Sample length: 10s

terrestrial.34cqaeut.ingestion-65bfb76ddd-vl9kr

ID: 221332758

Label: terrestrial

Sample length: 10s

terrestrial.34cq410o.ingestion-65bfb76ddd-zzcf6

ID: 221332757

Label: terrestrial

Sample length: 10s

terrestrial.34cq98r6.ingestion-65bfb76ddd-zzcf6

ID: 221332755

Label: terrestrial

Sample length: 10s

lift.34cqftn5.ingestion-65bfb76ddd-n9fzx

ID: 221332780

Label: lift

Sample length: 10s

Model accuracy (Unoptimized (float32))

Validation set

100.0%

Test set

96.4%

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

Latency

8 ms.

Peak RAM usage

3.0K

Flash usage

18.8K

Run this model

Scan QR code or launch in browser

Launch in browser

Dataset summary

Data collected

7m 10s

Sensors

accX, accY, accZ @ 62.5Hz

Labels

idle, lift, maritime, terrestrial

Project info

Project ID	198358
Project version	1
License	Apache 2.0
No. of views	10,193
No. of clones	14