Michael Adu-Gyamfi / LifeGuard Public

Target: Arduino Nicla Vision (Cortex-M7 480MHz) 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.

LifeGuard

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 (284 samples)

View all

falling.3o8ijgti.s1

ID: 1766408169

Label: falling

Sample length: 1s

falling.3o8iiavp.s2

ID: 1766408177

Label: falling

Sample length: 1s

falling.3o8jf3fo.s1

ID: 1766408057

Label: falling

Sample length: 1s

walking.3o3s4hsq

ID: 1766408003

Label: walking

Sample length: 1m 0s

falling.3o8j9bgv.s3

ID: 1766408113

Label: falling

Sample length: 1s

falling.3o8jh7t1.s1

ID: 1766408038

Label: falling

Sample length: 1s

still.3mq87v6t

ID: 1766407981

Label: still

Sample length: 10s

falling.3o8ik4ol.s2

ID: 1766408165

Label: falling

Sample length: 1s

Model accuracy (Unoptimized (float32))

Validation set

100.0%

Test set

99.5%

On-device performance (Arduino Nicla Vision (Cortex-M7 480MHz), Quantized (int8))

Latency

2 ms.

Peak RAM usage

1.8K

Flash usage

17.0K

Run this model

On any device

Clone project

Dataset summary

Data collected

18m 5s

Sensors

accX, accY, accZ @ 10Hz

Labels

falling, still, unknown, walking

Project info

Project ID	657930
License	3-Clause BSD
No. of views	4,327
No. of clones	1