Edge Impulse Experts / Fall_Detection_using_Transformer Public

Target: Arduino Portenta H7 (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.

Fall_Detection_using_Transformer

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 (4,528 samples)

View all

FALL.F05_SA09_R04.s1

ID: 241170218

Label: FALL

Sample length: 4s

FALL.F06_SA02_R05.s1

ID: 241170765

Label: FALL

Sample length: 4s

ADL.D10_SE10_R02

ID: 241172614

Label: ADL

Sample length: 12s

ADL.D04_SA11_R01

ID: 241173454

Label: ADL

Sample length: 1m 40s

ADL.D08_SA20_R03

ID: 241172951

Label: ADL

Sample length: 12s

FALL.F05_SA01_R02.s1

ID: 241169908

Label: FALL

Sample length: 4s

FALL.F07_SA10_R05.s1

ID: 241170361

Label: FALL

Sample length: 4s

ADL.D12_SE05_R02

ID: 241172317

Label: ADL

Sample length: 12s

Model accuracy (Unoptimized (float32))

Validation set

97.4%

Test set

97.3%

On-device performance (Arduino Portenta H7 (Cortex-M7 480MHz), Quantized (int8))

Latency

132 ms.

Peak RAM usage

2.3K

Flash usage

30.6K

Run this model

Scan QR code or launch in browser

Launch in browser

Dataset summary

Data collected

16h 57m 47s

Sensors

accX, accY, accZ @ 50Hz

Labels

ADL, FALL

Project info

Project ID	208622
Project version	2
License	Apache 2.0
No. of views	216,868
No. of clones	144