Edge Impulse Experts / Continuous Gait Monitor (anomaly detection) Public

Target: Nordic nRF5340 DK (Cortex-M33 128MHz) 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.

Continuous Gait Monitor (anomaly detection)

A wearable for continuous gait analysis, aiming to detect gait abnormalities indicative of potential medical conditions.

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 (156 samples)

View all

standing.4p84b3bp.s4

ID: 873338314

Label: standing

Sample length: 5s

standing.4p84674c.s3

ID: 873338433

Label: standing

Sample length: 5s

standing.4p83vt94.s1

ID: 873338469

Label: standing

Sample length: 5s

walking.4p7pdbgk.s2

ID: 873338503

Label: walking

Sample length: 5s

running.4p7pom5i.s2

ID: 873338604

Label: running

Sample length: 5s

running.4p7prpe7.s2

ID: 873338578

Label: running

Sample length: 5s

standing.4p844hgb.s4

ID: 873338448

Label: standing

Sample length: 5s

walking.4p7pe4vq.s3

ID: 873338498

Label: walking

Sample length: 5s

Model accuracy (Unoptimized (float32))

Validation set

100.0%

Test set

On-device performance (Nordic nRF5340 DK (Cortex-M33 128MHz), Quantized (int8))

Latency

4 ms.

Peak RAM usage

2.4K

Flash usage

19.2K

Run this model

Scan QR code or launch in browser

Launch in browser

Dataset summary

Data collected

13m 0s

Sensors

accX, accY, accZ @ 20Hz

Labels

running, standing, walking

Project info

Project ID	366723
License	Apache 2.0
No. of views	33,348
No. of clones	42