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

walking.4p87cmik.s1

ID: 873381657

Label: walking

Sample length: 5s

standing.4p83ue15.s2

ID: 873338476

Label: standing

Sample length: 5s

standing.4p84b3bp.s1

ID: 873338311

Label: standing

Sample length: 5s

standing.4p844hgb.s3

ID: 873338447

Label: standing

Sample length: 5s

walking.4p7p416i.s2

ID: 873338523

Label: walking

Sample length: 5s

running.4p7prpe7.s3

ID: 873338579

Label: running

Sample length: 5s

walking.4p7pe4vq.s2

ID: 873338497

Label: walking

Sample length: 5s

walking.4p7ovikh.s1

ID: 873338542

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

On any device

Clone project

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	23,285
No. of clones	35