Balaji M / rasynboard_activity_tracker Public

Target: Espressif ESP-EYE (ESP32 240MHz) 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.

rasynboard_activity_tracker

This project is used to detect basic exercise movement and send the inference result over ble

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 (60 samples)

View all

bicep_curls.4jo2bgve

ID: 787747099

Label: bicep_curls

Sample length: 10s

bicep_curls.4jo27l6j

ID: 787746585

Label: bicep_curls

Sample length: 10s

bicep_curls.4jo2c056

ID: 787747118

Label: bicep_curls

Sample length: 10s

twist_to_on.4jlaa5k4

ID: 786241083

Label: twist_to_on

Sample length: 10s

bicep_curls.4jo293ic

ID: 787746858

Label: bicep_curls

Sample length: 10s

twist_to_on.4jlaf41k

ID: 786241124

Label: twist_to_on

Sample length: 10s

idle.4jl9pjo4

ID: 786239586

Label: idle

Sample length: 10s

bicep_curls.4jo2e25q

ID: 787747222

Label: bicep_curls

Sample length: 10s

Model accuracy (Unoptimized (float32))

Validation set

99.0%

Test set

On-device performance (Espressif ESP-EYE (ESP32 240MHz), Quantized (int8))

Latency

30 ms.

Peak RAM usage

3.8K

Flash usage

15.8K

Run this model

On any device

Clone project

Dataset summary

Data collected

10m 0s

Sensors

ax, ay, az, gx, gy, gz @ 100Hz

Labels

bicep_curls, idle, twist_to_on

Project info

Project ID	332665
License	Apache 2.0
No. of views	4,870
No. of clones	13