Jim's Demo Org / Pebble Typing Detection Public

Target: Cortex-M4F 80MHz 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.

Pebble Typing Detection

Example project for deploying to a Pebble smartwatch to detect if the wearer is typing or not.

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 (428 samples)

View all

sample

ID: 2352146748

Label: typing

Sample length: 1s

sample

ID: 2352146931

Label: typing

Sample length: 1s

sample

ID: 2352271320

Label: idle

Sample length: 1s

sample

ID: 2352150539

Label: idle

Sample length: 1s

sample

ID: 2352150114

Label: idle

Sample length: 1s

sample

ID: 2352143286

Label: idle

Sample length: 1s

sample

ID: 2352148353

Label: typing

Sample length: 1s

sample

ID: 2354383546

Label: idle

Sample length: 1s

Model accuracy (Unoptimized (float32))

Validation set

100.0%

Test set

82.6%

On-device performance (Cortex-M4F 80MHz, Quantized (int8))

Latency

1 ms.

Peak RAM usage

1.6K

Flash usage

18.1K

Run this model

On any device

Clone project

Dataset summary

Data collected

8m 51s

Sensors

accX, accY, accZ @ 50Hz

Labels

idle, typing

Project info

Project ID	819643
License	BSD 3-Clause Clear
No. of views	0
No. of clones	0