Jenny Plunkett / Sense2GoL-Pulse Radar 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.

Sense2GoL-Pulse Radar

Use this project to train a model to detect gestures using an Infineon Sense2GoL-Pulse radar development kit & Edge Impulse!

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 (726 samples)

View all

reach.json.1ssupl87.s18

ID: 7699254

Label: reach

Sample length: 1s

nothing.json.1sst1vt8.s4

ID: 7699485

Label: nothing

Sample length: 1s

tap.json.1sssem67.s3

ID: 7699556

Label: tap

Sample length: 1s

reach.json.1st01kn3.s23

ID: 7698973

Label: reach

Sample length: 1s

nothing.json.1sstqv8e.s1

ID: 7699409

Label: nothing

Sample length: 1s

nothing.json.1st0843g.s3

ID: 7698922

Label: nothing

Sample length: 1s

pinch.json.1ssva1qv.s13

ID: 7699132

Label: pinch

Sample length: 1s

pinch.json.1ssvmf1k.s22

ID: 7699018

Label: pinch

Sample length: 1s

Model accuracy (Unoptimized (float32))

Validation set

86.1%

Test set

82.9%

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

Latency

1 ms.

Peak RAM usage

4.0K

Flash usage

34.9K

Run this model

On any device

Clone project

Dataset summary

Data collected

14m 31s

Sensors

I, Q @ 75Hz

Labels

nothing, pinch, reach, tap

Project info

Project ID	16659
Project version	1
License	BSD 3-Clause Clear
No. of views	36,387
No. of clones	20