Edge Impulse Experts / Smart Table Tennis Bat – Real‑Time Stroke Classification Public

Target: Arduino Nano 33 BLE Sense (Cortex-M4F 64MHz) 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.

Smart Table Tennis Bat – Real‑Time Stroke Classification

A custom smart table tennis bat for real-time stroke classification and motivational feedback, powered by Edge Impulse and Arduino Nano 33 BLE Sense.

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 (707 samples)

View all

BHsmash.30014

ID: 2013510999

Label: BHsmash

Sample length: 500ms

FHdrive.30001

ID: 2013510823

Label: FHdrive

Sample length: 500ms

BHdrive.20042

ID: 2013510929

Label: BHdrive

Sample length: 500ms

FHloop.10006

ID: 2013511084

Label: FHloop

Sample length: 500ms

FHloop.30004

ID: 2013511236

Label: FHloop

Sample length: 500ms

BHdrive.40031

ID: 2013511096

Label: BHdrive

Sample length: 500ms

zzz.0022

ID: 2013511228

Label: zzz

Sample length: 500ms

FHloop.20018

ID: 2013510666

Label: FHloop

Sample length: 500ms

Model accuracy (Unoptimized (float32))

Validation set

96.4%

Test set

88.0%

On-device performance (Arduino Nano 33 BLE Sense (Cortex-M4F 64MHz), Quantized (int8))

Latency

12 ms.

Peak RAM usage

1.5K

Flash usage

16.8K

Run this model

On any device

Clone project

Dataset summary

Data collected

6m 34s

Sensors

accX, accY, accZ, gyrX, gyrY, gyrZ @ 50Hz

Labels

BHdrive, BHsmash, FHdrive, FHloop, FHsmash, unknown, zzz

Project info

Project ID	732429
License	3-Clause BSD
No. of views	14,059
No. of clones	17