Yi Xuan / Recyclable Waste Classification - Version 1 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.

Recyclable Waste Classification - Version 1

Audio classification project for paper, plastic and metal recyclables. This version is used for data collection and preprocessing.

Keyword spotting

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 (900 samples)

View all

Plastic.4rim67up.s7

ID: 939374283

Label: Plastic

Sample length: 1s

Plastic.4rileurk.s7

ID: 939374439

Label: Plastic

Sample length: 1s

Paper.4ril0lrc.s22

ID: 939374457

Label: Paper

Sample length: 1s

Metal.4rin5g3h.s6

ID: 939373998

Label: Metal

Sample length: 1s

Plastic.4rilmpkn.s47

ID: 939374297

Label: Plastic

Sample length: 1s

Metal.4rin153t.s37

ID: 939374020

Label: Metal

Sample length: 1s

Metal.4rimkmul.s13

ID: 939374192

Label: Metal

Sample length: 1s

Metal.4rin153t.s1

ID: 939374056

Label: Metal

Sample length: 1s

Model accuracy (Unoptimized (float32))

Validation set

96.5%

Test set

97.2%

On-device performance (Arduino Nano 33 BLE Sense (Cortex-M4F 64MHz), Unoptimized (float32))

Latency

647 ms.

Peak RAM usage

32.9K

Flash usage

32.7K

Run this model

Scan QR code or launch in browser

Launch in browser

Dataset summary

Data collected

15m 0s

Sensor

audio @ 16KHz

Labels

Metal, Paper, Plastic

Project info

Project ID	373417
Project version	2
License	Apache 2.0
No. of views	3,306
No. of clones	0