Kutluhan Aktar / IoT AI-driven Food Irradiation Classifier 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.

IoT AI-driven Food Irradiation Classifier

About this project

Project Description

This artificial neural network model (ANN) makes predictions on food irradiation dose levels (classes) based on ionizing radiation, weight, and visible light (color) measurements:

Regulated
Unsafe
Hazardous

After building my neural network model, I deployed my model as an Arduino library and uploaded it to Beetle ESP32-C3 so as to run inferences.

Data (540 samples)

View all

Unsafe.training.sample_42

ID: 108389927

Label: Unsafe

Sample length: 1s

Hazardous.training.sample_266

ID: 108390178

Label: Hazardous

Sample length: 1s

Unsafe.training.sample_303

ID: 108389854

Label: Unsafe

Sample length: 1s

Unsafe.training.sample_314

ID: 108389844

Label: Unsafe

Sample length: 1s

Unsafe.training.sample_498

ID: 108389784

Label: Unsafe

Sample length: 1s

Regulated.training.sample_22

ID: 108390073

Label: Regulated

Sample length: 1s

Regulated.training.sample_277

ID: 108390011

Label: Regulated

Sample length: 1s

Regulated.training.sample_280

ID: 108390008

Label: Regulated

Sample length: 1s

Model accuracy (Unoptimized (float32))

Validation set

100.0%

Test set

96.3%

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

Latency

4 ms.

Peak RAM usage

1.7K

Flash usage

21.4K

Run this model

On any device

Clone project

Dataset summary

Data collected

9m 0s

Sensors

weight, f1, f2, f3, f4, f5, f6, f7, f8, cpm, nsv, usv @ 1Hz

Labels

Hazardous, Regulated, Unsafe

Project info

Project ID	109647
Project version	1
License	No license attached
No. of views	41,369
No. of clones	3