Kutluhan Aktar / BLE Smartwatch Detecting Potential Sun Damage 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.

BLE Smartwatch Detecting Potential Sun Damage

About this project

Project Description

I built this artificial neural network model (ANN) for my BLE AI-driven smartwatch project. The model makes predictions on sun damage risk levels (classes) based on UV index, temperature, pressure, and altitude measurements:

Tolerable
Risky
Perilous

After building the neural network model, I deployed the model as an Arduino library and uploaded it to XIAO BLE. Also, I employed XIAO BLE to transmit (advertise) the prediction (detection) result and the recently collected data over BLE.

Data (157 samples)

View all

Risky.sample_51

ID: 102149394

Label: Risky

Risky.sample_47

ID: 102149395

Label: Risky

Tolerable.sample_1

ID: 102149388

Label: Tolerable

Tolerable.sample_24

ID: 102149364

Label: Tolerable

Risky.sample_11

ID: 102149438

Label: Risky

Tolerable.sample_48

ID: 102149340

Label: Tolerable

Risky.sample_19

ID: 102149434

Label: Risky

Perilous.sample_26

ID: 102149460

Label: Perilous

Model accuracy (Unoptimized (float32))

Validation set

100.0%

Test set

90.9%

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

Latency

2 ms.

Peak RAM usage

2.1K

Flash usage

26.4K

Run this model

Scan QR code or launch in browser

Launch in browser

Dataset summary

Data collected

2m 37s

Sensors

uv_index, temperature, pressure, altitude @ 1Hz

Labels

Perilous, Risky, Tolerable

Project info

Project ID	104321
Project version	1
License	No license attached
No. of views	26,959
No. of clones	5