Manivannan / worker safety wearable 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.

worker safety wearable

Accelerometer

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 (14 samples)

View all

InCorrect posture - Bent Down.3fubejup

ID: 143173438

Label: InCorrect posture - Bent Down

Sample length: 30s

Walking.3fubqovu

ID: 143173436

Label: Walking

Sample length: 1m 0s

Correct posture - squat.3fuaoo2a

ID: 143173439

Label: Correct posture - squat

Sample length: 1m 0s

InCorrect posture - Bent Down.3fub9bfa

ID: 143173441

Label: InCorrect posture - Bent Down

Sample length: 1m 0s

Good Sitting posture.3fubv57d

ID: 143173435

Label: Correct Sitting posture

Sample length: 1m 0s

Walking.3fubo48t

ID: 143173437

Label: Walking

Sample length: 1m 0s

Correct posture - squat.3fuarhve

ID: 143173442

Label: Correct posture - squat

Sample length: 1m 0s

Improper Sitting posture.3fuc7632

ID: 143173434

Label: Improper Sitting posture

Sample length: 1m 0s

Model accuracy (Unoptimized (float32))

Validation set

100.0%

Test set

90.3%

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

Latency

7 ms.

Peak RAM usage

3.3K

Flash usage

78.4K

Run this model

On any device

Clone project

Dataset summary

Data collected

10m 40s

Sensors

accX, accY, accZ @ 100Hz

Labels

Correct posture - squat, Correct Sitting posture, Improper Sitting posture, InCorrect posture - Bent Down, Walking

Project info

Project ID	148375
Project version	2
License	Apache 2.0
No. of views	14,923
No. of clones	4