Dashboard
Devices
Data acquisition
Impulse design
EON TunerNew
Retrain model
Live classification
Model testing
Versioning
Deployment

Getting started

Documentation
Forums

MJRoBot (Marcelo Rovai) / Blender - Motion Detection Public

Clone this project

MJRoBot (Marcelo Rovai) / Blender - Motion Detection Public

Clone this project

#1

Select a version

Primary version

Anomaly detection settings

Cluster count

Please provide a valid cluster count (numeric only)

Axes

Select feature axes to include in model training.

accX RMS

accX Peak 1 Freq

accX Peak 1 Height

accX Peak 2 Freq

accX Peak 2 Height

accX Peak 3 Freq

accX Peak 3 Height

accX Spectral Power 0.1 - 0.5

accX Spectral Power 0.5 - 1.0

accX Spectral Power 1.0 - 2.0

accX Spectral Power 2.0 - 5.0

accY RMS

accY Peak 1 Freq

accY Peak 1 Height

accY Peak 2 Freq

accY Peak 2 Height

accY Peak 3 Freq

accY Peak 3 Height

accY Spectral Power 0.1 - 0.5

accY Spectral Power 0.5 - 1.0

accY Spectral Power 1.0 - 2.0

accY Spectral Power 2.0 - 5.0

accZ RMS

accZ Peak 1 Freq

accZ Peak 1 Height

accZ Peak 2 Freq

accZ Peak 2 Height

accZ Peak 3 Freq

accZ Peak 3 Height

accZ Spectral Power 0.1 - 0.5

accZ Spectral Power 0.5 - 1.0

accZ Spectral Power 1.0 - 2.0

accZ Spectral Power 2.0 - 5.0

Training output

Cancel

Clone this project to train this model

Model

Model version:

By definition there should be as few as possible anomalies in the training dataset, and thus accuracy is not calculated during training. Run Model testing to learn more about the model performance.

Anomaly explorer

X Axis

Y Axis

Test data

Loading...

Retrain this model to reveal additional visualizations

Anomaly score

...

Average axis distance

...

© 2024 EdgeImpulse Inc. All rights reserved

Anomaly detection - Manage block versions

List of block versions ()

Note

To use an Input block version, connect it to a DSP block version using the Manage versions dialog on a DSP block page. The starred Input block version is the one connected to the Primary learn block, via a DSP block.

Note

To use a DSP block version, connect it to a Learn block version using the Manage versions dialog on a Learn block page. The starred DSP block version is the one connected to the Primary learn block.

Note

The Primary learn block version is the one that will be used when a project is deployed. When you set a Learn block version to Primary, any DSP and Input block versions it connects to will automatically be selected for deployment.

Selected version

Description

#9

Input blocks

Target device

Configure your target device for model performance calculations, and to enable target specific optimizations.

Show logs

Waiting...

Cancel job

Help & documentation Get help on the forum Send feedback Contact sales

Join us

Terms of Service Privacy policy

Send us your feedback!

We're always looking for ways to improve Edge Impulse. If you have any feedback, please let us know!

Subject

This field is required

How was your experience?

This field is required

Almost there!

You'll need a free Edge Impulse account to clone this project. Creating an account lets you add your own data, modify models, and join a community of thousands of embedded machine learning developers!

Sign up for free

I already have an account

Create a new project

Enter the name for your new project:

Enter a name for your new project

Choose your project type:

Personal

20 min job limit, 4GB or 4 hours of data, limited collaboration.

Enterprise

No job or data size limits, higher performance, custom blocks.

Choose your project setting:

Public

Anyone on the internet can view and clone this project under the Apache 2.0 license.

Private

( of remaining)

Only invited users can edit and view your project.

How often should we bill you?

YEARLY

$400 /month

billed annually

SAVE 15%

MONTHLY

$475 /month

billed monthly