The Product

The Ekkono SDK. Releasing the True Potential in IoT.

We have developed an embedded software library – a Software Development Kit – built for the purpose to help developers rapidly and easily deploy edge machine learning, embedded onboard connected devices, to make them conscious, self-learning, and predictive.

The framework is all-software, platform agnostic, with the a C++ and a C library core. However, the API provides bindings to other programming languages like Python and C#. We focus on the implementation of machine learning and not the analytics. We license software.

Our comprehensive toolbox – the SDK – is everything needed for selecting machine learning technique and optimizing algorithms for the target platform. We offer multiple machine learning techniques and provide the entire feature-set a company needs to make smart products.

The Uniqueness

What differs Ekkono’s technology from other machine learning techniques is the ability to do incremental learning on streaming sensor data – onboard the device. The benefits are significant:

  • No need to collect any data in advance.
  • Our software process high-frequency sensor data in real-time.
  • Data is processed onboard the device, which means product companies don’t have to send raw data, but only relevant and enriched data, to the cloud for further analysis.
  • Radically reduced need for band-with and less dependency on the quality of the network connection.
  • Increased safety and data integrity when less data is sent to and stored in the cloud, or between suppliers.
  • Models adapt to local environments and learn their individual conditions.
  • Processing minimum amount of data means less footprint, still optimal performance.
  • Connected things become autonomously smart!

Built for purpose

Ekkono’s SDK is fit for purpose, since the software is built for purpose. Our key features are:

 

  • Incremental Learning
  • Conformal Predictions
  • Automated Change Detectors

…by using these machine learning techniques:

  • Regression Trees
  • Random Forest
  • Neural Networks

Watch the Ekkono Explainer Video

 

Related Product Content