Data Analytics

The i4FS Data Analytics covers the creation of building blocks for off-line and stream analytical processing of inputs coming from the Manufacturing environment. This includes machine learning algorithms supporting supervised and unsupervised scenarios.

In a factory there will be two different types of analytics tasks to be performed: those ones depending on historical data sources, e.g. readings of sensors for a given period of time in the past, and those ones that need to be calculated on real-time as they will be involved in triggering alarms conducting to time (or spend) critical actions. As such, the Data Analytics component integrates these two different modules focusing each of them in these two areas.

The Historic Data Analytics is a browser-based tool designed to guide the developer in specifying and deploying historic analytics models. The Streaming Data Analytics, though, is a service that detects anomalies in the values received from streaming data. Both of them are callable through the i4 Studio.

In the Historic Data Analytics, developers will be able to load datasets for training and testing purposes to deploy a prediction model. Once the developer considers the analytics model is finished, it can be published in the i4FS Marketplace for its usage within the Process Designer. Regarding the Streaming Data Analytics, developers will use a REST API to define stream analysis modules. In each module, several conditions can be established, involving mathematical operators, streaming data and user defined thresholds. When a condition is met, an alarm is raised by the Streaming Data Analytics.

For developing and using these analytics libraries, the developers need to have access and re-use the following i4FS elements:

  • i4 Studio
  • i4FS Marketplace

i4 Studio
The development of any i4 App starts with the access to the specific development IDE that i4FS provides. Inside the Studio, a direct access to the Data Analytics is provided to allow the developer to develop the analytics libraries. Once these are ready, the Data Analytics allows to deploy them as standalone libraries.

i4FS Marketplace
These deployed libraries are then annotated, uploaded and published to the i4FS Marketplace so that they are accessible for being part of a i4 App.

Play Video
Play Video

Import datasets

Easily import CSV-based datasets.

Create Analytic Models

Use your own datasets for creating personalised Analytics models.

Train and test your Analytics model

Train the selected algorithm and test it with your imported datasets.

Publish to i4FS Marketplace

Once ready, easily, and quickly publish to i4FS Marketplace

Additional ressources

Learn more about i4FS by visting the project website for general information, the wiki for information about the core components, the Technical Manual for API documentation, and downloading the repository’s source code.


Get a better understanding of the global architecture and information flow.

Source code

Our source code is opensource and available on our Gitlab repository.

API endpoints

Let your infrastructure communicate with the i4 Platform.