Skip to main content


Connhex AI is a modular machine learning system that can be used to process data from Connhex Cloud. Its core strength consists in being specialized in processing data from connected devices (time series, events, etc.).

Connhex AI: architecture.

Main features

Connhex AI focuses on anomaly detection and forecasting. It doesn't make any assumptions on your data, so it can be used out of the box.

It also includes advanced evaluation metrics, together with a simulation mode. This - as the name suggests - makes it possible to simulate how the model gradually evolves over time as data keeps flowing in.

Models automatically improve over time thanks to the feedback loop with Connhex Cloud: when enough data is available, the model is automatically retrained and updated if the performance is better than the previous one. It features:

  • automatic model(s) selection (Auto-ML), optimization and training​
  • auto-deployment on performance improvement​

Anomaly detection

  • Automatically detect anomalies in collected data​
  • Adjustable monitoring window size​
  • Customizable multi-event handling​ (more on this below)

Time series forecasting

  • Forecast values based on sensor readings​
  • Variable prediction period​
  • Prediction quality continuous monitoring​


Connhex AI integrates with Connhex Cloud to generate actions from predictions and anomalies (notifications, alarms, etc.). Multi-event scenarios customization proves to be particularly useful in this case. When an event occurs, should Connhex Cloud be immediately notified, or should Connhex AI wait for another event to occur? If multiple events happen in a given period, should it deliver those independently or batch them together to create a single alarm?

Connhex AI is also integrated with Connhex Edge to analyze data directly on device and automatically update models on the edge