ST’s web-based tool, AIoT Craft, simplifies the development and provisioning of node-to-cloud AIoT projects that use the machine-learning core (MLC) of ST’s smart MEMS sensors. Intended for both beginners and seasoned developers, AIoT Caft helps program these sensors to run inference operations.
The MLC enables decision-tree learning models to run directly in the sensor. Operating autonomously without host system involvement, the MLC handles tasks that require AI skills, such as classification and pattern detection.
To ease the creation of decision-tree models, AIoT Craft includes AutoML, which automatically selects optimal attributes, filters, and window size for sensor datasets. This framework also trains the decision tree to run on the MLC and generates the configuration file to deploy the trained model. To provision the IoT project, the gateway can be programmed with the Data Sufficiency Module, intelligently filtering data points for transmission to the cloud.
As part of the ST Edge AI Suite, AIoT Craft offers customizable example code for in-sensor AI and sensor-to-cloud solutions. Decision tree algorithms can be tested on a ready-to-use evaluation board connected to the gateway and cloud.
Find more datasheets on products like this one at Datasheets.com, searchable by category, part #, description, manufacturer, and more.
The post Online tool programs smart sensors for AIoT appeared first on EDN.