The LSM6DSOX iNEMO™ sensor contains a machine-learning core to classify motion data based on known patterns.
STMicroelectronics has integrated machine-learning technology into its inertial sensors to improve activity-tracking performance and battery life in mobiles and wearables. The LSM6DSOX iNEMO™ sensor contains a machine-learning core, classifying motion data based on known patterns. Equipped with a 3D MEMS accelerometer and gyroscope, complex movements are tracked using the machine-learning core at low typical current consumption of 0.55mA. Devices using ST’s LSM6DSOX deliver an “always-on” user experience while customers creating activity-tracking products with the LSM6DSOX can train the core for decision-tree based classification using Weka, an open-source PC-based application to generate settings from sample data such as acceleration, speed, and magnetic angle. With the LSM6DSOX in full production, it can be integrated with Android and iOS. The sensor is priced from $2.50 for orders of 1000 pieces.