Bosch sensors can now run machine learning algorithms created on Qeexo’s automated machine learning platform. The relevant Bosch MEMS industrial sensors can now run automatically generated tinyML algorithms at near real time speeds.

The Qeexo AutoML generated tinyML algorithms can be deployed on Arduino Nicla Sense ME with Bosch BHI260AP and BME688 sensors. The Bosch BHI260AP is a self-learning AI sensor with integrated IMU, and the BME688 is a 4-in-1 gas sensor with AI.

Using Qeexo AutoML, machine learning (ML) models – that would otherwise run on the host processor – can be deployed in and executed by BHI260AP and BME688. Its efficient machine learning models overcome traditional die-size-imposed limits to computational power and memory size

“Qeexo’s collaboration with Bosch enables application developers to quickly build and deploy machine learning algorithms on Bosch’s AI integrated sensors,” said Sang Won Lee, CEO of Qeexo. “Machine learning solutions running on Bosch’s AI integrated sensors are light-weight and do not consume MCU cycles or additional system resources as seen with traditional embedded ML.”

“Bosch Sensortec and Qeexo are collaborating on machine learning solutions for smart sensors and sensor nodes. We are excited to see more applications made possible by combining the smart sensors BHI260AP and BME688 from Bosch Sensortec and AutoML from Qeexo.” said Dr. Stefan Finkbeiner, CEO at Bosch Sensortec.