Infineon mixes AI and ML for smart home alarm

  • July 13, 2022
  • Steve Rogerson

German electronics company Infineon Technologies has introduced a battery-powered smart alarm system that achieves accuracy and low-power operation using sensor fusion based on artificial intelligence and machine learning (AI/ML).

This technology combined with low-power wake-on acoustic event detection is said to exceed the detection accuracy of acoustic-only alarm systems used in smart buildings and homes, and other IoT applications, while achieving equal or greater battery life compared with less sophisticated products.

“We are excited to enable a unique and differentiated approach to bringing AI/ML capabilities to cost-sensitive, battery-powered home security sensor systems, without sacrificing battery life,” said Laurent Remont, vice president of IoT at Infineon. “Current home security is unreliable for detecting events such as glass break. Our new solution combines a number of best-in-class technologies to create an alarm system that is smart, reliable and power efficient. We look forward to bringing more innovations into the home security market.”

It incorporates Infineon’s high signal-to-noise ratio analogue Xensiv IM73A135V01 MEMS microphone, Xensiv DPS310 digital pressure sensor and PSoC 62 microcontroller. The firm also provides a sensor fusion software algorithm based on precisely trained AI/ML that combines acoustic and pressure sensor data to differentiate accurately between sharp sounds inside a home and distinctive audio and pressure events.

These events can be created when glass is broken, or a house alarm is triggered due to a smoke or carbon monoxide alarm, or an intrusion is detected through a door or window.

The AI/ML sensor fusion algorithm can also eliminate many other background sounds or background pressure events that can generate false positives due to the similarities to alarm systems.

The home security alarm reference design technology is available today, with the board available in September.