comment on this article

Companies look to accelerate development of intelligent sensing products

Pittsburgh-based analogue machine learning IC specialist, Aspinity, is joining up with Infineon to combine its Reconfigurable Analogue Modular Processing (RAMP) technology with Infineon’s XENSIVTM sensor family.

Aspinity’s RAMP chip is the first compact, ultra-low-power, analogue machine learning chip that can analyse raw, unstructured analogue sensor data to determine which data are important at the start of the signal chain — introducing an architectural approach to system design that saves significant battery power in end devices.

Functioning like an intelligent gate keeper, the RAMP chip will analyse analogue data from Infineon’s XENSIV MEMS sensors to determine what is relevant. The RAMP chip then triggers the analogue-to-digital converter and downstream digital signal processor or microcontroller to perform more complex analysis only on the relevant data, eliminating the power inefficiencies typical of other systems that waste power digitizing all of the data, relevant or not.

Since designers can easily program a RAMP chip for application-specific inferencing, the combination of Aspinity’s RAMP chip with the XENSIV sensors can facilitate a power-efficient analyse-first architecture in a whole new generation of small, power- and data-efficient always-on devices.

“Infineon’s high-performance XENSIV sensors allow electronic devices to see, hear, feel, and understand their environment - attributes that have become increasingly important for our customers,” said Rosina Kreutzer, director of business development at Infineon. “Combining the RAMP IC and our XENSIV sensors promotes high accuracy in combination with power efficiency in a broad range of always-on smart products. Our aim is to delight users with the features and functionality they can rely on.”

Author
Neil Tyler

Comment on this article


This material is protected by MA Business copyright See Terms and Conditions. One-off usage is permitted but bulk copying is not. For multiple copies contact the sales team.

What you think about this article:


Add your comments

Name
 
Email
 
Comments
 

Your comments/feedback may be edited prior to publishing. Not all entries will be published.
Please view our Terms and Conditions before leaving a comment.

Related Articles