Analyze-First: The Most Efficient Way to Process Data in Always-on Devices

In the next five years, billions of hands-free, always-on sensing devices that run on battery will assist us in our daily lives at home and at work: playing music and controlling our homes upon request, alerting us to danger, monitoring the wear and tear of factory equipment, and even continuously monitoring our health. These devices are always-on, continuously digitizing and analyzing all sensor data as they wait to detect a random, sporadic event, such as voice, an alarm, or a variation in a vibrational frequency. This constant analysis of data that is mostly irrelevant is grossly inefficient – expending precious power and data resources on data that will ultimately be thrown away.

We need a better solution if the next generation of portable, always-on sensing devices are going to have reasonable battery lifetimes. And this is where Aspinity's RAMP technology is changing the game.
Aspinity offers a fundamentally new architectural approach to conserving power and data resources in always-on devices. Its scalable and programmable RAMP (Reconfigurable Analog Modular Processor)  technology incorporates powerful machine learning into an ultra-low power ANALOG neuromorphic processor that can detect unique events from background noise BEFORE the data is digitized. By directly analyzing the analog raw sensor data for what’s important, the RAMP chip eliminates the higher-power processing of irrelevant data.

Finally, system designers can stop sacrificing features and accuracy for longer battery life because Aspinity’s analyze-first approach reduces the power consumption of always-sensing systems by up to 10x and data requirements by up to 100x.
The RAMP chip’s analog blocks can be reprogrammed with application-specific algorithms for detection of both different events and different types of sensor input.  For example, designers can use a RAMP chip for always-listening applications in which the chip conserves system power by keeping the rest of the always-listening system in a low power sleep state until a specific sound, such as voice or an alarm, has been detected. Unlike other sensor edge solutions for voice activity detection, the RAMP chip also supports voice-first devices by storing the preroll data required by wake word engines. For industrial applications, designers can use a RAMP chip to sample and select only the most important data points from thousands of points of sensor data:  compressing vibration data into a reduced number of frequency/energy pairs and dramatically decreasing the amount of data collected and transmitted for analysis.

With so many ways to program a RAMP core, as well as broad algorithm support for different types of analysis and output, the RAMP chip uniquely enables a whole new generation of smaller, lower-cost, more power- and data-efficient, battery-operated, always-on devices for consumer, IoT, industrial and biomedical applications.
The patented and innovative RAMP technology enables sophisticated digital signal processing tasks to be replicated in analog. Aspinity has leveraged the nonlinear characteristics of a small number of transistors to enable a new architectural approach to machine learning: modular, parallel and continuously operating analog blocks mimic the brain’s efficient neural network. These blocks are configurable for typical analog tasks such as sensor interfacing, signal processing and data conversion as well as more complex tasks such as feature extraction, event detection and classification. Each of these blocks is implemented in a much smaller footprint than a traditional analog block and allows early event detection from raw, unstructured analog sensor data.