Machine Learning for Sensor Transducer Conversion Routines

TL;DR

This paper introduces machine learning methods to create less-complex sensor conversion routines that maintain accuracy, significantly reducing computational overhead for low-power embedded systems, demonstrated on the BME680 environmental sensor.

Contribution

It presents novel machine learning approaches to learn sensor conversion routines that are computationally efficient while preserving accuracy, outperforming traditional methods.

Findings

Reduced computational overhead by up to 71% for temperature, pressure, and humidity conversions.

Maintained high accuracy with RMS errors of 0.0114°C, 0.0280 KPa, and 0.0337%.

Demonstrated effectiveness on the BME680 environmental sensor.

Abstract

Sensors with digital outputs require software conversion routines to transform the unitless analogue-to-digital converter samples to physical quantities with correct units. These conversion routines are computationally complex given the limited computational resources of low-power embedded systems. This article presents a set of machine learning methods to learn new, less-complex conversion routines that do not sacrifice accuracy for the BME680 environmental sensor. We present a Pareto analysis of the tradeoff between accuracy and computational overhead for the models and models that reduce the computational overhead of the existing industry-standard conversion routines for temperature, pressure, and humidity by 62%, 71 %, and 18 % respectively. The corresponding RMS errors are 0.0114 degrees C, 0.0280 KPa, and 0.0337 %. These results show that machine learning methods for learning conversion routines can produce conversion routines with reduced computational overhead which maintain good accuracy.