Classification via an Embedded Approach

TL;DR

This paper introduces an embedded machine learning approach on an Arduino Uno for VOC classification using an electronic nose, achieving high accuracy and enabling portable, PC-free operation.

Contribution

It presents a novel embedded classification algorithm integrated into an Arduino-based electronic nose for real-time VOC detection.

Findings

Achieved 99% classification accuracy with the embedded system.

Demonstrated portable VOC identification without a PC.

Compared favorably with PC-based toolbox performance.

Abstract

This paper presents the results of an automated volatile organic compound (VOC) classification process implemented by embedding a machine learning algorithm into an Arduino Uno board. An electronic nose prototype is constructed to detect VOCs from three different fruits. The electronic nose is constructed using an array of five tin dioxide (SnO2) gas sensors, an Arduino Uno board used as a data acquisition section, as well as an intelligent classification module by embedding an approach function which receives data signals from the electronic nose. For the intelligent classification module, a training algorithm is also implemented to create the base of a portable, automated, fast-response, and economical electronic nose device. This solution proposes a portable system to identify and classify VOCs without using a personal computer (PC). Results show an acceptable precision for the embedded approach in comparison with the performance of a toolbox used in a PC. This constitutes an embedded solution able to recognize VOCs in a reliable way to create application products for a wide variety of industries, which are able to classify data acquired by an electronic nose, as VOCs. With this proposed and implemented algorithm, a precision of 99% for classification was achieved into the embedded solution.