TY - JOUR
T1 - Classification via an embedded approach
AU - Rubio, José de Jesús
AU - Avila, Francisco Jacob
AU - Meléndez, Adolfo
AU - Stein, Juan Manuel
AU - Meda, Jesús Alberto
AU - Aguilar, Carlos
N1 - Publisher Copyright:
© 2017 by the authors. Licensee MDPI, Basel, Switzerland.
PY - 2017/9
Y1 - 2017/9
N2 - 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.
AB - 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.
KW - Approach
KW - Arduino
KW - Artificial intelligence
KW - Electronic nose
KW - Embedded systems
KW - VOC classification
UR - http://www.scopus.com/inward/record.url?scp=85095439881&partnerID=8YFLogxK
U2 - 10.3390/designs1010007
DO - 10.3390/designs1010007
M3 - Artículo
AN - SCOPUS:85095439881
SN - 2411-9660
VL - 1
SP - 1
EP - 16
JO - Designs
JF - Designs
IS - 1
M1 - 7
ER -