Classification via an Embedded Approach
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 const...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2017-09-01
|
| Series: | Designs |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2411-9660/1/1/7 |
| _version_ | 1818957767446102016 |
|---|---|
| author | José de Jesús Rubio Francisco Jacob Avila Adolfo Meléndez Juan Manuel Stein Jesús Alberto Meda Carlos Aguilar |
| author_facet | José de Jesús Rubio Francisco Jacob Avila Adolfo Meléndez Juan Manuel Stein Jesús Alberto Meda Carlos Aguilar |
| author_sort | José de Jesús Rubio |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-12-20T11:15:05Z |
| format | Article |
| id | doaj.art-924021b597b448318226541dabbc7b13 |
| institution | Directory Open Access Journal |
| issn | 2411-9660 |
| language | English |
| last_indexed | 2024-12-20T11:15:05Z |
| publishDate | 2017-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Designs |
| spelling | doaj.art-924021b597b448318226541dabbc7b132022-12-21T19:42:38ZengMDPI AGDesigns2411-96602017-09-0111710.3390/designs1010007designs1010007Classification via an Embedded ApproachJosé de Jesús Rubio0Francisco Jacob Avila1Adolfo Meléndez2Juan Manuel Stein3Jesús Alberto Meda4Carlos Aguilar5Sección de Estudios de Posgrado e Investigación, ESIME Azcapotzalco, Instituto Politécnico Nacional, Mexico D.F. 02250, MexicoTecnológico de Estudios Superiores de Ecatepec, Ecatepec, Estado de Mexico 55210, MexicoTecnológico de Estudios Superiores de Ecatepec, Ecatepec, Estado de Mexico 55210, MexicoTecnológico de Estudios Superiores de Ecatepec, Ecatepec, Estado de Mexico 55210, MexicoSección de Estudios de Posgrado e Investigación, ESIME Zacatenco, Instituto Politécnico Nacional, Mexico D.F. 07738, MexicoCentro de Investigación en Computación, Instituto Politécnico Nacional, Mexico D.F. 07738, MexicoThis 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.https://www.mdpi.com/2411-9660/1/1/7Arduinoartificial intelligenceelectronic noseembedded systemsapproachVOC classification |
| spellingShingle | José de Jesús Rubio Francisco Jacob Avila Adolfo Meléndez Juan Manuel Stein Jesús Alberto Meda Carlos Aguilar Classification via an Embedded Approach Designs Arduino artificial intelligence electronic nose embedded systems approach VOC classification |
| title | Classification via an Embedded Approach |
| title_full | Classification via an Embedded Approach |
| title_fullStr | Classification via an Embedded Approach |
| title_full_unstemmed | Classification via an Embedded Approach |
| title_short | Classification via an Embedded Approach |
| title_sort | classification via an embedded approach |
| topic | Arduino artificial intelligence electronic nose embedded systems approach VOC classification |
| url | https://www.mdpi.com/2411-9660/1/1/7 |
| work_keys_str_mv | AT josedejesusrubio classificationviaanembeddedapproach AT franciscojacobavila classificationviaanembeddedapproach AT adolfomelendez classificationviaanembeddedapproach AT juanmanuelstein classificationviaanembeddedapproach AT jesusalbertomeda classificationviaanembeddedapproach AT carlosaguilar classificationviaanembeddedapproach |