Assessment of E-Senses Performance through Machine Learning Models for Colombian Herbal Teas Classification
This paper describes different E-Senses systems, such as Electronic Nose, Electronic Tongue, and Electronic Eyes, which were used to build several machine learning models and assess their performance in classifying a variety of Colombian herbal tea brands such as <i>Albahaca</i>, <i&g...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-06-01
|
| Series: | Chemosensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-9040/11/7/354 |
| _version_ | 1797589822118821888 |
|---|---|
| author | Jeniffer Katerine Carrillo Cristhian Manuel Durán Juan Martin Cáceres Carlos Alberto Cuastumal Jordana Ferreira José Ramos Brian Bahder Martin Oates Antonio Ruiz |
| author_facet | Jeniffer Katerine Carrillo Cristhian Manuel Durán Juan Martin Cáceres Carlos Alberto Cuastumal Jordana Ferreira José Ramos Brian Bahder Martin Oates Antonio Ruiz |
| author_sort | Jeniffer Katerine Carrillo |
| collection | DOAJ |
| description | This paper describes different E-Senses systems, such as Electronic Nose, Electronic Tongue, and Electronic Eyes, which were used to build several machine learning models and assess their performance in classifying a variety of Colombian herbal tea brands such as <i>Albahaca</i>, <i>Frutos Verdes</i>, <i>Jaibel</i>, <i>Toronjil</i>, and <i>Toute</i>. To do this, a set of Colombian herbal tea samples were previously acquired from the instruments and processed through multivariate data analysis techniques (principal component analysis and linear discriminant analysis) to feed the support vector machine, K-nearest neighbors, decision trees, naive Bayes, and random forests algorithms. The results of the E-Senses were validated using HS-SPME-GC-MS analysis. The best machine learning models from the different classification methods reached a 100% success rate in classifying the samples. The proposal of this study was to enhance the classification of Colombian herbal teas using three sensory perception systems. This was achieved by consolidating the data obtained from the collected samples. |
| first_indexed | 2024-03-11T01:11:35Z |
| format | Article |
| id | doaj.art-5726b147c46146ca836eed3178d66f37 |
| institution | Directory Open Access Journal |
| issn | 2227-9040 |
| language | English |
| last_indexed | 2024-03-11T01:11:35Z |
| publishDate | 2023-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Chemosensors |
| spelling | doaj.art-5726b147c46146ca836eed3178d66f372023-11-18T18:47:06ZengMDPI AGChemosensors2227-90402023-06-0111735410.3390/chemosensors11070354Assessment of E-Senses Performance through Machine Learning Models for Colombian Herbal Teas ClassificationJeniffer Katerine Carrillo0Cristhian Manuel Durán1Juan Martin Cáceres2Carlos Alberto Cuastumal3Jordana Ferreira4José Ramos5Brian Bahder6Martin Oates7Antonio Ruiz8GISM Group, University of Pamplona, Pamplona 543050, ColombiaGISM Group, University of Pamplona, Pamplona 543050, ColombiaGISM Group, University of Pamplona, Pamplona 543050, ColombiaGISM Group, University of Pamplona, Pamplona 543050, ColombiaLaboratory of Residues and Contaminants, Embrapa Environment, São Paulo 13918-110, BrazilCollege of Computing and Engineering, Nova Southeastern University, Davie, FL 33314, USADepartment of Entomology and Nematology, University of Florida–FREC, Davie, FL 33314, USADepartment of Engineering (EPSO), Miguel Hernández University, Orihuela 03312, Alicante, SpainDepartment of Engineering (EPSO), Miguel Hernández University, Orihuela 03312, Alicante, SpainThis paper describes different E-Senses systems, such as Electronic Nose, Electronic Tongue, and Electronic Eyes, which were used to build several machine learning models and assess their performance in classifying a variety of Colombian herbal tea brands such as <i>Albahaca</i>, <i>Frutos Verdes</i>, <i>Jaibel</i>, <i>Toronjil</i>, and <i>Toute</i>. To do this, a set of Colombian herbal tea samples were previously acquired from the instruments and processed through multivariate data analysis techniques (principal component analysis and linear discriminant analysis) to feed the support vector machine, K-nearest neighbors, decision trees, naive Bayes, and random forests algorithms. The results of the E-Senses were validated using HS-SPME-GC-MS analysis. The best machine learning models from the different classification methods reached a 100% success rate in classifying the samples. The proposal of this study was to enhance the classification of Colombian herbal teas using three sensory perception systems. This was achieved by consolidating the data obtained from the collected samples.https://www.mdpi.com/2227-9040/11/7/354herbal teaselectronic noseelectronic tongueelectronic eyesclassificationdata processing |
| spellingShingle | Jeniffer Katerine Carrillo Cristhian Manuel Durán Juan Martin Cáceres Carlos Alberto Cuastumal Jordana Ferreira José Ramos Brian Bahder Martin Oates Antonio Ruiz Assessment of E-Senses Performance through Machine Learning Models for Colombian Herbal Teas Classification Chemosensors herbal teas electronic nose electronic tongue electronic eyes classification data processing |
| title | Assessment of E-Senses Performance through Machine Learning Models for Colombian Herbal Teas Classification |
| title_full | Assessment of E-Senses Performance through Machine Learning Models for Colombian Herbal Teas Classification |
| title_fullStr | Assessment of E-Senses Performance through Machine Learning Models for Colombian Herbal Teas Classification |
| title_full_unstemmed | Assessment of E-Senses Performance through Machine Learning Models for Colombian Herbal Teas Classification |
| title_short | Assessment of E-Senses Performance through Machine Learning Models for Colombian Herbal Teas Classification |
| title_sort | assessment of e senses performance through machine learning models for colombian herbal teas classification |
| topic | herbal teas electronic nose electronic tongue electronic eyes classification data processing |
| url | https://www.mdpi.com/2227-9040/11/7/354 |
| work_keys_str_mv | AT jenifferkaterinecarrillo assessmentofesensesperformancethroughmachinelearningmodelsforcolombianherbalteasclassification AT cristhianmanuelduran assessmentofesensesperformancethroughmachinelearningmodelsforcolombianherbalteasclassification AT juanmartincaceres assessmentofesensesperformancethroughmachinelearningmodelsforcolombianherbalteasclassification AT carlosalbertocuastumal assessmentofesensesperformancethroughmachinelearningmodelsforcolombianherbalteasclassification AT jordanaferreira assessmentofesensesperformancethroughmachinelearningmodelsforcolombianherbalteasclassification AT joseramos assessmentofesensesperformancethroughmachinelearningmodelsforcolombianherbalteasclassification AT brianbahder assessmentofesensesperformancethroughmachinelearningmodelsforcolombianherbalteasclassification AT martinoates assessmentofesensesperformancethroughmachinelearningmodelsforcolombianherbalteasclassification AT antonioruiz assessmentofesensesperformancethroughmachinelearningmodelsforcolombianherbalteasclassification |