Terahertz imaging and machine learning in the classification of coffee beans

Date
2021-06-15Author
Uceda, Patricia
Yoshida, Hideaki
Castillo, Pedro
Metadata
Show full item recordAbstract
ABSTRACT
The geographical origin of coffee beans represents an effect on the attributes and quality of the product due to the different soil and weather conditions for a specific location. Therefore, the development of methods for rapid classification and authentication of coffee beans based on their geographical origin is essential. This research was done with the purpose of determining the capacity of coffee (Coffea arabica) varieties classification with the use of Terahertz (THz) imaging and machine learning. THz images of coffee beans samples from 3 different geographical origins were acquired with a time-domain spectrometer and then used to measure the classification performance of methods such as neural networks, random forests, and support vector machines. The results obtained reached an accuracy up to 91.2%, which showed that the use of THz imaging and machine learning is an effective method for the non-destructive analysis of coffee variables and classification based on geographical origin.
Mostrar más
Bibliographic citation
Uceda, P., Yoshida, H., & Castillo, P. (2021). Terahertz imaging and machine learning in the classification of coffee beans. Proceedings of the 6th Brazilian Technology Symposium. Smart Innovation, Systems and Technologies, 233, 854-861. https://doi.org/10.1007/978-3-030-75680-2_94
Note
El texto completo de este trabajo no está disponible en el Repositorio Académico UPN por restricciones de la casa editorial donde ha sido publicado.
Subject
Collections
The following license files are associated with this item:
Related items
Showing items related by title, author, creator and subject.
-
Determination of the geographical origin of two coffee varieties by NIR spectroscopy [Determinación del origen geográfico de dos variedades de café mediante espectroscopia NIR]
Oblitas-Cruz, Jimy; Cieza-Rimarachin, Yuleyci; Castro-Silupu, Wilson (LACCEI, 2021-09-08)Acceso abiertoThe objective was to implement a non-invasive classification system for green coffee beans by using near-infrared spectroscopy (NIR) and multivariate data analysis. For this, 4 types of coffee were analyzed, according to ... -
Elección de características de interés en la clasificación de granos de café mediante un sistema de visión por computadora
Perez Miranda, Stefany Carolyn; Rosell Llanos, Luis Adrián (Universidad Privada del Norte, 2017-10-05)Acceso cerradoRESUMEN La clasificación de la calidad del café antes de ser tostado, una de las operaciones más importantes para definir su calidad y precio en el mercado, se realiza manualmente por personal entrenado en el reconocimiento ... -
Terahertz Time-domain Spectroscopy (THz-TDS) for classification of blueberries according to their maturity
Oblitas Cruz, Jimy (IEEE, 2020-11-18)Acceso abiertoABSTRACT Non-destructive determination of blueberry compound using spectral detection method is still a challenge due to the spectral THZ variation caused by abundant biological variations, such as geographic origins and ...