Classification of the maturity stage of coffee cherries using comparative feature and machine learning

Authors

DOI:

https://doi.org/10.25186/.v16i.1710

Keywords:

Dielectric spectroscopy, Coffee maturity, Machine learning, Maturity classification, Physicochemical analysis

Abstract

This work presents the use of multiple techniques (i.e., physicochemical and spectral) applied to harvested coffee cherries for the postharvest classification of the maturity stage. The moisture content (MC), total soluble solids (TSS), bulk density, fruits’ hardness, CIEL*a*b parameters and the dielectric spectroscopy methods were applied on coffee cherries at seven maturity stages. These maturity stages were assessed according to the days after flowering (DAF) and the physical appearance as traditionally performed by growers. An increase of the green-to-red ratio (i.e., a*) parameter was perceived, accompanied by a monotonic response for the hardness, TSS and bulk density with a maximum moisture content at stage 5. In the case of the dielectric spectroscopy technique, the loss parameter presented higher losses for unripe stages at the ionic conduction region. To compare the individual performance of each of the techniques, three machine learning methods were used: random forest (RF), support vector machine (SVM) and k-nearest neighbours (k-NN). The meta-parameters for these techniques were optimized for each case to achieve the best performance possible. Furthermore, as the dielectric response is of spectral nature, recursive feature selection was applied and the 500
MHz to 1.3 GHz frequency range selected for the task. The highest performance was obtained for the colorimetric (75.1%) and hardness (72.5%) responses, while the lowest was obtained for the moisture content (45.5%). The dielectric spectroscopy response presented a promising response (56.8%), that achieved a clear separation of unripe from ripe stages, except for stage 5 in which some of the samples were classified as stage 2. Most techniques studied are compatible with field conditions, and the dielectric technique shows potential to be transferred based on available
software-radio defined platforms.


Key words: Dielectric spectroscopy; Coffee maturity; Postharvest classification; Physicochemical analysis.

References

ADNAN, A. et al. Rapid prediction of moisture content in intact green coffee beans using near infrared spectroscopy. Foods, 6(5):38, 2017.

ARCILA, J. et al. Sistemas de producción de café en Colombia. Chinchiná, Cenicafé. 2007.309p.

ARISTIZÁBAL-TORRES, I. D. et al. Physical and mechanical properties correlation of coffee fruit (Coffea Arabica) during its ripening. Dyna, 72(172):148-155, 2012.

BASHIR, H. A.; ABU-GOUKH, A. B. A. Compositional changes during guava fruit ripening. Food Chemistry, 80(4):557-563, 2003.

BEHERA, S. K.; RATH, A. K.; SETHY, P. K. Maturity status classification of papaya fruits based on machine learning and transfer learning approach. Information Processing in Agriculture, 2214-3173, 2020.

BERBERT, P. A. et al. Use of a dielectric function for determination of coffee seeds moisture content. Bragantia, 67(2):541-548, 2008.

CASTRO-GIRALDEZ, M. et al. Development of a dielectric spectroscopy technique for the determination of apple (Granny Smith) maturity. Innovative Food Science & Emerging Technologies, 11(4):749-754, 2010.

CHANDRASEKAR, V.; VISWANATHAN, R. Physical and thermal properties of coffee. Journal of Agricultural Engineering Research, 73(3):227-234, 1999.

CRAIG, A. P. et al. Fourier transform infrared spectroscopy and near infrared spectroscopy for the quantification of defects in roasted coffees. Talanta, 134:379-386, 2015.

DE CASTRO, R. D.; MARRACCINI, P. Cytology, biochemistry and molecular changes during coffee fruit development. Brazilian Journal of Plant Physiology, 18(1):175-199, 2006.

FARAH, A. Coffee constituents, in: CHU, Y. F. Coffee: Emerging health effects and disease prevention. wiley-blackwell, new york, p. 21-58, 2012.

FASHI, M.; NADERLOO, L.; JAVADIKIA, H. The relationship between the appearance of pomegranate fruit and color and size of arils based on image processing. Postharvest Biology and Technology, 154:52-57, 2019.

FEDERACIÓN NACIONAL DE CAFETEROS - FNC. Sustainability that matters 1927-2010, FNC - Management reports. 2010.

Available in: https://www.federaciondecafeteros.org/static/files/informe_sostenibilidad_eng.pdf, Access in: March, 03, 2017.

FRANCO, A. P. et al. Dielectric properties of green coconut water relevant to microwave processing: Effect of temperature and field frequency. Journal of Food Engineering, 155:69-78, 2015.

GUO, W. et al. Determination of soluble solids content and firmness of pears during ripening by using dielectric spectroscopy. Computers and Electronics in Agriculture, 117:226-233, 2015.

IACCHERI, E. et al. Different analytical approaches for the study of water features in green and roasted coffee beans. Journal of Food Engineering, 146:28-35, 2015.

KEYSIGHT TECHNOLOGIES, Basics of measuring the dielectric properties of materials, Application note. 2015. Available in: https://www.keysight.com/us/en/assets/7018-01284/application-notes/5989-2589.pdf, Access in: February, 20, 2019.

LI, X. et al. SSC and pH for sweet assessment and maturity classification of harvested cherry fruit based on NIR hyperspectral imaging technology. Postharvest Biology and Technology, 143:112-118, 2018.

MARÍN-LÓPEZ, S. M. et al. Cambios físicos y químicos durante la maduración del fruto de Café (Coffea arabica L. var. Colombia). Cenicafé, 54(3):208-225, 2003.

MARÍN, ARCILA, J. et al. Relación entre el estado de madurez del fruto del café y las características de beneficio rendimiento y calidad de la bebida. Cenicafé, 54(4):297-315, 2004.

MOMENY, M. et al. Accurate classification of cherry fruit using deep CNN based on hybrid pooling approach. Postharvest Biology and Technology, 166:e111204, 2020.

PIEDAD, E. et al. Postharvest classification of banana (Musa acuminata) using tier-based machine learning. Postharvest Biology and Technology, 145:93-100, 2018.

PUERTA-QUINTERO, G. I. Influencia de los granos de café cosechados verdes en la calidad física y organoléptica de la bebida. Cenicafé, 51(2):136-150, 2000.

RUNGPICHAYAPICHET, P. et al. Robust NIRS models for non-destructive prediction of postharvest fruit ripeness and quality in mango. Postharvest Biology and Technology, 111:31-40, 2016.

SANTOS PEREIRA, L. F. et al. Predicting the ripening of papaya fruit with digital imaging and random forests. Computers and Electronics in Agriculture, 145:76-82, 2018.

SILVA, S. D. et al. Coffee quality and its relationship with brix degree and colorimetric information of coffee cherries. Precision Agriculture, 15:543-554, 2014.

SOSA-MORALES, M. E. et al. Dielectric properties of berries in the microwave range at variable temperature. Journal of Berry Research, 7(4):239-247, 2017.

SOSA-MORALES, M. E. et al. Dielectric properties of foods: Reported data in the 21st Century and their potential applications. LWT - Food Science and Technology, 43(8):1169-1179, 2010.

SUNARHARUM, W. B.; WILLIAMS, D. J.; SMYTH, H. E. Complexity of coffee flavor: A compositional and sensory perspective. Food Research International, 62:315-325, 2014.

VELÁSQUEZ, S. et al. Volatile and sensory characterization of roast coffees - Effects of cherry maturity. Food Chemistry, 274:137-145, 2019.

YANG, X. et al. Machine learning for cultivar classification of apricots (Prunus armeniaca L.) based on shape features. Scientia Horticulturae, 256:e108524, 2019.

Downloads

Published

2021-03-01

How to Cite

VELASQUEZ, S.; FRANCO, A. P.; PEÑA, N.; BOHORQUEZ, J. C.; GUTIERREZ, N. Classification of the maturity stage of coffee cherries using comparative feature and machine learning. Coffee Science - ISSN 1984-3909, [S. l.], v. 16, p. e161710, 2021. DOI: 10.25186/.v16i.1710. Disponível em: http://www.coffeescience.ufla.br/index.php/Coffeescience/article/view/1710. Acesso em: 30 sep. 2022.