logo

Use of the Holt-Winters Model as a strategy for predicting environmental conditions during the cocoa storage process

10.24050/reia.v19i38.1593
Published 2022-06-02
Articles

Abstract

The project arises as a response to the business challenge presented by the company Chocolate Girones before the University - Company - State Committee (CUUES) and the Office for the Transfer of Research Results (OTRI), which expresses the need to have a basic system technology with the capacity to monitor and manage the cocoa traceability process during the storage and manufacture of chocolate. In view of the above, the objective of this article is to propose the use of the Holt-Winters model as a strategy to predict the behavior of temperature, relative humidity and dew point temperature that could be present in the process of storage of the cocoa bean, incorporating the use of analysis techniques supported in time series, thereby facilitating better control and monitoring of the quality of the bean during its stay in the winery. According to the results obtained, the proposed model allowed to predict the behavior of variables such as temperature, relative humidity and dew temperature, which play a fundamental role in the quality of the grain, as a strategy for the control of fungi and mold that could reach to emerge in the bean during storage, because cocoa is a hygroscopic product. Additionally, the proposed model can be considered as a very important prediction tool during the cocoa traceability process, reaching adjustment levels higher than 0.8, accompanied by a very low standard error of estimation and with a confidence level of 95 %.

Keywords

Categories

Authors

  • Juan Carlos Vesga Ferreira

    Universidad Nacional Abierta y a Distancia

  • Martha Fabiola Contreras Higuera

  • José Antonio Vesga Barrera

References

Afoakwa, E. (2014). Cocoa Production and Processing Technology, Cleveland, CRC Press, pp. 140-200.

Andrade, J.; Rivera, J.; Chire, G.; Ureña, M. (2019). Propiedades físicas y químicas de cultivares de cacao (Theobroma cacao L.) de Ecuador y Perú. Enfoque UTE, 10(4), pp. 1–12, https://doi:10.29019/ENFOQUE.V10N4.462.

Beg, M.; Ahmad, S.; Jan, K.; Bashir, K. (2017). Status, supply chain and processing of cocoa - A review. Trends in Food Science & Technology, 66(1), pp. 108–116, https://doi: 10.1016/J.TIFS.2017.06.007.

Cernaianu, A.; Cernaianu, C.; Popescu, D.; Tutunea, D. (2018). Studies on the cooling systems for the production of electricity through Seebeck effect with TEG elements, International Conference on Applied and Theoretical Electricity (ICATE), Craiova, Romania, pp. 1-6, https://doi: 10.1109/ICATE.2018.8551444.

Fedecacao (2020). Cadena Productiva del Cacao: Diagnóstico de libre competencia. Superintendencia de Industria y Comercio. Disponible en: https://www.sic.gov.co/recursos_user/documentos/promocion_competencia/Estudios_Economicos/Cacao.pdf

Figueroa, C.; Mota, J.; Ferrocino. I. (2019). The challenges and perspectives of the selection of starter cultures for fermented cocoa beans. International Journal of Food Microbiology, 301(1), pp. 41–50, https://doi: 10.1016/J.IJFOODMICRO.2019.05.002.

Germán, A.; Tauro, C.; Andreo, V.; Bernasconi, I. Ferral, A. (2016). Análisis de una serie temporal de clorofila-a a partir de imágenes MODIS de un embalse eutrófico, IEEE Biennial Congress of Argentina (ARGENCON), Buenos Aires, Argentina, pp. 697–704. https://doi: 10.1109/ARGENCON.2016.7585365.

Hudson, D.; Cohen, M. (2016). Neural networks and artificial intelligence for biomedical engineering, New Jersey, Wiley-IEEE Press, pp. 105-120.

Lambert, M.; Blaes, X.; Traore, P.; Defourny, P. (2017). Estimate yield at parcel level from S2 time serie in sub-Saharan smallholder farming systems, 9th International Workshop on the Analysis of Multitemporal Remote Sensing Images, Brugge, Belgium, pp. 1-7, https://doi:10.1109/Multi-Temp.2017.8035204.

Mejdal, M.; Abouhilal, A.; Chahid, E. (2017). Effects of temperature in the performance of the thermoelectric devises: Power generation, International Renewable and Sustainable Energy Conference-IRSEC, Marrakech, Morocco, pp. 338–343, https://doi: 10.1109/IRSEC.2016.7984011.

Muñoz, M.; Cortina, J.; Vaillant, F.; Parra, S. (2019). An overview of the physical and biochemical transformation of cocoa seeds to beans and to chocolate: Flavor formation, Critical Reviews in Food Science and Nutrition, 60(10), pp. 1593–1613. https://doi.org/10.1080/10408398.2019.1581726.

Nair, K. (2021). Cocoa (Theobroma cacao L.). Tree Crops, London, Springer International Publishing, pp. 153–213.

Vesga, J. C.; Contreras, M.; Vesga, J. A. (2021). Nuevos desafíos en el desarrollo de soluciones para e-health en Colombia, soportados en Internet de las Cosas (IoT). Revista EIA, 18(36), 36008 pp. 1–19. https://doi.org/10.24050/reia.v18i36.1508

Wei, W. (2013). Time Series Analysis, London, Oxford University Press, pp. 148–195

Wu, J.; He, Y. (2021). Prediction of GDP in Time Series Data Based on Neural Network Model, IEEE International Conference on Artificial Intelligence and Industrial Design (AIID), Guangzhou, China, pp. 20–23, https://doi: 10.1109/AIID51893.2021.9456509.

Yang, D.; Chen, H.; Song, Y.; Gong, Z. (2017). Granger Causality for Multivariate Time Series Classification, IEEE International Conference on Big Knowledge, Hefei, China, pp. 103–110, https://doi: 10.1109/ICBK.2017.36.

Żyżelewicz, D.; Budryn, G.; Oracz, J.; Antolak, H.; Kręgiel, D.; Kaczmarska, M. (2018). The effect on bioactive components and characteristics of chocolate by functionalization with raw cocoa beans. Food Research International, 113(1), pp. 234–244, https://doi: 10.1016/J.FOODRES.2018.07.017.

Statistics

Abstract
0
PDF accesses
0

Dimensions

PlumX

Downloads

Download data is not yet available.