Prototype for cocoa mucilage classification using ICT in El Empalme, Ecuador
DOI:
https://doi.org/10.64439/cisai.v1i1.4Keywords:
Cocoa mucilage, Raspberry Pi, ESP8266, Neural networks, Teachable machineAbstract
The quality classification of cocoa mucilage is an important process to ensure product acceptance in national and international markets. However, the presence of impurities often leads to product rejection and loss of trust among buyers. In El Empalme, Ecuador, this challenge motivated the development of an automated prototype capable of separating impurities, delivering a cleaner product and strengthening trust in commercial transactions. The system incorporates a conveyor belt for mucilage classification and a mobile application that records the number of buckets collected and the total production weight. It also includes a webcam to capture images of the mucilage, which are processed by a Raspberry Pi running a convolutional neural network algorithm trained with Teachable Machine to classify the two categories. Finally, a servomotor deposits the product into the appropriate container. As a result, the prototype successfully classified mucilage automatically, optimizing the process, reducing losses, and increasing buyer confidence. Furthermore, all information is stored in the system and can be accessed through the mobile application. In conclusion, the developed prototype satisfactorily meets the needs of the farm.
References
[1] T. P. Ramos-Ramos, D. J. Guevara-Llerena, L. B. Sarduy-Pereira, and K. Diéguez-Santana, “Producción más limpia y ecoeficiencia en el procesado del cacao: un caso de estudio en Ecuador,” I&D, vol. 20, no. 1, pp. 135–146, Jul. 2020. https://doi.org/10.23881/idupbo.020.1-10i
[2] A. Teixeira, P. Iannetta, K. Binnie, T. A. Valentine, and P. Toorop, “Myxospermous seed-mucilage quantity correlates with environmental gradients indicative of water-deficit stress: Plantago species as a model,” Plant Soil, vol. 446, no. 1–2, pp. 343–356, Jan. 2020. https://doi.org/10.1007/s11104-019-04335-z
[3] W. Deng, P. P. M. Iannetta, P. D. Hallett, P. E. Toorop, G. R. Squire, and D.-S. Jeng, “The rheological properties of the seed coat mucilage of Capsella bursa-pastoris L. Medik. (shepherd’s purse),” Biorheology, vol. 50, no. 1–2, pp. 57–67, 2013. https://doi.org/10.3233/BIR-130627
[4] B. Hirko, H. Mitiku, and A. Getu, “Role of fermentation and microbes in cacao fermentation and their impact on cacao quality,” Syst Microbiol and Biomanuf, vol. 3, no. 4, pp. 509–520, Oct. 2023. https://doi.org/10.1007/s43393-023-00160-9
[5] A. Figoli, J. Hoinkis, S. A. Altinkaya, and J. Bundschuh, Eds., Application of Nanotechnology in Membranes for Water Treatment, 1st ed. CRC Press, 2017. https://doi.org/10.1201/9781315179070
[6] O. V. Zinina, A. V. Sharopatova, and J. A. Olentsova, “Management of an agricultural organization based on building a quality management system,” IOP Conf. Ser.: Earth Environ. Sci., vol. 677, no. 2, p. 022029, Mar. 2021. https://doi.org/10.1088/1755-1315/677/2/022029
[7] M. Mukhiddinov, A. Muminov, and J. Cho, “Improved Classification Approach for Fruits and Vegetables Freshness Based on Deep Learning,” Sensors, vol. 22, no. 21, p. 8192, Oct. 2022. https://doi.org/10.3390/s22218192
[8] A. A. Garcés-Cadena, O. A. Menéndez Granizo, E. P. Córdova, and A. J. Prado Romo, “Clasificación de calidad de manzana para monitoreo de cosechabilidad utilizando visión por computador y algoritmos de aprendizaje profundo,” Ingeniare. Rev. chil. ing., vol. 31, Aug. 2023. https://doi.org/10.4067/S0718-33052023000100215
[9] J. F. Lopes, V. G. T. Da Costa, D. F. Barbin, L. J. P. Cruz-Tirado, V. Baeten, and S. Barbon Junior, “Deep computer vision system for cocoa classification,” Multimed Tools Appl, vol. 81, no. 28, pp. 41059–41077, Nov. 2022. https://doi.org/10.1007/s11042-022-13097-3
[10] C. Pal, S. Das, A. Akuli, S. K. Adhikari, and A. Dey, “Cocoa-Net: Performance Analysis on Classification of Cocoa Beans Using Structural Image Feature,” IJCAI, vol. 48, no. 12, Sep. 2024. https://doi.org/10.31449/inf.v48i12.5762
[11] S. Das, A. Akuli, S. Biswas, A. Dey, A. Ghosh, and R. Shaw, “Discrimination of Cocoa Beans using Structural Image Features: An Experimental Analysis,” in 2022 IEEE IAS Global Conference on Emerging Technologies (GlobConET), Arad, Romania: IEEE, May 2022, pp. 1138–1142. https://doi.org/10.1109/GlobConET53749.2022.9872329
[12] A. K. Jean, M. Diarra, B. A. Bakary, G. Pierre, and A. K. Jérôme, “Application based on Hybrid CNN-SVM and PCA-SVM Approaches for Classification of Cocoa Beans,” IJACSA, vol. 13, no. 9, 2022. https://doi.org/10.14569/IJACSA.2022.0130927
[13] T. Coughlin, “Supersize My Pi [The Art of Storage],” IEEE Consumer Electron. Mag., vol. 6, no. 3, pp. 124–144, Jul. 2017. https://doi.org/10.1109/MCE.2017.2685038
[14] P. D. Prasetyo Adi et al., “Optimization and Development of Raspberry Pi 4 Model B for the Internet of Things,” in 2023 IEEE 9th Information Technology International Seminar (ITIS), Batu Malang, Indonesia: IEEE, Oct. 2023, pp. 1–6. https://doi.org/10.1109/ITIS59651.2023.10420261
[15] A. P. Singh and D. Agarwal, “Webcam Motion Detection in Real-Time Using Python,” in 2022 International Mobile and Embedded Technology Conference (MECON), Noida, India: IEEE, Mar. 2022, pp. 1–4. https://doi.org/10.1109/MECON53876.2022.9752059
[16] M. Islamiah and F. Fathurrahmaniah, “Praktikalitas Pembelajaran STEM dengan Arduino dan Sensor HX-711 pada Materi Impuls Berbasis Website,” jm-jpmipa, vol. 4, no. 4, pp. 707–717, Dec. 2024. https://doi.org/10.53299/jagomipa.v4i4.904
[17] S. P. Atti, H. Raj, H. K. A. N, H. R, P. N. H, and M. R. K, “Humanoid Robot,” in 2024 IEEE 11th Uttar Pradesh Section International Conference on Electrical, Electronics and Computer Engineering (UPCON), Lucknow, India: IEEE, Nov. 2024, pp. 1–4. https://doi.org/10.1109/UPCON62832.2024.10982951
[18] J. Vazquez, A. P. Torres, F. J. L. Alcolea, E. J. M. Martinez, and P. Roncero-Sanchez, “Implementation of a sensorized home alarm prototype on an FPGA platform,” in 2022 Congreso de Tecnología, Aprendizaje y Enseñanza de la Electrónica (XV Technologies Applied to Electronics Teaching Conference), Teruel, Spain: IEEE, Jun. 2022, pp. 1–7. https://doi.org/TAEE54169.2022.9840636
[19] J. Torres Ventura, A. H. Ruelas Puente, and J. R. Herrera García, “Rendimiento para la interoperabilidad entre Rasperry pi, ESP8266 y PLC con Node-RED para el IIoT,” ings, no. 29, pp. 90–97, Jan. 2023. https://doi.org/10.17163/ings.n29.2023.08
[20] D. Ascencios, K. Meza, J. Lluen, and G. Simon, “Calibración, validación y automatización del sistema de riego por goteo subterráneo usando un microcontrolador Arduino,” Rev. investig. altoandin., vol. 22, no. 1, pp. 95–105, Jan. 2020. https://doi.org/10.18271/ria.2020.540
[21] J. B. Rola et al., “Convolutional Neural Network Model for Cacao Phytophthora Palmivora Disease Recognition,” ijacsa, vol. 15, no. 8, 2024. https://doi.org/10.14569/IJACSA.2024.0150897
[22] D. Anduyan, N. Cabillo, N. Gultiano, and M. P. Pacot, “Enhancing Cocoa Pod Disease Classification via Transfer Learning and Ensemble Methods: Toward Robust Predictive Modeling,” 2025, arXiv. https://doi.org/10.48550/ARXIV.2504.12992
[23] O. Eric, R.-M. O. M. Gyening, O. Appiah, K. Takyi, and P. Appiahene, “Cocoa beans classification using enhanced image feature extraction techniques and a regularized Artificial Neural Network model,” Engineering Applications of Artificial Intelligence, vol. 125, p. 106736, Oct. 2023. https://doi.org/10.1016/j.engappai.2023.106736
[24] D. B. Vera, B. Oviedo, W. C. Casanova, and C. Zambrano-Vega, “Deep Learning-Based Computational Model for Disease Identification in Cocoa Pods (Theobroma cacao L.),” 2024, arXiv. https://doi.org/10.48550/ARXIV.2401.01247
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Mishelle Mosquera Rizzo, Jorge Piguave Rodríguez, Charles M. Pérez-Espinoza, Teresa Samaniego Cobo
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
