Prediksi Kadar Air Greenbeans Kopi Pra-Roasting Menggunakan Metode ANFIS
Abstract
Moisture content of green coffee beans is a critical parameter that determines quality stability during storage and the pre-roasting stage; however, conventional measurement methods are destructive and unsuitable for continuous monitoring. This study aims to develop an Internet of Things (IoT)-based moisture content prediction system using the Adaptive Neuro-Fuzzy Inference System (ANFIS). Input variables include temperature, relative humidity (RH), and capacitive sensor ADC signals, while moisture content is used as the target variable. A dataset consisting of 1032 observations was divided into training and testing sets with an 80:20 ratio. The ANFIS model employed Gaussian membership functions and an early stopping mechanism, and its performance was evaluated using MAE, RMSE, MAPE, and the coefficient of determination (R²). Experimental results achieved MAE of 0.2648, RMSE of 0.4187, MAPE of 2.077%, and R² of 0.8109 with an accuracy of 97.923%. The proposed system enables accurate, non-destructive, and real-time moisture content prediction.
Keywords: Moisture content; Green beans; Coffee; ANFIS; Prediction.
Abstrak
Kadar air biji kopi hijau merupakan parameter penting yang menentukan stabilitas mutu selama penyimpanan hingga tahap pra-roasting, namun metode pengukuran konvensional bersifat destruktif dan tidak mendukung monitoring berkelanjutan. Penelitian ini bertujuan mengembangkan sistem prediksi kadar air berbasis Internet of Things (IoT) menggunakan metode Adaptive Neuro-Fuzzy Inference System (ANFIS). Variabel input meliputi suhu, kelembaban relatif (RH), dan sinyal ADC sensor, dengan kadar air sebagai variabel target. Dataset sebanyak 1032 data dibagi menjadi data latih dan data uji dengan rasio 80:20. Model ANFIS menggunakan fungsi keanggotaan Gaussian dan mekanisme early stopping, serta dievaluasi menggunakan MAE, RMSE, MAPE, dan koefisien determinasi (R²). Hasil pengujian menunjukkan MAE 0,2648, RMSE 0,4187, MAPE 2,077%, dan R² sebesar 0,8109 dengan akurasi 97,923%. Sistem yang diusulkan mampu melakukan prediksi kadar air secara akurat, non-destruktif, dan real-time.
Keywords
References
C. P. Gallego, J. Pabón, R. D. Medina, and V. Osorio, “Maintenance of the Quality of Coffee (Coffea arabica L.) in Different Packaging and Storage Locations,” Int. J. Food Sci., vol. 2025, no. 1, p. 5049217, 2025, doi: https://doi.org/10.1155/ijfo/5049217.
J. Błaszkiewicz et al., “Effect of green and roasted coffee storage conditions on selected characteristic quality parameters,” Sci. Rep., vol. 13, no. 1, p. 6447, Dec. 2023, doi: 10.1038/s41598-023-33609-x.
A. Adnan, D. von Hörsten, E. Pawelzik, and D. Mörlein, “Rapid prediction of moisture content in intact green coffee beans using near infrared spectroscopy,” Foods, vol. 6, no. 5, pp. 1–11, May 2017, doi: 10.3390/foods6050038.
L. Anokye-Bempah, J. Han, K. Kornbluth, W. Ristenpart, and I. R. Donis-González, “The use of desiccants for proper moisture preservation in green coffee during storage and transportation,” J. Agric. Food Res., vol. 11, p. 100478, Mar. 2023, doi: 10.1016/j.jafr.2022.100478.
L. Anokye-Bempah, K. Phetpan, D. Slaughter, and I. R. Donis-González, “Design, calibration, and validation of an inline green coffee moisture estimation system using time-domain reflectometry,” J. Food Eng., vol. 341, p. 111342, Mar. 2023, doi: 10.1016/j.jfoodeng.2022.111342.
R. Moulana, S. Zakaria, and A. A. Munawar, “Rapid and non-destructive prediction of moisture content on intact gayo coffee beans using near infrared spectroscopy,” IOP Conf. Ser. Earth Environ. Sci., vol. 1356, no. 1, p. 012041, 2024, doi: 10.1088/1755-1315/1356/1/012041.
L. Wulandari, G. Indrayanto, and M. Yuwono, “Determination of Moisture Content in Ground Coffee Using Near-Infrared Spectroscopy and Chemometrics,” Asian Journal of Green Chemistry, vol. 10, no. 1, pp. 101–113, Jan. 2026, doi: 10.48309/AJGC.2026.535228.1775.
J. Błaszkiewicz and others, “Effect of Green and Roasted Coffee Storage Conditions on Selected Characteristic Quality Parameters,” Sci. Rep., vol. 13, no. 1, p. 6380, 2023, doi: 10.1038/s41598-023-33609-x.
S. Alyammahi, A. Alhmoudi, M. Alawadhi, and F. Alqaydi, “Low-Cost IoT-Based Smart Grain Monitoring System for Sustainable Storage Management,” in The 12th International Electronic Conference on Sensors and Applications, Basel Switzerland: MDPI, Nov. 2025, p. 90. doi: 10.3390/ECSA-12-26545.
K. S. O. Lozano, A. F. B. Monje, and N. G. Guzman, “Predictive model of moisture content in dry parchment coffee beans using near-infrared spectroscopy (FT-NIR),” Coffee Sci., vol. 20, pp. e202289-e202289, Feb. 2025, doi: 10.25186/.v20i.2289.
S. Ordoñez-Lozano, G. A. Collazos-Escobar, A. F. Bahamón-Monje, and N. Gutiérrez-Guzmán, “Monitoring moisture content in parchment coffee beans during drying using Fourier Transform near infrared (FT-NIR) spectroscopy: A dataset for calibrating chemometric-based models for moisture prediction,” Data Brief, vol. 59, p. 111436, Apr. 2025, doi: 10.1016/j.dib.2025.111436.
G. A. Collazos-Escobar, N. Gutiérrez-Guzmán, H. A. Váquiro, J. V. García-Pérez, and J. A. Cárcel, “Analysis of Machine Learning Algorithms for the Computer Simulation of Moisture Sorption Isotherms of Coffee Beans,” Food Bioproc. Tech., vol. 18, no. 6, pp. 5419–5430, Jun. 2025, doi: 10.1007/s11947-025-03785-x.
W. Ruiz Martinez and R. Ferro Escobar, “Internet of Things (IoT) System to Monitor Environmental Variables in a Coffee Crop Review Article,” Journal of agriculture and horticulture research, vol. 3, no. 1, pp. 10–12, 2020, [Online]. Available: www.opastonline.com
M. Esmaili et al., “Assessment of adaptive neuro-fuzzy inference system (ANFIS) to predict production and water productivity of lettuce in response to different light intensities and CO2 concentrations,” Agric. Water Manag., vol. 258, p. 107201, Dec. 2021, doi: 10.1016/j.agwat.2021.107201.
A. Abdurohman, M. Siregar, C. Olivia Sereati, S. Windasari, and MM. L. W. Pandjaitan, “Implementation and Analysis of Fuzzy Inference System (FIS) and Adaptive Neuro-Fuzzy Inference System (ANFIS) for Irrigation,” International Journal of Engineering Continuity, vol. 4, no. 1, pp. 210–231, Aug. 2025, doi: 10.58291/ijec.v4i1.399.
O. Taylan, A. E. M. Al-Juaidi, and B. Guloglu, “Novel Machine Learning Approaches for Predicting Soil Moisture Content Using Hydrological and Soil Characteristics: A Comparative Analysis of ANN, SVM, and ANFIS Models,” Dec. 05, 2024. doi: 10.21203/rs.3.rs-5404605/v1.
G. A. Collazos-Escobar, V. Hurtado-Cort’es, A. F. Baham’on-Monje, and N. Guti’errez-Guzm’an, “Mathematical modeling of water sorption isotherms in specialty coffee beans processed by wet and semidry postharvest methods,” Sci. Rep., vol. 15, p. 3898, 2025, doi: 10.1038/s41598-024-83702-y.
J. Seyedmohammadi and M. N. Navidi, “Optimizing soil water retention predictions using a subtractive clustering-based ANFIS model,” Cogent Food Agric., vol. 12, no. 1, p, 2612450 2026, doi: 10.1080/23311932.2025.2612450.
How To Cite This :
Refbacks
- There are currently no refbacks.
