Klasifikasi risiko jamur biji kopi hijau menggunakan adaptive neuro-fuzzy inference system
Keywords:
ANFIS, green coffee beans, fungal risk, machine learning, classificationAbstract
Penyimpanan biji kopi hijau (green beans) pada fase pra-roasting sangat rentan terhadap perubahan kondisi lingkungan yang dapat memicu pertumbuhan jamur dan menurunkan mutu kopi. Pemantauan kondisi penyimpanan yang masih bersifat manual menyebabkan keterlambatan deteksi risiko, sehingga diperlukan pendekatan cerdas berbasis data. Penelitian ini bertujuan untuk mengklasifikasikan indikasi risiko pertumbuhan jamur pada biji kopi hijau menggunakan Adaptive Neuro-Fuzzy Inference System (ANFIS) berbasis data primer hasil pengukuran lapangan. Data diperoleh dari sistem Internet of Things (IoT) yang dipasang di lokasi penyimpanan biji kopi hijau Kelompok Tani Bontugu, Kecamatan Trawas, Kabupaten Mojokerto. Parameter lingkungan yang digunakan meliputi suhu, kelembaban relatif, konsentrasi karbon dioksida (CO₂), dan kadar air biji kopi. Data diklasifikasikan ke dalam tiga kelas risiko, yaitu risiko rendah, sedang, dan tinggi. Hasil pengujian menunjukkan bahwa model ANFIS memiliki kinerja yang sangat baik dengan nilai akurasi sebesar 96,97%, nilai MAE 0,013, RMSE 0,0175, dan koefisien determinasi (R²) sebesar 0,9935. Hasil ini menunjukkan bahwa ANFIS efektif digunakan sebagai sistem pendukung keputusan untuk pemantauan dan pengendalian risiko pertumbuhan jamur pada biji kopi hijau selama penyimpanan.
Downloads
References
Abreu, G. F., Rosa, S. D. V. F., Coelho, S. V. B., Pereira, C. C., Malta, M. R., Fantazzini, T. B., & Vilela, A. L. (2023). Influence Of Hulling And Storage Conditions On Maintaining Coffee Quality. Anais Da Academia Brasileira de Ciencias, 95(4). https://doi.org/10.1590/0001-3765202320190612
Błaszkiewicz, J., Nowakowska-Bogdan, E., Barabosz, K., Kulesza, R., Dresler, E., Woszczyński, P., Biłos, Ł., Matuszek, D. B., & Szkutnik, K. (2023). Effect of green and roasted coffee storage conditions on selected characteristic quality parameters. Scientific Reports, 13(1). https://doi.org/10.1038/s41598-023-33609-x
Bulus, H. N. (2024). Adaptive Neuro-Fuzzy Inference System and Artificial Neural Network Models for Predicting Time-Dependent Moisture Levels in Hazelnut Shells (Corylus avellana L.) and Prina (Oleae europaeae L.). Processes, 12(8). https://doi.org/10.3390/pr12081703
Casari, M., De Luca, D., Mariani, S., & Rizzi, E. (2024). Optimisation of the Adaptive Neuro-Fuzzy Inference System (ANFIS) for Low-Cost Sensor Data. Measurement, 224, 115917. https://doi.org/10.1016/j.measurement.2024.115917
Gallego, C. P., Pabón, J., Medina, R. D., & Osorio, V. (2025). Maintenance of the Quality of Coffee (Coffea arabica L.) in Different Packaging and Storage Locations. International Journal of Food Science, 2025(1). https://doi.org/10.1155/ijfo/5049217
Gantner, M., Kostyra, E., Górska-Horczyczak, E., & Piotrowska, A. (2024). Effect of Temperature and Storage on Coffee’s Volatile Compound Profile and Sensory Characteristics. Foods, 13(24). https://doi.org/10.3390/foods13243995
Hagos, L., Guta, M., & Bacha, K. (2024). Prevalence of mycotoxigenic fungi and ochratoxin A in coffee (Coffea arabica L.). Cogent Food and Agriculture, 10(1). https://doi.org/10.1080/23311932.2024.2407524
López-Rodríguez, C., Verheecke-Vaessen, C., Strub, C., Fontana, A., Schorr-Galindo, S., & Medina, A. (2024). Reduction in Ochratoxin A Occurrence in Coffee: From Good Practices to Biocontrol Agents. In Journal of Fungi (Vol. 10, Number 8). Multidisciplinary Digital Publishing Institute (MDPI). https://doi.org/10.3390/jof10080590
Nofriyanti, D., Handayani, A. S., Suroso, Novianti, L., Rahkman, M. A., & Asriyadi. (2025). Web-Based Monitoring System for Automatic Coffe Driying in a Smart Dryer Dome.
Nuhu, A. A. (2015). Occurrence, harmful effects and analytical determination of Ochratoxin A in coffee. Journal of Applied Pharmaceutical Science, 5(1), 120–127. https://doi.org/10.7324/JAPS.2015.50121
Ozbek, A., Ünal, Ş., & Bilgili, M. (2022). Daily average relative humidity forecasting with LSTM neural network and ANFIS approaches. Theoretical and Applied Climatology, 150(1–2), 697–714. https://doi.org/10.1007/s00704-022-04181-7
Pakshir, K., Dehghani, A., Nouraei, H., Zareshahrabadi, Z., & Zomorodian, K. (2021). Evaluation of fungal contamination and ochratoxin A detection in different types of coffee by HPLC-based method. Journal of Clinical Laboratory Analysis, 35(11). https://doi.org/10.1002/jcla.24001
Santosa, R., Sari, P. A., & Sasongko, A. T. (2023). Sistem Monitoring Suhu dan Kelembaban Berbasis IoT (Internet of Thing) pada Gudang Penyimpanan PT Sakafarma Laboratories. Jurnal Teknologi Dan Sistem Informasi Bisnis, 5(4), 391–400. https://doi.org/10.47233/jteksis.v5i4.943
Taylan, O., Al-Juaidi, A. E. M., & Guloglu, B. (2024). Novel Machine Learning Approaches for Predicting Soil Moisture Content Using Hydrological and Soil Characteristics: A Comparative Analysis of ANN, SVM, and ANFIS Models. https://doi.org/10.21203/rs.3.rs-5404605/v1
Xu, L., Li, Y., Weng, X., Shi, J., Feng, H., Liu, X., & Zhou, G. (2024). A Monitoring Device and Grade Prediction System for Grain Mildew. Sensors, 24(20). https://doi.org/10.3390/s24206556
