Pengembangan Prototipe untuk Prediksi Tingkat Penyeduhan Kopi Menggunakan Data Spektroskopi dan Deep Learning

Muhammad Teguh Prananto; Ridwan Raafi'udin; Muhammad Adrezo; Musthofa Galih Pradana; Nurul Afifah Arifuddin

doi:10.30591/jpit.v10i3.8710

Pengembangan Prototipe untuk Prediksi Tingkat Penyeduhan Kopi Menggunakan Data Spektroskopi dan Deep Learning

Muhammad Teguh Prananto, Ridwan Raafi'udin, Muhammad Adrezo, Musthofa Galih Pradana, Nurul Afifah Arifuddin

Abstract

Consistency in coffee flavor is a crucial factor for coffee enthusiasts, thus requiring a method capable of objectively measuring the coffee brewing level in accordance with the standard brewing chart. This study utilizes the AS7265X spectroscopy sensor to capture the characteristics of coffee based on the resulting light spectrum. The spectral data is then used in a deep learning model using the Convolutional Neural Network (CNN) algorithm to classify the coffee brewing level into five distinct classes. A total of 150 data samples were used in the training and testing process. Initial results show that the model achieved a very high average accuracy of approximately 97%. After hyperparameter tuning using the Random Search method, the model's accuracy further improved, reaching a very high accuracy. However, this performance improvement resulted in a trade-off in computational time, with execution time increasing from 15 seconds to 1 minute and 43 seconds. This research is expected to contribute to ensuring consistent coffee brew quality and to open opportunities for further studies that combine sensor technology and artificial intelligence in the food and beverage sector.

Keywords

Klasifikasi/prediksi, Coffee Brewing Level, Data Spektroskopi, Convolutional Neural Network (CNN), Sensor AS7265X.

Full Text:

References

S. Zakiah, “Kenaikan Konsumsi Kopi Tak Dibarengi Peningkatan Produksi.” https://www.metrotvnews.com/play/NA0CjeYW-kenaikan-konsumsi-kopi-tak-dibarengi-peningkatan-produksi (accessed Sep. 29, 2024).

I. M. S. Sayekti, “Trend Industri Kopi Masa Depan: Keberlanjutan Bisnis Hingga Keberlanjutan Lingkungan.” https://pressrelease.kontan.co.id/news/trend-industri-kopi-masa-depan-keberlanjutan-bisnis-hingga-keberlanjutan-lingkungan (accessed Sep. 30, 2024).

M. Várady, J. Tauchen, P. Klouček, and P. Popelka, “Effects of Total Dissolved Solids, Extraction Yield, Grinding, and Method of Preparation on Antioxidant Activity in Fermented Specialty Coffee,” Fermentation, vol. 8, no. 8, 2022, doi: 10.3390/fermentation8080375.

D. Rabbani, "Klasifikasi Beras Oplosan Berbasis Data Spektroskopi Menggunakan Deep Learning." Universitas Pembangunan Nasional 2024.

“Coffee Brewing Control Chart: Panduan Mendasar Penyeduhan Kopi - Coffeeland.” https://coffeeland.co.id/coffee-brewing-control-chart-panduan-mendasar-penyeduhan-kopi/ (accessed Aug. 22, 2024).

M. K. N. Wanhar, “Pengembangan Alat Ukur Portable untuk meprediksi Kandungan Nitrogen, Phospor, Kalium, danMagnesium Daun Melon Menggunakan SensorSpektroskopi Berbasis Reflektansi-Fluoresensi,” Aug. 2023.

R. Raafi’udin, Y. A. Purwanto, I. S. Sitanggang, and D. A. Astuti, “Feature Selection Model Development on Near-Infrared Spectroscopy Data Case Study of Beef Freshness Quality Prediction,” Int. J. Adv. Comput. Sci. Appl., vol. 15, no. 1, pp. 645–653, 2024, doi: 10.14569/IJACSA.2024.0150163.

H. Z. Amanah, “Prediksi Kandungan Gula pada Kentang (Solanum tuberosum L.) Sehat dan Terinfeksi Cendawan Fusarium sp. dengan menggunakan Spektroskopi Vis-NIR Sensor Fiber Optic dan AS7265x IBNU FARRAS, Dr. Rudiati Evi Masithoh, STP., M.DT; Hanim Zahrotul Amanah, STP., M,” vol. 12, no. 11, 2023, Accessed: Sep. 05, 2024. [Online]. Available: https://etd.repository.ugm.ac.id/penelitian/detail/220125

ams AG, “ams Datasheet AS7265x Smart 18-Channel VIS to NIR Spectral_ ID 3-Sensor Chipset with Electronic Shutter,” 2020.

Y. Wang, M. Li, R. Ji, M. Wang, Y. Zhang, and L. Zheng, “Mark-Spectra: A convolutional neural network for quantitative spectral analysis overcoming spatial relationships,” Comput. Electron. Agric., vol. 192, p. 106624, Jan. 2022, doi: 10.1016/J.COMPAG.2021.106624.

WANDB, “Understanding L1 and L2 regularization: techniques for optimized model training | ml-articles – Weights & Biases,” 2024. https://wandb.ai/mostafaibrahim17/ml-articles/reports/Understanding-L1-and-L2-regularization-techniques-for-optimized-model-training--Vmlldzo3NzYwNTM5?utm_source=chatgpt.com (accessed Mar. 20, 2025).

F. Adha, H. Airi, T. Suprapti, and A. Bahtiar, “Komparasi Metode Klasifikasi Data Mining Untuk Prediksi,” vol. 18, pp. 73–79, 2023.

A. I. Pradana and V. Atina, “Teknik K-Fold Cross Validation untuk Mengevaluasi Kinerja Mahasiswa,” pp. 239–248, 2024, doi: 10.33364/algoritma/v.21-1.1618.

I. C. Azhari and T. Haryanto, “Modeling Of Hyperparameter Tuned RNN-LSTM and Deep Learning For Garlic Price Forecasting In Indonesia,” J. Informatics Telecommun. Eng., vol. 7, no. 2, pp. 502–513, 2024, doi: 10.31289/jite.v7i2.10714.

Ravi Kumar, “Grid search Vs Randomize search CV,” Apr. 18, 2022. https://medium.com/@ravikumar10593/grid-search-cv-vs-randomize-search-cv-54708be0d599 (accessed May 06, 2025).

S. Raschka, “No, We Don’t Have to Choose Batch Sizes As Powers Of 2,” 2022. https://sebastianraschka.com/blog/2022/batch-size-2.html (accessed Feb. 27, 2025).

DOI: https://doi.org/10.30591/jpit.v10i3.8710