Pengembangan Model Jaringan Syaraf Tiruan untuk Penentuan Kandungan Kimia Biji Kopi Arabika Gayo dengan NIRS

Hafiz Fajrin Aditama, I Wayan Budiastra, Slamet Widodo

Abstract


Penelitian ini bertujuan untuk mengembangkan model jaringan syaraf tiruan (JST) terbaik untuk memprediksi kandungan kimia biji kopi arabika Gayo dan memvalidasi model. Data input yang digunakan adalah data principal component (PC) spektra yang terlebih dahulu telah dilakukan pre-treatment data menggunakan multiplicative scatter correction (MSC), Normalisasi (N-1,1), dan turunan pertama Savitzky-Golay (dg1). Model JST menggunakan Multilayer Perceptron (MLP) feed forward neural network dengan algoritma pelatihan dasar Levenberg-Marquard. Penggunaan 10 jumlah neuron lapisan tersembunyi sudah cukup untuk dapat memprediksi kandungan kimia biji kopi Gayo. Kadar air dapat diprediksi dengan model JST menggunakan 8 jumlah PC dan normalisasi (r = 0,96; CV = 1,77%; RPD = 3,79). Kafein dapat diprediksi dengan 8 jumlah PC dan kombinasi normalisasi dengan dg1 (r = 0,98; CV = 2,15%; RPD = 4,44). Karbohidrat dapat diprediksi dengan menggunakan 5 jumlah PC dan dg1 (r = 0,99; CV = 0,27%; RPD = 9,55). Lemak dapat diprediksi dengan menggunakan 8 jumlah PC dan kombinasi MSC dengan dg1 (r = 1; CV = 0,41%; RPD = 19,11). Protein dapat diprediksi dengan menggunakan 5 jumlah PC dan kombinasi MSC dengan dg1 (r = 0,99; CV = 0,84%; RPD = 7,08). 


Keywords


kopi arabika gayo, jaringan syaraf tiruan, analisis komponen utama, near infrared spectroscopy

Full Text:

PDF INDONESIA

References


[AOAC] Association of Official Analytical Chemists. (2016). Official Method 948.22: Fat (crude) in nuts and nut products and Official Method 950.48: Protein (crude) in nuts and nut products. Official Methods of Analysis of AOAC International, 20th ed., AOAC International, Gaithersburg, MD, USA.

Arnita, & Sutarman. (2011). Membanding Metode Multiplicative Scatter Correction (MSC) dan Standard Normal Variate (SNV) pada Model Kalibrasi Peubah Ganda. Bulletin of Mathematics Journal, 03 (01), 25–38.

Ayu, P. C., Budiastra, I. W., Sutrisno, & S., Widyotomo, S. (2018). Prediction of Caffeine Content in Java Preanger Coffee Beans by NIR Spectroscopy Using PLS and MLR Method. IOP Conference Series: Earth and Environmental Science Publishing, 147 (2018) 012004.

Brígida, M., Sorane, C., Kitzberger, G., & Protasio, F. (2015). Application of near infrared spectroscopy for green coffee biochemical phenotyping. Near Infrared Spectroscopy Journal, 22 (December 2014), 411–421.

Buddenbaum, H., & Steffens, M. (2012). The Effects of Spectral Pretreatments on Chemometric Analyses of Soil Profiles Using Laboratory Imaging Spectroscopy. Applied and Environmental Soil Science Journal.

Citra, S., Madi, Y., Budiastra, I. W., Purwanto, Y. A., & Widyotomo, S. (2018). Analisis Pengaruh Variasi Jumlah Lapisan Biji pada Akurasi Prediksi Kandungan Minor Biji Kopi Arabika Hijau Bondowoso dengan NIR Spectroscopy. Jurnal Ilmu Pertanian Indonesia, 23 (2), 81–87.

Fulop, A., & Hancsok, J. (2009). Comparison of calibration models based on near infrared spectroscopy data for the determination of plant oil properties. Chemical Engineering Transactions Journal, 17, 445–450.

Kurniawan F. (2017). Karakterisasi dan klasifikasi biji kopi java arabika berdasarkan indikasi geografis menggunakan metode NIR spectroscopy dan analisis diskriminan. Tesis Program Studi Teknologi Pascapanen. Institut Pertanian Bogor: Bogor.

Lengkey, L. C. E. C., Budiastra, I. W., Seminar, K. B., & Purwoko, B. S. (2013). Determination of Chemical Properties in Jatropha Curcas L . Seed IP-3P by Partial Least-Squares Regression and Near-Infrared Reflectance Spectroscopy. Agriculture Innovations and Research Journal, 2(1).

Mardison S. (2010). Penentuan Komposisi Kimia Biji Jarak Pagar secara Nondestruktif dengan Metode NIR dan Jaringan Syaraf Tiruan. Tesis Program Studi Teknik Mesin Pertanian dan Pangan. Institut Pertanian Bogor: Bogor.

Mattjik AS dan Made IS. (2006). Perancangan Percobaan dengan Aplikasi SAS dan MINITAB. IPB Press: Bogor.

Naripati R. (2017). Penentuan Kandungan Kimia Utama Biji Kopi Arabika Java Preanger secara Nondestruktif dengan Near Infrared Spectroscopy (NIRS). Skripsi Departemen Teknik Mesin dan Biosistem. Institut Pertanian Bogor: Bogor.

Nircal 5.5 manual. (2013). Nircal manual. Switzerland: Buchi Labortechnik AG, CH Flawil.

Osborne BG, Fearn T, Hindle PH. (1993). Practical NIR Spectroscopy with Application in Food and Baverage Analysis. Singapore: Longman Singapore Publishers (Pte) Ltd.

Rodrigo, J., Sarraguça, M. C., Rangel, A. O. S. S., & Lopes, J. A. (2012). Evaluation of green coffee beans quality using near infrared spectroscopy : A quantitative approach. Food Chemistry Journal, 135, 1828–1835.

Rosita, R. (2016). Penentuan Kandungan Kimia Biji Kopi Arabika Gayo secara Non-destruktif dengan Near Infrared Spectroscopy. Tesis Program Studi Teknologi Pascapanen. Institut Pertanian Bogor: Bogor.

Rosita, R., Budiastra, I. W., & Sutrisno, S. (2016). Prediksi Kandungan Kafein Biji Kopi Arabika Gayo dengan Near Infrared Spectroscopy. Jurnal Keteknikan Pertanian, 4(2), 179–186.

Towaha, J., Purwanto, E. H., Supriadi, H., Raya, J., Km, P., & Indonesia, S. (2015). Atribut Kualitas Kopi Arabika pada Tiga Ketinggian Tempat di Kabupaten Garut. Jurnal Tanaman Industri dan Penyegar, 2(1), 29–34.

Wei, F., & Tanokura, M. (2015). Coffee in Health and Disease Prevention, Chapter 10: Chemical Changes in the Components of Coffee Beans during Roasting. Academic Press, Elsevier Inc.

Williams P and Norris K. (1990). Near-infrared technology in the agricultural and food industries. American As-sociation of cereal chemical, Inc. St. Paul. USA[US]: 146.

Zhang, X., Li, W., Yin, B., Chen, W., Kelly, D. P., Wang, Du, Y. (2013). Molecular and Biomolecular Spectroscopy Improvement of near infrared spectroscopic (NIRS) analysis of caffeine in roasted Arabica coffee by variable selection method of stability competitive adaptive reweighted sampling (SCARS).

Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy Journal, 114, 350–356.




DOI: http://dx.doi.org/10.32765/warta%20ihp.v36i1.4767

Refbacks

  • There are currently no refbacks.


Copyright (c) 2019 Warta Industri Hasil Pertanian

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Our journal indexed by:


Copyright © Balai Besar Industri Agro, 2018. Powered By OJS 

Theme design credited to MEV edited by Warta IHP

Creative Commons License   
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License