PEMODELAN PENGERINGAN KUNYIT (CURCUMA DOMESTICA VAL.) BERBASIS MACHINE VISION DENGAN MENGGUNAKAN ARTIFICIAL NEURAL NETWORK

Authors

  • Muchammad Zakaria Brawijaya University
  • Yusuf Hendrawan Brawijaya University
  • Gunomo Djojowasito Brawijaya University

DOI:

https://doi.org/10.21776/ub.jtp.2017.018.01.2

Keywords:

Artificial Neural Network, Kunyit, Kadar Air, Machine Vision

Abstract

ABSTRAK

Pengeringan pada kunyit (Curcuma Domestica Val.) bertujuan untuk memperpanjang umur simpan serta mengurangi kadar air hingga batas perkembangan mikroorganisme dan kegiatan enzim yang menyebabkan pembusukan menjadi terhambat. Saat ini, pengeringan kunyit menggunakan sinar matahari dan alat pengering mekanis dengan kontrol waktu dan suhu. Banyaknya kendala pada proses pengeringan meyebabkan dibutuhkannya suatu teknologi yang dapat memonitoring kadar air dari kunyit secara pasti dan akurat, yaitu dengan mesin pengering berbasis machine vision dan artificial neural network (ANN). Tujuan penelitian untuk mengetahui waktu terbaik untuk pengeringan kunyit berbasis machine vision dengan menggunakan ANN, mengetahui perbedaan grafik ANN untuk gambar yang memenuhi syarat kadar air standar pengeringan kunyit, mengetahui ANN terbaik dalam proses pengeringan kunyit. Penelitian ini menggunakan metode deskriptif yang terdiri dari lama waktu pengeringan yaitu 5 jam dengan 5 kali pengulangan dan menggunakan bahan kunyit. Metode aplikasi mesin pengering yang dilengkapi dengan machine vision sebagai pengambil data gambar pada bahan, kemudian di ekstrak warnanya untuk mengetahui nilai (red, green, dan blue). Proses pembangunan model ANN digunakan learning rate sebesar 0.1, 0.2, 0.3, 0.4, dan 0.5 pada momentum rate sebesar 0.5, 0.6, 0.7, 0.8, dan 0.9. Hasil learning process terbaik adalah learning rate 0.3 dan momentum rate 0.9. Model ANN dengan nilai error terendah yaitu untuk training 0.005 MSE, dan 24.59% ARE (Average Error), untuk validasi 0.005 MSE dan 25.35% ARE

 

ABSTRACT

To maintain turmeric (Curcuma domestica Val.) to be durable is by drying. The purpose of drying to reduce the moisture content up to limit the development of microorganisms and enzyme activities that cause spoilage. Nowadays, turmeric drying is using sunlight and mechanical drier with time and temperature control. However, drying process often arise various problems, therefore require a technology to monitor the moisture content of turmeric definitively and accurately, that is using drying machine-based machine vision and ANN (Artificial Neural Network). The purpose of this study to determine the best time for drying turmeric-based machine vision by using ANN, to know the difference of ANN’s graph for image that qualify the standard of moisture content in drying turmeric, to know the best ANN in the turmeric drying process. This research use descriptive method that consisted of duration of drying time, 5 hours with five repetitions. The application of drying machine equipped with a machine vision is to take data image on the materials, then color was extracted to know the value of (red, green, and blue). In the development process of ANN model, use learning rate of 0.1, 0.2, 0.3, 0.4, and 0.5 on the momentum rate of 0.5, 0.6, 0.7, 0.8, and 0.9. Best results is showed on the learning process of learning rate 0.3 and momentum rate 0.9. ANN models with the lowest error value is for training 0005 MSE and 24.59% ARE, for validation MSE 0005 and 25.35% ARE

References

Adawyah, R. 2008. Pengolahan dan Pengawetan Ikan. Bumi Aksara, Jakarta

Alfina, O. 2012. Analisis Perbandingan Neural Network Backpropagation dengan Simple Perceptron dalam Mengenali Image Daun. Tesis. USU, Sumatera Utara

Asghari, G, A, Mostajeran, A, Shebli, M. 2009. Curcuminoid and essential oil components of turmeric at different stages of growth cultivated. Research in Pharmaceutical Sciences. 4(1):55-61

Asriyanti. 2013. Mempelajari Pembuatan Bumbu Inti Kunyit (Curcuma Domestica Val) Bubuk. Skripsi. Unhas. Sulawesi Selatan

Bas, E, Uslu, V, R, Egrioglu, E. 2016. Robust learning algorithm for multiplicative neuron model artificial neural networks. Expert Systems with Applications. 56:80-88

Boniglia, C, Aureli, P, Bortolin, E, Onori, S. 2009. Verification of imported food upon import for radiation processing: Dried herbs, including herbs used in food supplements, and spices by PSL and TL. Radiation Physics and Chemistry. 78:679-681

Borah, A, Hazarika, Khayer, S, M. 2015. Drying kinetics of whole and sliced turmeric rhizomes (Curcuma longa L.) in a solar conduction dryer. Information Processing in Agriculture. 2(2):85-92

Box, H. 1989. Developments in the spices trade: a Review. British Food Journal. 91(6):15-18

Chan, E, W, C, Lye, P, Y, Eng, S, Y, Tan, Y, P. 2013. Antioxidant properties of herbs with enhancement effects of drying treatments: a synopsis. Free Radicals and Antioxidants. 3(1):2-6

Dhanalakshmi, K, Bhattacharya, S. 2014. Agglomeration of turmeric powder and its effect on physico-chemical and microstructural characteristics. Journal of Food Engineering. 120:124-134

Fadilah, Distantina, S, Pratiwi, D, B, Muliapakarti, R, Danarto, Y, C, Wiratni,

Fahrurrozi, M. 2010. Pengaruh metode pengeringan terhadap kecepatan pengeringan dan kualitas karagenan dari rumput laut Eucheuma cottonii. Prosiding Seminar Rekayasa Kimia dan Proses, Universitas Diponegoro, Semarang, pp. 1–6

Hameed, A, A, Karlik, B, Salman, M, S. 2016. Back-propagation algorithm with variable adaptive momentum. Knowledge Based Systems. 114:79-87

Harsha, M, R, Prakash, S, V, C, Dharmesh, S, M. 2016. Modified pectic polysaccharide from turmeric (Curcuma longa): A potent dietary component against gastric ulcer. Carbohydrate Polymers. 138:143-155

Hayat, M, Bennamoun, M, El-Salam, A, A. 2016. An RGB–D based image set classification for robust face recognition from Kinect data. Neurocomputing. 171:889-900

Hee Kim, J, Jeong Yang, H, Jae Kim, Y, Park, S, Hee Lee, O, Kim, K, S, Kim, M, J. 2016. Korean turmeric is effective for dyslipidemia in human intervention study. Journal of Ethnic Foods. 3(3):213-221

Hermawan, A. 2006. Jaringan Syaraf Tiruan. Penerbit Andi, Yogyakarta

Hmar, B, Z, Kalita, D, Srivastava, B. 2017. Optimization of microwave power and curing time of turmeric rhizome (Curcuma Longa L.) based on textural degradation. LWT-Food Science and Technology. 76:48-56

Khalili, K, Bagherian, M, Khisheh, S. 2014. Numerical Simulation of Drying Ceramic Using Finite Element and Machine Vision. Procedia Technology. 12:388-393

Khazaei, N, B, Tavakoli, T, Ghassemian, H, Khoshtaghaza, M, H, Banakar, A. 2013. Applied machine vision and artificial neural network for modeling and controlling of the grape drying process. Computers and Electronics in Agriculture. 98:205-213

Kusuma, I, W, Abadi, A, M. 2011. Aplikasi model backpropagation neural network untuk perkiraan produksi tebu pada pt perkebunan nusantara IX. Prosiding Seminar Nasional Matematika dan Pendidikan Matematika, UNY, Yogyakarta, pp. 97-108

Kusumaningrum, H, P, Kusdiyantini, E, Pujiyanto, S. 2015. Kualitas simplisia tanaman biofarmaka Curcuma domestica setelah proses pemanasan pada suhu dan waktu bervariasi. Bioma. 17(1):27-33

Lee Yue, G, G, Kwok, H, F, Ming Lee, J, K, Jiang, L, Wai Wong, E, C, Gao, S, Lok Wong, H, Li, L, Man Chan, K, Chung Leung, P, Pui Fung, K. 2016. Combined therapy using bevacizumab and turmeric ethanolic extract (with absorbable curcumin) exhibited beneficial efficacy in colon cancer mice. Pharmacological Research. 111:43-57

Leon Roque, N, Abderrahim, M, Nunez Alejos, L, Arribas, S, M, Condezohoyos, L. 2016. Prediction of fermentation index of cocoa beans (Theobroma cacao L.) based on color measurement and artificial neural networks. Talanta. 161:31-39

Lorentzen, G, Breiland, M, S, W, Ostli, J, Wang Andersen, J, Olsen, R, L. 2015. Growth of halophilic microorganisms and histamine content in dried salt-cured cod (Gadus morhua L.) stored at elevated temperature. LWT-Food Science and Technology. 60(1):598-602

Luc Buessler, J, Smagghe, P, Phillippe Urban, J. 2014. Image receptive fields for artificial neural networks. Neurocomputing. 144:258-270

Man, S, Chai, H, Qiu, P, Liu, Z, Fan, W, Wang, J, Gao, W. 2015. Turmeric enhancing anti-tumor effect of Rhizoma paridis saponins by influencing their metabolic profiling in tumors of H22 hepatocarcinoma mice. Pathology-Research and Practice. 211(12):948-954

Mason, R, O. 2003. Ethical issues in artificial intelligence. Encyclopedia of Information Systems. 239-258

Morgan, C, A, Herman, N, White, P, A, Vesey, G. 2006. Preservation of micro-organisms by drying; a review. Journal of Microbiological Methods. 66(2):183-193

Nadian, M, H, Abbaspour-Fard, M, H, Martynenko, A, Golzarian, M, R. 2017. An intelligent integrated control of hybrid hot air-infrared dryer based on fuzzy logic and computer vision system. Computers and Electronics in Agriculture. 137:138-149

Narayanan, S, J, Bhatt, R, B, Perumal, B. 2016. Improving the accuracy of fuzzy decision tree by direct back propagation with adaptive learning rate and momentum factor for user localization. Procedia Computer Science. 89:506-513

Peschl, M, F. 1993. Knowledge representation in cognitive systems and science: In search of a new foundation for philosophy of science from a neurocomputational and evolutionary perspective of cognition. Journal of Social and Evolutionary Systems. 16(2):181-213

Plotto, A. 2004. Turmeric : post – production Management. Dilihat 7 Februari 2017. <http://www.fao.org/3/a-ax446e.pdf>

Prasad, J, Vijay, V, K, Tiwari, G, N, Sorayan, V, P, S. 2006. Study on performance evaluation of hybrid drier for turmeric (Curcuma longa L.) drying at village scale. Journal of Food Engineering. 75(4):497-502

Pratt, M, A, Konda, S, Chu, C, H, H. 2008. Texture-based image steganalysis by artificial neural networks. International Journal of Intelligent Computing and Cybernetics. 1(4):549-562

Rahayu,H, D, I. 2010. Pengaruh Pelarut Yang Digunakan Terhadap Optimasi Ekstraksi Curcumin pada Kunyit (Curcuma Domestica Val.). Skripsi. UMS. Surakarta

Sangwan, A, Kawatra, A, Sehgal, S. 2012. Nutrient composition of mint powder prepared from various drying methods. Nutrition & Food Science. 42(1):21-25

Schaarschmidt, S. 2016. Public and private standards for dried culinary herbs and spices—part I: standards defining the physical and chemical product quality and safety. Food Control. 70:339-349

Shin, H, S, See, H, J, Jung, S, Y, Choi, D, W, Kwon, D, A, Bae, M, J, Sung, K, S, Shon, D, H. 2015. Journal of Ethnopharmacology. 175:21-29

Siallagan. B. 2009. Kajian Proses Pengeringan Kemoreaksi Jahe Dengan Kapur Api (CaO). Skripsi. USU, Sumatera Utara

Syukur, C. 2010. Turina, varietas unggul kunyit kurkumin tinggi. Dilihat 6 Februari 2016. <http://pustaka.litbang.pertanian.go.id/inovasi/kl10111.pdf>

Teimouri, N, Omid, M, Mollazade, K, Rajabipour, A. 2014. A novel artificial neural networks assisted segmentation algorithm for discriminating almond nut and shell from background and shadow. Computers and Electronics in Agriculture. 105:34-43

Trujillo, J, Chirino, Y, I, Moliana-Jijon, E, Anderica-Romero, A C, Tapia, E T, Pedraza-Chaverri, J. 2013. Renoprotective effect of the antioxidant curcumin: recent findings. Redox Biology. 1(1):448-456

WWF. 2009. Hutan indonesia: penyerap atau pelepas emisi gas rumah kaca?. Dilihat 20 Januari 2017. <http://d2d2tb-15kqhejt.cloudfront.net/downloads/lembar_fakta_deforestasi_tanpa_foto.

pdf>

Xie, Y, Gao, Z, Liu, Y, Xiao, H. 2017. Pulsed vacuum drying of rhizoma dioscoreae slices. LWT-Food Science and Technology. 80:237-249

Xu, J, L, Sun, D, W. 2017. Identification of freezer burn on frozen salmon surface using hyperspectral imaging and computer vision combined with machine learning algorithm. International Journal of Refrigeration. 74:151-164

Xu, Y, Y. 2016. Multiple-instance learning based decision neural networks for image retrieval and classification. Neurocomputing. 171:826-836

Yao, Y. 2016. Enhancement of mass transfer by ultrasound: Application to adsorbent regeneration and food drying/dehydration. Ultrasonics Sonochemistry. 31:512-531

Downloads

Published

2017-04-03

Issue

Section

Articles