การทำนายปริมาณสารไลโคปีนในฟักข้าวด้วยการวิเคราะห์ภาพสี RGB ร่วมกับวิธีการโครงข่ายประสาทเทียม
Article Sidebar
Main Article Content
Abstract
This work presents a method to predict the lycopene quantity in the gac-fruit using coupled RGB images analysis and artificial neural network (ANN). 75 gac-fruits were photographed and the photos were analyzed to separate the RGB extraction, later the data were used in the prediction model. Each gac-fruit was tested to search for lycopene using UV-spectrophotometric and was used as the output data for the training and testing process of the model. The 3 layers ANN models with different numbers of hidden node (2-12), epoch number (300-1,500), learning rate (0.1-0.4) and different momentum (0.1-0.4) were developed and examined. In addition, the k-nearest neighbor (KNN) with different k parameters (2-10) was developed to compare with prediction from the ANN model. The best prediction results are obtained from the ANN model with the number of nodes in the input layer, hidden layer and output layer are 3, 3 and 1 respectively. The results showed that the mean squared error (MSE) was 1.7252 and the regression coefficient of determination (R2) was 0.9867.
Keywords: gac-fruit; lycopene; artificial neural network; image processing; k-nearest neighbor
Article Details
References
[2] Yua, J.S., Roh, H.S., Lee, S., Jung, K., Baek, K.H. and Kim, K.H., 2017, Antiproliferative effect of Momordica cochinchinensis seeds on human lung cancer cells and isolation of the major constituents, Rev Bras Farmacogn. 27: 329-333
[3] Kang, J.M., Kim, N., Kim, B., Kim, J.H., Lee, B.Y., Park, J.H., Lee, M.K., Lee, H.S., Kim, J.S., Jung, H.C. and Song, I.S., 2010, Enhancement of gastric ulcer healing and angio-genesis by Cochinchina Momordica seed extract in rats, J. Korean Med. Sci. 25: 875-881.
[4] Bhumsaidon, A. and Chamchong, M., 2016, Variation of lycopene and beta-carotene contents after harvesting of gac fruit and its prediction, ANRES 50: 257-263.
[5] Liu, Y., Pu, H. and Sun, D.W., 2017, Hyperspectral imaging technique for evaluating food quality and safety during various processes: A review of recent applications, Trends Food Sci. Tech. 69: 25-35.
[6] Gomes, J.F.S, Vieira, R.R. and Leta, F.R., 2013, Colorimetric indicator for classification of bananas during ripening, Sci. Hort. 150: 201-205.
[7] Liming, X. and Yanchao, Z., 2010, Automated strawberry grading system based on image processing, Comput. Electron. Agr. 71S: S32-S39.
[8] Manninen, H., Paakki, M., Hopia, A. and Franzen, R., 2015, Measuring the green color of vegetables from digital images using image analysis, LWT Food Sci. Technol. 63: 1184-1190.
[9] Khazaei, N.B., Tavakoli, T., Ghassemian, H., Khoshtaghaza, M.H. and Banakar, A., 2013, Applied machine vision and artificial neural network for modeling and controlling of the grape drying process, Comput. Electron. Agr. 98: 205-213.
[10] Nadian, M.H., Rafiee, S., Aghbashlo, M., Hosseinpour, S. and Mohtasebi, S.S., 2015, Continuous real-time monitoring and neural network modeling of apple slices color changes during hot air drying, Food Bioprod. Process. 94: 263-274.
[11] Han, J., Kamber, M. and Pei, J., Data Mining Concepts and Techniques, 3rd Ed., Elsevier, Inc., Massachusetts, 398 p.
[12] Yam, L.K. and Papadakis, E.S., 2004, A simple digital imaging method for measuring and analyzing color of food surfaces, J. Food Eng. 61: 137-142.
[13] Chen, X., Xun, Y., Lia, W. and Zhang, J., 2010, Combining discriminant analysis and neural networks for corn variety identification, Comput. Electron. Agr. 71S: S48-S53.