IDENTIFIKASI TAHAP KEMATANGAN BUAH MANGGIS BERDASARKAN WARNA MENGGUNAKAN FUZZY NEURAL NETWORK IDENTIFICATION OF MANGOSTEEN STAGE MATURITY ON COLOR BASED USING FUZZY NEURAL NETWORK

Fuzzy Neural Network (FNN) has a capability to classify a pattern located within two different classes where a classical Neural Network (NN) is failed to do so. The fuzzy pattern classification is using membership degree on output of neuron as learning target. The objective of this research was to undertake non-destructive identification of fresh mangosteen stage maturity using Fuzzy Neural Network. Component of colour resulted in from image processing that influential against level of mangosteen’s maturity was used as input parameter. Percentage accuracy ratio of FNN model compare to NN for five, three, and two classification classes was 70:40, 86:65 and 90:90, respectively. The best result of FNN modeling was achieved on three class target classification (unripe, export and local) with green colour index, value, a* u*, v*, entropy, contrast, energy and homogeneity as predicting parameters and 15 neurons hidden layer. Comparisons of percentage capability of FNN against NN to identify the class were 100:0, 100:87, and 63:75.

[1]  M. Hadi Mashinchi,et al.  Three-Term Fuzzy Back-Propagation , 2009, Foundations of Computational Intelligence.

[2]  Henry O. Nyongesa,et al.  Automatic fingerprint classification system using fuzzy neural techniques , 2002, 2002 IEEE World Congress on Computational Intelligence. 2002 IEEE International Conference on Fuzzy Systems. FUZZ-IEEE'02. Proceedings (Cat. No.02CH37291).

[3]  Mario Ignacio Chacon Murguia.  A Fuzzy Neural Network Approach for Document Region Classification Using Human Visual Perception Features , 2002, Computación y Sistemas.

[4]  Chin-Teng Lin,et al.  Neural fuzzy systems , 1994 .

[5]  A. Allan,et al.  Colour development and quality of mangosteen (Garcinia mangostana L.) fruit during ripening and after harvest , 2009 .

[6]  Manish Sarkar,et al.  Backpropagation learning algorithms for classification with fuzzy mean square error , 1998, Pattern Recognit. Lett..

[7]  Nikola Kasabov.  Evolving Neuro-Fuzzy Inference Systems , 2003 .

[8]  Irmansyah.  Pemutuan Belimbing Berdasarkan Warna dan Rasa dengan Pengolahan Citra dan Logika Fuzzy , 2009 .

[9]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[10]  Sankar K. Pal,et al.  Multilayer perceptron, fuzzy sets, and classification , 1992, IEEE Trans. Neural Networks.

[11]  D. Pustaka,et al.  (Deptan) Departemen Pertanian. 2006. Prosedur Operasional Standar Pengendalian Penyakit Avian Influenza di Indonesia. Jakarta: Direktorat Jendral Peternakan Departemen Pertanian. , 2011 .

[12]  Petr Dejmek,et al.  Calibrated color measurements of agricultural foods using image analysis , 2006 .