MODELING THE EFFECT OF FERTILIZATION ON GROWTH PATTERN OF BRASSICA RAPA USING BACKPROPAGATION NEURAL NETWORK

Wiwiet Herulambang

Sari


Application that able to predict plant growth patterns as function of nutrients obtained from fertilization pattern is very useful in agriculture, especially for research .It can be realized with support of biological sciences, mathematics, and computer technology, which popularly called by bioinformatics.The purpose of this research was to design and build a simulation system of fertilization effect on plants growth patterns with Backpropagation Neural Network. As the object of research is green mustard (Brassica Rapa). The parameters of growth modeling arethe number of seedling leaves and the length of leaves as function of changes in fertilizing elements (micro and macro) which are applied. First, green mustard are planted in the test field and then some fertilizing variations are applied for each plant. Fertilizing variations marked by variations of micro and macro nutrients in the applied fertilizer. The growth of each plant is monitored and recorded, from germination until the plant is ready for harvest. Observational data of plant growth then processed by Backpropagation Neural Network into a model of green mustard growth. From the model, software system of green mustard growth simulation as the function of fertilizing variations is built. The system testing is done using data obtained from direct observations at the plant field. Fertilization effects on green mustard growth patterns is evident in the increasing number of seedling leaves and length of leaves which indicates a reproductive improvement of the plant. Using Backpropagation Neural Network with five neuron in its hidden layer, the minimal error of the system achieved when the minimal epoch is 1000. Through experiment on several data variation of green mustard growth, the average obtained precision for NL (number of leaves) and LL (length of leaves) are 83% and 85%, respectively, which indicate that this system has achieved the expected target.

Teks Lengkap:

PDF

Referensi


Dodge, Y. (2003). The Oxford Dictionary of Statistical Terms, Oxford University Press, United Kingdom.

Draper, N.R., and Smith, H. (1998). Applied Regression Analysis, 3rd edition, John Wiley, New York USA.

Gunawan, A.D., and Soenardjo, S.N. (2009).Penerapan Algoritma Backpropagation Untuk Klasifikasi Musik Dengan Solo Instrumen, in Proceedings of Seminar Nasional Aplikasi Teknologi Informasi (SNATI).

Guo, Y.(2007).Plant Modelling and Its Applications to Agriculture, IEEE Second International Symposium on Plant Growth Modelling, Simulation, Visualization and Applications, pp. 135-141.

Kang, M.Z., Cournede, P.H., Reffye, P., Auclair, D., and Hu, B.G. (2008). Analytical study of a stochastic plant growth model: Application to the GreenLab model, Mathematics and Computers in Simulation, 78(1), pp. 57-75.

Mackay, D.J. (2003). Information theory, inference and learning algorithms, Cambridge University Press, United Kingdom.

Murray, M.T., Pizzorno, J.E., and Pizzorno, L. (2005). The Encyclopedia of Healing Foods, Simon and Schuster, Inc.

Pessarakli and Mohammad.(2002).Handbook of Plant and Crop Physiology,2nd edition, Marcel Dekker Inc., New York USA.

Rumelhart, D.E., Hinton, G.E., and Williams, R.J.(1988).Learning representations by back-propagating errors, Cognitive modeling, 5(3), pp. 533-536.

Witten, I.H., Frank, E., and Hall, M.A. (2011). Data Mining: Practical Machine Learning Tools and Techniques, Elsevier.


Refbacks

  • Saat ini tidak ada refbacks.


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