Dendrobium sonia-28 is a popular orchid hybrid for its flowering recurrence and dense inflorescences which currently facing serious production problems due fungal diseases. In the present study, Protocorm like bodies (PLBs) of Dendrobium sonia-28 were subjected to different doses of gamma irradiation (10-200 Gy) followed by inoculation with various concentrations of fusarium proliferatum culture filtrate (CF) (2.5-20%). The results from these measurements were used in establishing an artificial neural network model meant to predict the result of more samples while being treated as carrying out laboratory measurements would be time consuming. CF and gamma irradiation were model inputs, while output was result value. The prediction performances of various neural network modelswere evaluated using statistical performance indices such as root of the mean squared error (RMSE), the mean squared error(MSE), and the multiple coefficient of determination (R2). The results show that the multilayer perceptron (MLP) neural network model with different nodes in the hidden layer was desirable for predicting results. Artificial Neural Networks analysis indicated that survival and growth rates of treated PLBs were dependent to treatment doses. Biochemical results revealed that the chlorophyll and total soluble protein decreased notably as the irradiation and inoculation concentration increases.
RahelehDehgahi and AlirezaJoniyas (2017); Use of Artificial Neural Network in Predicting Survival and Growth Rates and Biochemical Characteristics in Dendrobium Sonia-28;
Int J Sci Res Publ 7(6) (ISSN: 2250-3153). http://www.ijsrp.org/research-paper-0617.php?rp=P666534