Extraction of Natural Dye from Flame of Forest ...

Due to the harmful effects of synthetic dye, dying has been forced to substitute preparation of dye using natural sources like flowers, leaves, stem, bark etc. These natural dyes are eco-friendly having no side effect on skin and no disposal problem. In this present study, a computer-stimulated model is developed to get the correlation between the input (variable parameters responsible for extraction) and output parameters (concentration of dye) for dye extraction from the Flame of Forest flower. After a number of trials, the best feed forward neural network has been developed with three layers: an input layer of 3 neurons (extraction time, temperature, amount of flower), a hidden layer with 10 neurons, and the output layer with 1 neuron which gives the total dye present in the solution of Flame of Forest. The developed Artificial Neural Network (ANN) model provides a good interpretation of the experimental data and it shows high correlation between the experimental and simulated values of dye extraction. Finally, experimental and simulated ANN model for total dye extraction from 1 gm and 2 gm flame of forest flowers were statistically compared by % error and Chi-squared test ( ) based on the validation data set. Results suggest that experimental data and the error between the experimental and simulated results are very low.