Asian Journal of Microbiology, Biotechnology & Environmental Sciences Paper

Vol 11, Issue 4, 2009; Page No.(777-782 )

VALIDITY OF ARTIFICIAL NEURAL NETWORK FOR PREDICTING EFFECT OF MEDIA COMPONENTS ON ENZYME PRODUCTION BY A. NIGER IN SOLID STATE FERMENTATION

ARUNA SINGH, DIVYA TATEWAR, S.L. PANDHARIPANDE AND RN. SHASTRI

Abstract

Solid state fermentation involves treatment of biodegradable solid substrate with microorganisms, and is characterized by the presence of limited moisture, sufficient to solubilise the nutrients, but avoid leaching . Water activity (a) is maintained around 0.85, and is specially suitable for production of extracellular enzymes and metabolites by molds. It is widely utilized for biotransformation of agricultural waste for recovery of industrial enzymes, organic solvents and other biochemicals. On account of difference in water binding capacity of different substrates, optimum moisture level needs to be established for various combination of substrates, which involves extensive laborious experimental work. Present investigations were carried out to study the application of Artificial Neural Network as a tool for predicting cellulase and xylanase production by Aspergillus niger as a function of bagasse content and moisture level incorporation in basic wheat bran medium. A correlation coefficient > 0.8 and root mean square error < 0.2 indicates ANN as a good prediction tool for complex biological process.

Enter your contact information below to receive full paper.
Your Name :
Email:
Phone:
City:
Cost of Full Paper: Rs.150 for Indian Nationals or $20 (USD) for international subscribers.
By clicking on Request Paper you Agree to pay the above mentioned cost per paper.