Nasaruddin, Ricca Rahman and Jami, Mohammed Saedi and Alam, Md. Zahangir (2011) The potential of artificial neural network (ANN) in optimizing bioconversion process: in case of media constituents of citric acid production from palm oil Empty Fruit Bunches (EFB). In: 2nd International Conference on Biotechnology Engineering (ICBioE 2011), 17 - 19 May 2011, Kuala Lumpur.
PDF (The potential of artificial neural network)
- Accepted Version
Restricted to Repository staff only Download (213kB) | Request a copy |
Abstract
This work aims at optimizing the media constituents for citric acid production from oil palm empty fruit bunches (EFB) as renewable resource using artificial neural network (ANN) approach. The bioconversion process was done through solid state bioconversion using Aspergillus niger. ANN model was built using MATLAB software. A 20 dataset of an earlier published paper was used to developed ANN. The predictive and generalization ability of ANN and the results of RSM in the used published paper were compared. The determination coefficient (R2-value) for ANN and RSM models were 0.997 and 0.985, respectively, indicating the superiority of ANN in capturing the non-linear behavior of the system. Validation process was done and the maximum citric acid production (147.74 g/kg-EFB) was achieved using the optimal solution from ANN which consists of 6.1% sucrose, 9.2% mineral solution and 15.0% inoculum.
Item Type: | Conference or Workshop Item (Full Paper) |
---|---|
Additional Information: | 5545/3170 |
Uncontrolled Keywords: | EFB, ANN, Sucrose, Mineral Solution, Inoculum, Citric acid |
Subjects: | T Technology > TP Chemical technology > TP155 Chemical engineering |
Kulliyyahs/Centres/Divisions/Institutes (Can select more than one option. Press CONTROL button): | Kulliyyah of Engineering > Department of Biotechnology Engineering |
Depositing User: | Prof. Ir. Dr. Mohammed Saedi Jami, PhD CEng MIChemE |
Date Deposited: | 14 Oct 2011 11:08 |
Last Modified: | 14 Oct 2011 11:08 |
URI: | http://irep.iium.edu.my/id/eprint/3170 |
Actions (login required)
View Item |