Comparison of Artificial Neural Networks (ANN) and Adaptive Neuro-Fuzzy Inference System (ANFIS) Models in Simulating Polygalacturonase Production

Download

index.pdf

Date

2016-11-01

Author

UZUNER, SİBEL
Çekmecelioğlu, Deniz

Metadata

Show full item record

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

Item Usage Stats

194
views

102
downloads

The artificial neural network (ANN) method was used in comparison with the adaptive neuro-fuzzy inference system (ANFIS) to describe polygalacturonase (PG) production by Bacillus subtilis in submerged fermentation. ANN was evaluated with five neurons in the input layer, one hidden layer with 7 neurons, and one neuron in the output layer. Five fermentation variables (pH, temperature, time, yeast extract concentration, and K2HPO4 concentration) served as the input of the ANN and ANFIS models, and the polygalacturonase activity was the output. Coefficient of determination (R-2) and root mean square values (RMSE) were calculated as 0.978 and 0.060, respectively for the best ANFIS structure obtained in this study. The R-2 and RMSE values were computed as 1.00 and 0.030, respectively for the best ANN model. The results showed that the ANN and ANFIS models performed similarly in terms of prediction accuracy.

Subject Keywords

Back-propagation network, Artificial intelligence, Polygalacturonase, Adaptive neuro-fuzzy inference system

URI

https://hdl.handle.net/11511/33030

Journal

BIORESOURCES

DOI

https://doi.org/10.15376/biores.11.4.8676-8685

Collections

Department of Food Engineering, Article

Suggestions

OpenMETU
Core

Evaluation of PCB dechlorination pathways in anaerobic sediment microcosms using an anaerobic dechlorination model Demirtepe, Hale; Kjellerup, Birthe; Sowers, Kevin R.; İmamoğlu, İpek (Elsevier BV, 2015-10-15) A detailed quantitative analysis of anaerobic dechlorination (AD) pathways of polychlorinated biphenyls (PCBs) in sediment microcosms was performed by applying an anaerobic dechlorination model (ADM). The purpose of ADM is to systematically analyze changes in a contaminant profile that result from microbial reductive dechlorination according to empirically determined dechlorination pathways. In contrast to prior studies that utilized modeling tools to predict dechlorination pathways, ADM also provides quant...
Optimization and field application of a filter pack system for the simultaneous sampling of atmospheric HNO3, NH3 and SO2 Karakas, D; Tuncel, Süleyman Gürdal (1997-06-01) Optimization and field application of a filter pack system for the simultaneous collection of atmospheric gas-phase HNO3, NH3 and SO2 have been studied. A Teflon prefilter was used to remove particulate matter. Nylon filter, oxalic-acid-treated Whatman 41 filter and sodium-carbonate-treated Whatman 41 filter were used for the collection of HNO3, NH3 and SO2, respectively. For the collection of gas-phase HNO3, nylon filters had better efficiency and capacity as compared to NaCl-impregnated Whatman 41 filters...
Comparison of anaerobic acrylic acid biotransformation in single- and two-stage pH-stat completely stirred tank reactor systems Demirer, Göksel Niyazi; Speece, RE (Wiley, 2000-01-01) Performance of single- and two-stage pH-stat completely stirred tank reactor (CSTR) systems for anaerobic acrylic acid biotransformation was investigated and compared. In the experiments, acetate was added with acrylic acid. Acetate concentration in both single- and two-stage reactors was continuously maintained at a nonlimiting concentration of 2000 +/- 200 mg/L. using a computer-controlled pH-stat system to allow observation of the effect of acrylate biotransformation on the more sensitive methanogenic st...
Artificial-neural-network prediction of hexagonal lattice parameters for non-stoichiometric apatites Kockan, Umit; Ozturk, Fahrettin; Evis, Zafer (2014-01-01) In this study, hexagonal lattice parameters (a and c) and unit-cell volumes of non-stoichiometric apatites of M-10(TO4)(6)X-2 are predicted from their ionic radii with artificial neural networks. A multilayer-perceptron network is used for training. The results indicate that the Bayesian regularization method with four neurons in the hidden layer with a tansig activation function and one neuron in the output layer with a purelin function gives the best results. It is found that the errors for the predicted ...
Kinetic analyses of the effects of temperature and light intensity on growth, hydrogenm production and organic acid utilization by rhodobacter capsulatus Sevinç, Pelin; Gündüz, Ufuk; Department of Biotechnology (2010) Effects of temperature and light intensity on photofermentative hydrogen production by Rhodobacter capsulatus DSM1710 by use of acetic and lactic acids as substrates were studied. Experiments were conducted at 20, 30 and 38oC incubator temperatures under light intensities in the 1500 – 7000 lux range. pH of the medium and quantity of hydrogen forming together with quantity of biomass, and concentrations of acetic, lactic, formic, butyric and propionic acids in the medium were determined periodically. Growth...

Citation Formats

S. UZUNER and D. Çekmecelioğlu, “Comparison of Artificial Neural Networks (ANN) and Adaptive Neuro-Fuzzy Inference System (ANFIS) Models in Simulating Polygalacturonase Production,” BIORESOURCES, pp. 8676–8685, 2016, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/33030.