© 2015 Elsevier B.V. All rights reserved. Second generation ethanol is produced from the carbohydrates released from the cell wall of bagasse and straw of sugarcane. The objective of this work is the characterization and application of a voltammetric electronic tongue using an array of glassy carbon electrodes modified with multi-walled carbon nanotubes containing metal (Paladium, Gold, Copper, Nickel and Cobalt) oxy-hydroxide nanoparticles (GCE/MWCNT/MetalsOOH) towards a simpler analysis of carbohydrates (glucose, xylose, galactose and mannose). The final architecture of the back-propagation Artificial Neural Network (ANN) model had 36 input neurons and a hidden layer with 5 neurons. The ANN based prediction model has provided satisfactory concentrations for all carbohydrates; the obtained response had a maximum NRMSE of 12.4% with a maximum deviation of slopes in the obtained vs. expected comparison graph of 15%. For all species, the comparison correlation coefficient was of r ≥ 0.99 for the training subset and of r ≥ 0.96 for the test subset.
|Journal||Sensors and Actuators, B: Chemical|
|Publication status||Published - 12 Jan 2016|
- Artificial neural network
- Electronic tongue
- Metal nanoparticles
- Multi-walled carbon nanotubes
- Second generation ethanol