Optimisation of a multi gas-sensor system, training of the artificial neural network and use of the electronic nose system for quality assessment of whiting (Merlangius merlangus).

Summary

Results of the optimisation experiments and testing the ability of the system for quality assessment of whiting are presented in the paper. After the most appropriate set of metal oxide gas sensors was chosen, the influence of flow rate, head space temperature, sample weight and head space generation time on gas sensor responses were investigated. Optimal experimental parameters were selected in order to standardise further fish experiments with this system. The signal pattern from the sensors is collected by a computer and further processed by an artificial neural network (ANN). Before the electronic nose system could be used for quality classification of fish samples, the ANN had to be trained.

Available documents

Format PDF

Pages: p 110-118

Available

  • Public price

    20 €

  • Member price*

    Free

* Best rate depending on membership category (see the detailed benefits of individual and corporate memberships).

Details

  • Original title: Optimisation of a multi gas-sensor system, training of the artificial neural network and use of the electronic nose system for quality assessment of whiting (Merlangius merlangus).
  • Record ID : 1999-0293
  • Languages: English
  • Source: Proceedings of the Final Meeting of the Concerted Action "Evaluation of Fish Freshness" AIR3CT94 2283: Methods to Determine the Freshness of Fish in Research and Industry.
  • Publication date: 1997/11/12
  • Document available for consultation in the library of the IIR headquarters only.

Links


See other articles from the proceedings (39)
See the conference proceedings