LOGIN TO YOUR ACCOUNT

Username
Password
Remember Me
Or use your Academic/Social account:

CREATE AN ACCOUNT

Or use your Academic/Social account:

Congratulations!

You have just completed your registration at OpenAire.

Before you can login to the site, you will need to activate your account. An e-mail will be sent to you with the proper instructions.

Important!

Please note that this site is currently undergoing Beta testing.
Any new content you create is not guaranteed to be present to the final version of the site upon release.

Thank you for your patience,
OpenAire Dev Team.

Close This Message

CREATE AN ACCOUNT

Name:
Username:
Password:
Verify Password:
E-mail:
Verify E-mail:
*All Fields Are Required.
Please Verify You Are Human:
fbtwitterlinkedinvimeoflicker grey 14rssslideshare1
Dziuba, Bartłomiej; Nalepa, Beata (2012)
Publisher: Faculty of Food Technology and Biotechnology, University of Zagreb
Journal: Food Technology and Biotechnology
Languages: English
Types: Article
Subjects: lactic acid bacteria; propionic acid bacteria; FTIR spectroscopy; artificial neural networks, bakterije mliječne kiseline; bakterije propionske kiseline; FTIR spektroskopija; umjetne neuronske mreže
In the present study, lactic acid bacteria and propionic acid bacteria have been identified at the genus level with the use of artificial neural networks (ANNs) and Fourier transform infrared spectroscopy (FTIR). Bacterial strains of the genera Lactobacillus, Lactococcus, Leuconostoc, Streptococcus and Propionibacterium were analyzed since they deliver health benefits and are routinely used in the food processing industry. The correctness of bacterial identification by ANNs and FTIR was evaluated at two stages. At first stage, ANNs were tested based on the spectra of 66 reference bacterial strains. At second stage, the evaluation involved 286 spectra of bacterial strains isolated from food products, deposited in our laboratory collection, and identified by genus-specific PCR. ANNs were developed based on the spectra and their first derivatives. The most satisfactory results were reported for the probabilistic neural network, which was built using a combination of W5W4W3 spectral ranges. This network correctly identified the genus of 95 % of the lactic acid bacteria and propionic acid bacteria strains analyzed.
  • No references.
  • No related research data.
  • No similar publications.

Share - Bookmark

Cite this article