Jove
Visualize
Contact Us

Related Experiment Videos

Microbial growth modelling with artificial neural networks.

S Jeyamkonda1, D S Jaya, R A Holle

  • 1Department of Biosystems Engineering, University of Manitoba, Winnipeg, Canada.

International Journal of Food Microbiology
|April 11, 2001
PubMed
Summary

Artificial neural networks (ANN) offer a promising alternative to traditional microbial enumeration. General regression neural networks (GRNN) show superior accuracy for microbial growth modeling, especially for unseen data.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Biogenic element concentration and TOC/N ratio analysis in Veli-Akkulam Lake, Kerala: seasonal changes and urbanization impacts.

Environmental monitoring and assessment·2025
Same author

Metal Contamination of Groundwater Sources in the Environs of a Tropical Estuary in South India.

Bulletin of environmental contamination and toxicology·2021
Same author

Metal pollution of groundwater in the vicinity of Valiathura Sewage Farm in Kerala, south India.

Bulletin of environmental contamination and toxicology·2014
Same author

Studies on the changes in lipid peroxidation and antioxidants in fishes exposed to hydrogen sulfide.

Toxicology international·2010
Same author

Evaluation of air pollution tolerance index of selected plant species along roadsides in Thiruvananthapuram, Kerala.

Journal of environmental biology·2010
Same author

Studies on the changes in lipid peroxidation and antioxidants in drought stress induced cowpea (Vigna unguiculata L.) varieties.

Journal of environmental biology·2009
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Area of Science:

  • Microbiology
  • Computational Biology
  • Food Science

Background:

  • Traditional microbial enumeration is time-consuming.
  • Existing statistical models for microbial growth have accuracy limitations.

Purpose of the Study:

  • To evaluate artificial neural networks (ANN), specifically general regression neural networks (GRNN), for modeling microbial growth.
  • To compare the accuracy of GRNN models against traditional statistical models.

Main Methods:

  • Published data for Aeromonas hydrophila, Shigella flexneri, and Brochothrix thermosphacta were used.
  • General regression neural network (GRNN) models were developed for each microorganism.
  • GRNN predictions were compared to statistical model predictions using six statistical indices.

Related Experiment Videos

Main Results:

  • GRNN models significantly outperformed statistical models for training data.
  • GRNN model performance was comparable or slightly lower than statistical models for test data.
  • GRNN predictions demonstrated good performance on unseen data.

Conclusions:

  • Artificial neural networks (ANN) provide an accurate alternative for microbial growth modeling.
  • GRNNs show potential for applications in food product development and food safety risk assessment.
  • Specific statistical indices are effective for comparing predictive microbiology models.