Jove
Visualize
Contact Us
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

Related Experiment Videos

Using historical data for bioprocess optimization: modeling wine characteristics using artificial neural networks and

S Vlassides1, J G Ferrier, D E Block

  • 1Department of Viticulture and Enology, University of California, One Shields Avenue, Davis, CA 95616, USA.

Biotechnology and Bioengineering
|March 20, 2001
PubMed
Summary
This summary is machine-generated.

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

Interdisciplinary collaboration in the 21st century.

Minnesota medicine·2001
Same author

Characterizing the production of a wild-type and benomyl-resistant Fusarium lateritium for biocontrol of Eutypa lata on grapevine.

Journal of industrial microbiology & biotechnology·2001
Same author

Technology-enhanced distance education: from experimentation to concerted action.

Journal of professional nursing : official journal of the American Association of Colleges of Nursing·2001
Same author

Differences in tobacco assessment and intervention practices: a regional snapshot.

Preventive medicine·2000
Same author

Tobacco counseling practices of dentists compared to other health care providers in a midwestern region.

Journal of dental education·1999
Same author

Technoglitches in distance education.

Computers in nursing·1999
Same journal

Microbial Hydrolysates as Amino Acid Source in Cell Culture Media for Cellular Agriculture.

Biotechnology and bioengineering·2026
Same journal

LLM-Guided Parameter Optimization for Mechanistic CHO Cell Bioreactor Models.

Biotechnology and bioengineering·2026
Same journal

Three-Dimensional-Printed Polylactic Acid Scaffolds Coated With a Paeonol-Incorporated Gelatin/Bioactive Glass Composite Layer for Enhanced Osteogenic Performance.

Biotechnology and bioengineering·2026
Same journal

Recent Progress in Antimicrobial Peptides (AMPs) Towards Enhanced Selectivity and Reduced Cytotoxicity by Molecular Engineering.

Biotechnology and bioengineering·2026
Same journal

mZVI-Enhanced Mixed Nitrogen Removal in Klebsiella oxytoca via Coordinated Electron Transfer and Metabolic Reprogramming.

Biotechnology and bioengineering·2026
Same journal

Growth Model for Continuous Culture of a Hydrogen-Oxidizing Bacterium, Hydrogenophilus thermoluteolus Strain TH-1.

Biotechnology and bioengineering·2026
See all related articles

Artificial neural networks (ANNs) can optimize fermentation processes by learning from historical data. This approach predicts fermentation kinetics and wine quality, improving productivity and product characteristics.

Area of Science:

  • Biotechnology
  • Machine Learning
  • Food Science

Background:

  • Fermentation process optimization is complex and challenging for traditional methods, especially at production scales.
  • Existing manufacturing data is often underutilized for process improvement.
  • Biological systems' complexity limits the effectiveness of mathematical models and designed experiments.

Purpose of the Study:

  • To develop a novel optimization method using historical process data and artificial neural networks (ANNs).
  • To correlate processing inputs with productivity and quality outputs in fermentation.
  • To identify optimal processing conditions for desired product characteristics and constraints.

Main Methods:

  • Training ANNs with historical process data to model input-output relationships.

Related Experiment Videos

  • Employing an optimization routine with trained ANNs to determine optimal processing conditions.
  • Utilizing a hybrid neural network training method, Stop Training with Validation (STV), for optimal architecture and training.
  • Investigating the interpolation and extrapolation capabilities of trained ANNs with sparse industrial data.

    • Main Results:

    • Demonstrated successful prediction of yeast-fermentation kinetics, chemical, and sensory properties of wine using trained ANNs.
    • Validated the ability of ANNs to predict wine characteristics based on grape properties and processing parameters.
    • Showcased the effectiveness of the STV method for neural network training.
    • Confirmed the capability of ANNs to interpolate and extrapolate using non-evenly spaced industrial data.

    Conclusions:

    • Historical process data combined with ANNs offers a powerful approach for fermentation optimization.
    • This method can be generalized for various fermentation processes to enhance quality and productivity.
    • The developed technique leverages existing industrial data for cost-effective process improvement.