AI Science Tracker
EN

Prediction of storage time in different seafood based on color values with artificial neural network modeling.

Not stated in the abstract reviewed · 29 Sep 2021 · computer science

Discovery

Prediction of storage time in different seafood based on color values with artificial neural network modeling.

Source check: Source checked. Not independent scientific confirmation.

Finding: A one-hidden-layer, 30-neuron feedforward ANN uses seafood colour coordinates (L*, a*, b*) to predict storage time. The primary paper compiled 205 literature datapoints and evaluated the model on an additional 45 literature datapoints from other seafood studies; the article reports R²=0.81 for the selected topology and a predicted/observed regression coefficient of 0.85 (the abstract rounds R² to 0.80). This is a narrow food-quality prediction result, not new measurements, and the pooled literature-derived validation is not prospective field validation.

Technology: A feedforward MLP uses measured L*, a*, b* values as inputs and one hidden layer to output storage time; topology was chosen by comparing R² and MSE.

Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.

AI contribution
A feedforward MLP uses measured L*, a*, b* values as inputs and one hidden layer to output storage time; topology was chosen by comparing R² and MSE.
Test and result
The selected 30-neuron topology reports R²=0.81 and MSE=0.20 during optimization; the paper separately reports a predicted/observed regression coefficient of 0.85 (abstract R² rounded to 0.80).
Limitation / still unknown
205 literature experiments were split into 145/30/30 train/test/validation; a distinct additional 45 literature datapoints from other species/studies were also used as validation. The evidence is pooled retrospective data, not prospective measured validation, and species/process heterogeneity limits generalization.
Evidence sources and annotation context

Evidence context (descriptions follow the cited sources; test type is a catalog classification):

Evidence sources: https://pmc.ncbi.nlm.nih.gov/articles/PMC9114270/

Source checked · editorial details

The source page was checked against this entry. Independent confirmation is not assessed by this label.

Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.

Review date: 22 Nov 2026. Review scope: Primary result-bearing material for the stated method, result and evaluation, with bibliographic version information..

No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.

Editorial assessment: Impact 3/5 · Validation 3/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.

Open in the full catalog for filters, charts and related discoveries. Browse computer science discoveries.