Pork meat quality evaluation from hyperspectral observations
Bibliographic record
Abstract
Little research has been reported on the use of visible and near infrared spectroscopy for the prediction of meat quality classes.Therefore, in this study hyperspectral reflectance measurements ranging from 350 to 2500 nm were made with the help of a spectroradiometer on fresh pork loin samples belonging to four different quality classes (Red, firm, non-exudative: RFN; Pale, firm, non-exudative: PFN; Red, soft, exudative: RSE and; Pale, soft and exudative: PSE).The samples were collected from a local cutting house in Quebec, and they were classified by a meat specialist.Data collected from the samples was analyzed using a stepwise approach to identify wavebands useful in differentiating pork quality classes.Discriminant Analysis was used to evaluate the usefulness of the selected wavebands and to classify meat samples into four quality classes.An overall classification accuracy of 76% was obtained for the prediction of pork meat quality classes for unseen data.These results confirmed the possibility of the prediction of meat quality classes rather than the prediction of quality attributes, as is commonly reported in literature.Various classification methods have been used to utilize hyperspectral data for meat quality evaluation.Selection of the best method is crucial in extracting the valuable information contained in hyperspectral observations.Therefore, the performance of four classification methods, Artificial Neural Networks, Decision Trees, k-Nearest Neighbor, and Discriminant Analysis, was compared in classifying pork meat quality using hyperspectral data.Models were developed to sort meat into four quality classes (PFN, RFN, RSE, and PSE), into two classes (pale and red), and finally further into two classes (soft and exudative, and firm and non-exudative) within the pale and red meat samples.Overall, the Discriminant Analysis achieved the highest classification accuracy for sorting meat into four quality classes, its performance was followed by ANNs, k-NN and DTs.In order to explore the industrial applicability of the technique, hyperspectral observations were acquired at five different locations along the same meat samples.The data collected at each location was analyzed separately.Stepwise regression and
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".