Rapid and non-destructive assessment of polyunsaturated fatty acids contents in Salmon using near-infrared hyperspectral imaging
Bibliographic record
Abstract
Polyunsaturated fatty acids (PUFAs) are important nutrients present in Salmon. However, current methods for quantifying the fatty acids (FAs) contents in foods are generally based on gas chromatography (GC) technique, which is time-consuming, laborious and destructive to the tested samples. Therefore, the capability of near-infrared (NIR) hyperspectral imaging to predict the PUFAs contents of C20:2 n-6, C20:3 n-6, C20:5 n-3, C22:5 n-3 and C22:6 n-3 in Salmon fillets in a rapid and non-destructive way was investigated in this work. Mean reflectance spectra were first extracted from the region of interests (ROIs), and then the spectral pre-processing methods of 2nd derivative and Savitzky-Golay (SG) smoothing were performed on the original spectra. Based on the original and the pre-processed spectra, PLSR technique was employed to develop the quantitative models for predicting each PUFA content in Salmon fillets. The results showed that for all the studied PUFAs, the quantitative models developed using the pre-processed reflectance spectra by “2nd derivative + SG smoothing” could improve their modeling results. Good prediction results were achieved with RP and RMSEP of 0.91 and 0.75 mg/g dry weight, 0.86 and 1.44 mg/g dry weight, 0.82 and 3.01 mg/g dry weight for C20:3 n-6, C22:5 n-3 and C20:5 n-3, respectively after pre-processing by “2nd derivative + SG smoothing”. The work demonstrated that NIR hyperspectral imaging could be a useful tool for rapid and non-destructive determination of the PUFA contents in fish fillets.
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 | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 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".