Identification and Classification of Multi‐Species Biofilms on Polymeric Surfaces Using Hyperspectral Imaging
Bibliographic record
Abstract
ABSTRACT Biofilm‐associated contamination poses significant challenges to the food industry, particularly in ensuring effective sanitization and reliable detection. This study explores the use of hyperspectral imaging (HSI) in the shortwave infrared (SWIR) range for non‐destructive detection and classification of biofilms on thermoplastic polyurethane (TPU) surfaces. Multi‐species biofilms composed of Comamonas sp., Raoultella sp., and Escherichia coli were formed at 10°C and 25°C and biofilm protein and polysaccharide contents were determined. Principal Component Analysis (PCA) and Partial Least Squares Discriminant Analysis (PLS‐DA) were used to differentiate among four classes of TPU coupons, including blank (BLANK), control (CTRL), intermediate‐strength biofilms formed at 10°C (S10), and strong biofilms formed at 25°C (S25). PCA successfully clustered samples based on spectral profiles of the classes, identifying significant wavelength regions at 1451 and 1926 nm, which correlated with the water, protein, and polysaccharide content of multi‐species biofilms. PLS‐DA provided a classification accuracy ranging from 68% to 100%, with the highest classification accuracy (100%) observed for BLANK and biofilm‐contaminated (S25) TPU coupons and the lowest accuracy (68%) for CTR. Additionally, Partial Least Squares Regression (PLSR) was employed to predict the protein content of biofilms, achieving reliable predictions both in calibration ( of 0.81) and external validation ( of 0.72). These findings demonstrate the potential of HSI to detect and classify biofilm‐infected TPU coupons utilizing wavebands associated with proteins, polysaccharides and water. Hence, HSI can be used as a rapid and non‐destructive alternative to traditional methods for biofilm detection, including chemical‐based methods such as BioDetect (SANI MARC) and fluorescence‐based imaging methods like BACTISCAN.
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) | 0.000 | 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".