A deep neural network classifies six types of microplastic and natural fibers using 72-dimensional polarization feature vectors from holographic microscopy at 96.7% accuracy, with SHAP analysis showing eigenvalue ratios as the dominant predictors.
Intelligent polarization-sensitive holographic flow-cytometer: Towards specificity in classifying natural and microplastic fibers,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
physics.optics 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Explainable deep-learning detection of microplastic fibers via polarization-resolved holographic microscopy
A deep neural network classifies six types of microplastic and natural fibers using 72-dimensional polarization feature vectors from holographic microscopy at 96.7% accuracy, with SHAP analysis showing eigenvalue ratios as the dominant predictors.