Classification of opacity for polymer nanocomposite films via deep neural network (DNN) classifiers

Keyphrases

• Opacity 100%
• Polymer Nanocomposite Film 100%
• Deep Neural Network Classifier 100%
• Multi-walled Carbon Nanotubes (MWCNTs) 50%
• Precision-recall 50%
• F1 Score 50%
• Recall Score 50%
• Polystyrene Latex Particles 50%
• Hidden Layer Size 50%
• Precision Score 50%
• Spectroscopic Data 25%
• Training Data 25%
• Classification Accuracy 25%
• Particle Size 25%
• Nanomaterials 25%
• Deep Learning Methods 25%
• Activation Function 25%
• Sigmoid Function 25%
• Nanotechnology 25%
• Computational Results 25%
• Annealing Temperature 25%
• Receiver Operating Characteristic Curve 25%
• Testing Data 25%
• Mass Fraction 25%
• Light Intensity 25%
• Area under the Curve 25%
• Nanofillers 25%
• Hidden Layer 25%
• Trial-and-error Method 25%
• Optical Transparency 25%
• Transmitted Light 25%
• Light Transmission 25%
• Three-class 25%
• Confusion Matrix 25%
• Accuracy Score 25%
• Two-hidden-layer 25%
• Class-based 25%
• Bayesian Optimization 25%
• Function Layer 25%
• Optimal Hyperparameters 25%
• Cross-entropy Loss 25%
• Fully Connected Deep Neural Network 25%
• Loss Score 25%
• Multi-characteristics 25%

Engineering

• Nanocomposite 100%
• Deep Neural Network 100%
• Hidden Layer 60%
• Metrics 40%
• Multi-Walled Carbon Nanotube 40%
• Classification Accuracy 20%
• Nanomaterial 20%
• Sigmoid Function 20%
• Activation Function 20%
• Receiver Operating Characteristic 20%
• Annealing Temperature 20%
• Optimal Design 20%
• Operating-Characteristic Curve 20%
• Mass Fraction 20%
• Particle Diameter 20%
• Limited Amount 20%
• Nanofiller 20%
• Optical Transparency 20%
• Testing Dataset 20%
• Confusion Matrix 20%
• Computed Curve 20%
• Deep Learning Method 20%
• Luminous Intensity 20%

Material Science

• Carbon Nanotube 100%
• Polystyrene 100%
• Nanocomposite Film 100%
• Polymer Nanocomposites 100%
• Film 50%
• Nanostructured Material 50%