INIS
prediction
100%
populations
100%
data
100%
precipitation
100%
balances
100%
recovery
100%
asphaltenes
100%
modeling
80%
machine learning
60%
injection
60%
randomness
40%
solvents
40%
experimental data
20%
accuracy
20%
testing
20%
processing
20%
density
20%
layers
20%
vectors
20%
boundary conditions
20%
datasets
20%
pipelines
20%
reliability
20%
decision tree analysis
20%
viscosity
20%
scaling
20%
annealing
20%
molecular weight
20%
forests
20%
api gravity
20%
deasphalting
20%
Keyphrases
Asphaltene Precipitation
100%
Connectionist Models
100%
Population Balance Model
100%
Bitumen Recovery
100%
Precipitation Prediction
100%
Modeling Approach
50%
Solvent Injection
50%
Committee Machine Intelligent System
50%
Paraffinic Solvent
50%
Machine Learning
25%
Viscosity
25%
Model-driven Development
25%
Machine Learning Approach
25%
Annealing
25%
Machine Learning Models
25%
Relative Accuracy
25%
Support Vector Machine
25%
Mathematical Relationship
25%
Random Search Algorithm
25%
Bitumen
25%
Smart Model
25%
Injection Rate
25%
Multilayer Perceptron
25%
Data Preprocessing
25%
Data Scaling
25%
Data Splitting
25%
Boxplot
25%
API Gravity
25%
Tree Support
25%
Preferred Models
25%
DATAPLOT
25%
Asphaltene Content
25%
Deasphalting
25%
Gravity Pressure
25%
Random Tree
25%
Engineering
Asphaltenes
100%
Connectionist Model
100%
Precipitation of Asphaltenes
100%
Bitumen Recovery
100%
Research Work
50%
Fluid Viscosity
50%
Artificial Intelligence
50%
Support Vector Machine
50%
Learning Approach
50%
Molecular Weight
50%
Data Point
50%
Injection Rate
50%
Testing Dataset
50%
Perceptron
50%
Initial and Boundary Condition
50%
Random Forest
50%
Data Preprocessing
50%
Asphaltene Content
50%
Chemical Engineering
Learning System
100%
Artificial Intelligence
33%
Support Vector Machine
33%
Multilayer Neural Networks
33%
Material Science
Asphaltenes
100%
Density
20%
Annealing
20%