support vector machines, k-nearest
neighbors, and a variety of decision
trees, including boosted trees
and bagged decision trees. They
ultimately found that boosted trees
worked best, with a prediction
accuracy of almost 95%.
I2C2 researchers are currently
integrating automated image
processing into their analysis
workflow. Using Image Processing
Toolbox, the team has analysed
thousands of photos of milk
powder particles, calculating
particle size, convexity, circularity,
and other shape factors and
correlating these metrics with
functional properties of the powder.
Results
1/ Key process flaws identified and
corrected. “At one of our partner’s
plants, a process designed to add
a key ingredient to milk powder was
failing from time to time, and plant
managers were unable to determine
the cause of this failure,” says Nick
‘Variable Importance’ to a PLS prediction of powder
functional property, showing one particular temperature to
have a very strong effect.
PCA analysis, coloured by powder bulk density, showing
almost all powders with very high density to be clustered in
a region with scores below -2 (1st PC) and above -2 (2nd PC).
Variable Importance’ to a PLS prediction of powder
functional property, showing one particular temperature to
have a very strong effect.
PCA analysis, coloured by powder bulk density, showing
almost all powders with very high density to be clustered in
a region with scores below -2 (1st PC) and above -2 (2nd PC).
‘Variable Importance’ to a PLS prediction of
powder functional property, showing one particular
temperature to have a very strong effect.
PCA analysis, coloured by powder bulk density, showing
almost all powders with very high density to be clustered in a
region with scores below -2 (1st PC) and above -2 (2nd PC).
Depree, project manager at I2C2
and postdoctoral researcher at the
University of Auckland. “The stepby
step analysis we conducted in
MATLAB enabled us to identify the
cause of the problem, and it has
now been resolved.”
2/ Multiple machine learning
classifiers evaluated in hours. “With
the Classification Learner app, in
a single afternoon we were able to
try support vector machines and
several other classifier types to see
which worked best with our data,”
David says. “Because we had little
prior experience with machine
learning, it could have taken us
months otherwise.”
3/ Large datasets easily handled;
manual processes automated.
“The tools we used for multivariate
analysis in the past failed to handle
our larger datasets, but MatLab
had no problems with them,” says
Depree. “Similarly, it would have
been impossible to create the
reports we share with Fonterra
manually in Microsoft Excel. With
MatLab, we automated this process
and generated hundreds of charts
from data spanning multiple plants
and years.”
A 3D plot of PCA analysis of plant process variables across three powder processing plants and six years of data. The analysis
shows that each plant exists in a completely separate operating space, despite producing the products with the same
specifications.
www.foodtechnology.co.nz 37
/www.foodtechnology.co.nz
