Tech Briefs Magazine - June 2021 - 53

data into a format ready for the SVM algorithm.
The SVM is then trained against
the training data set in accordance with a
hand-tuned set of parameters.
In the runtime operating mode, data is
collected much like in the training mode
but serially. This data is run through the
same preprocessor as the training data, so
that both training and runtime data are
scaled to the same mean and variance.
The SVM then takes this preprocessed
data and makes a best guess based on
its tuned parameters as to which module/location
the sample was collected in.
By using a moving window average over
five to ten samples, upwards of 95% tracking
accuracy can be achieved.
None of the individual aspects of the
algorithm are known to be fully novel,
although the specific pipeline of subroutines
may be. Other similar commercial
projects exist but none that clearly provide
the flexibility to work without GPS
information.
AI System Discovers New Material
The algorithm identified a new compound potentially useful for photonic devices and
biologically inspired computers.
National Institute of Standards and Technology, Gaithersburg, Maryland
esearchers have developed an artificial
in telligence (AI) algorithm called
Closed-Loop Autonomous System for
Materials Exploration and Optimization
(CAMEO) that discovered a potentially
useful new material without requiring
additional training from scientists. The
AI system could help reduce the amount
of trial-and-error time scientists spend in
the lab, while maximizing productivity
and efficiency in their research.
In the field of materials science, scientists
seek to discover new materials that
can be used in specific applications such
as metals that are light but also strong or
one that can withstand high stresses and
temperatures for a jet engine. Finding
such new materials usually takes a large
number of coordinated experiments and
time-consuming theoretical searches. If a
researcher is interested in how a material's
properties vary with different temperatures,
then the re search er may need to run
10 experiments at 10 different temperatures.
But temperature is just one parameter.
If there are five parameters, each with
10 values, then that researcher must run
the experiment 10 × 10 × 10 × 10 × 10
times - a total of 100,000 experiments.
CAMEO can ensure that each experiment
maximizes the scientist's knowledge and
understanding, skipping over experiments
that would give redundant information.
Machine learning is a process in which
computer programs can access data and
process it themselves, automatically im -
proving on their own instead of relying
on repeated training. This is the basis for
CAMEO, a self-learning AI that uses prediction
and uncertainty to determine
which experiment to try next.
R
DECIDE
EXECUTE
ANALYZE
Make
Active learning with physics
to choose next experiment
Measure
Database
Tech Briefs, June 2021
Cov
The developers are looking to test the
system with training data collected on
the ISS, allowing them to tune the system
parameters and ascertain the value
of SVM WiFi tracking in a truly highreflection
environment.
NASA seeks to freely license this software
and make it available for general use for
open source projects. Please contact NASA's
Licensing Concierge at Agency-PatentLicensing@mail.nasa.gov
or call us at 202358-7432
to initiate licensing discussions.
Ask an expert
Simulate & download
Bayesian statistical analysis with
physics-informed machine learning
CAMEO is capable of searching for new materials by operating in a closed loop. The AI determines
which experiment to run on a material, does the experiment, and collects the data. One cycle
through the experiment can take from seconds to tens of minutes. (Credit: N. Hanacek/NIST)
CAMEO looks for a useful new material
by operating in a closed loop: It determines
which experiment to run on a
material, does the experiment, and collects
the data. It can also ask for more
information, such as the crystal structure
of the desired material, from the scientist
before running the next experiment,
which is informed by all past experiments
performed in the loop.
The AI is also designed to contain
knowledge of key principles including
knowledge of past simulations and lab
experiments, how the equipment works,
and physical concepts. CAMEO is armed
with the knowledge of phase mapping,
which describes how the arrangement of
atoms in a material changes with chemiwww.techbriefs.com
ToC
cal
composition and temperature. Un -
der standing how atoms are arranged in a
material is important in determining its
properties such as how hard or how electrically
insulating it is and how well it is
suited for a specific application.
CAMEO discovered the material
Ge4Sb6Te7, which the group shortened to
GST467. CAMEO was given 177 po tential
materials to investigate, covering a large
range of compositional recipes. To arrive
at this material, CAMEO performed 19
different experimental cycles, which took
10 hours, compared with the estimated
90 hours it would have taken a scientist
with the full set of 177 materials.
The material is composed of three different
elements (germanium, antimony
53

http://www.techbriefs.com http://www.abpi.net/ntbpdfclicks/l.php?202106TBNAV

Tech Briefs Magazine - June 2021

Table of Contents for the Digital Edition of Tech Briefs Magazine - June 2021