Tech Briefs Magazine - December 2022 - 39

computing up to 100,000 times more efficient
than conventional computing.
The team will next teach the system using
real-world data, such as ECG signals,
and hopes to make it into a real computing
device. Eventually, magnetic systems could
be integrated into conventional computers
to improve their energy efficiency.
Their energy efficiency also means
they could feasibly be powered by renewable
energy and used to do " AI at
the edge " - processing the data where
it's being collected, rather than sending
it back to large data centers. Also,
they could be used on wearable devices
to process biometric data on the body
(e.g., predicting and regulating insulin
levels for diabetic people or detecting
abnormal heartbeats).
For more information, contact Hayley
Dunning at h.dunning@imperial.ac.uk;
44 (0)20 7594 2412.
Researchers have shown it is possible to perform artificial intelligence using tiny nanomagnets that
interact like neurons in the brain. (Image: imperial.ac.uk)
Meta Monitoring System
It helps to interpret deviation scores and determine whether anomalous behavior is transient
or systemic.
Ames Research Center, Moffett Field, CA
V
arious software approaches exist that
determine whether a given instrumented
system is experiencing anomalous
behavior. Many anomaly detection
systems simply generate some type of deviation
score, then rely on a subject matter
expert to evaluate the data and recommend
a course of action. These
evaluations are often nontrivial and can
lead to false alarms. NASA's Meta Monitoring
System (MMS) helps one to better
interpret such deviation scores and determine
whether detected anomalous
behavior is transient or systemic.
MMS was developed as an add-on to
NASA Ames-patented Inductive Monitoring
System (IMS), which estimates deviation
from normal system operations.
It has two phases: a model-building training
phase and a monitoring phase.
MMS not only uses deviation scores
from nominal data for training but can
also make limited use of results from
anomalous data. The invention builds
two models - one of nominal deviation
scores and another of anomalous deviation
scores - each consisting of a probability
distribution of deviation scores.
After the models are built, incoming
deviation scores from IMS (or a different
monitoring system that produces
Tech Briefs, December 2022
New data from sensors
Historical
Data
System
Monitor
System
Model
Historical
deviation from nominal
Deviation Scores
MMS
MMS
Model
High level architecture of NASA's Meta Monitoring System. (Image: NASA)
deviation scores) are passed to the
learned model, and probabilities of producing
the observed deviation scores
are calculated for both models. Users of
MMS can interpret deviation scores
from the monitoring system more effectively,
reducing false positives and negatives
in anomaly detection.
This software approach is applicable
where multivariate signals are being generated
within an operating system that
has regular behavior which can be modwww.techbriefs.com
eled,
and must be monitored (e.g., aircraft,
environmental control systems,
power generation facilities, automotive,
manufacturing, software systems etc.).
NASA is actively seeking licensees to
commercialize this technology. Please
contact NASA's Licensing Concierge at
Agency-Patent-Licensing@mail.nasa.gov
or call at 202-358-7432 to initiate licensing
discussions. For more information, visit
https://technology.nasa.gov/patent/
TOP2-306.
39
Nominal/
Off-nominal
determination

http://imperial.ac.uk https://technology.nasa.gov/patent/TOP2-306 http://www.techbriefs.com

Tech Briefs Magazine - December 2022

Table of Contents for the Digital Edition of Tech Briefs Magazine - December 2022