|
sensorMiner was developed
by Interface & Control Systems, in collaboration with NASA and
Florida Tech, to address the need for a sophisticated data mining
toolset that uses past performance data to build a human-readable
model to ultimately provide real-time fault detection capability.
The sensorMiner toolset is a unique
approach using a
combination of time warp, cluster, RIPPER (rule induction), Euclidean
error, and state machine technologies. The result is a sophisticated
temporal machine learner for real-time anomaly detection.
SensorMiner learns
from past performance data and automatically generates a monitoring system.
Conventional technology has made this process both a labor-intensive and
error-prone task often misunderstood, even by experts. SensorMiner will
correlate seemingly unrelated data automatically and provide rich graphical
feedback to the user.
The
ability to automatically make predictions or help people make
decisions faster and more accurately - in real-time - has
far-reaching implications that spread across industry boundaries. Any
system that can be modeled and must be monitored for
abnormalities is a candidate.
Typical
applications would include:
-
Satellite Control Centers
-
Test Sets and Post-Test Analysis
-
Industrial Control and
Monitoring
-
Medical/Biological
Monitoring
·
SensorMiner is built upon our portable, embeddable SCL
architecture which has been proven in control
centers for DoD and NASA. The SCL architecture provides a clear
separation of decision-making logic from procedural logic. Intelligent, real-time alerts can be generated based on any
event whether directly received from sensor data
or derived from algorithms. With 24/7 reliability,
full scalability, and plug-in capabilities for new, extended, or
legacy technologies.
The links below provide a
quick overview of sensorMiner features:
|