Information Technology and Systems Center
University of Alabama in Huntsville
S339 Technology Hall,
Huntsville, AL 35899
Mining and Image Processing Toolkits
|The Algorithm Development
and Mining System (ADaM) developed by the Information
Technology and Systems Center at the University
of Alabama in Huntsville is used to apply data mining
technologies to remotely-sensed and other scientific data.
The mining and
image processing toolkits consist of interoperable components
that can be linked together in a variety of ways for application
to diverse problem domains. ADaM has over 100
components that can be configured to create customized
mining processes. Preprocessing and analysis utilities aid
applying data mining to their specific problems. New components
can easily be added to adapt the system to different science
The 4.0 release of ADaM is a significant architectural paradigm
shift from previous versions.
The latest version (4.0.2) (see
release note) provides
a solution that easily supports the integration of 3rd
party algorithms and the reuse of ADaM
components by other systems. ADaM 4.0.2 provides this
support through the use of autonomous components in a distributed
Each component is provided with a C, C++, or other application
programming interface (API), an executable in support of
scripting tools (e.g. Perl,
shell scripts) and eventually web service interfaces to support
web and grid
applications. ADaM 4.0.2 components are general
purpose mining and image processing modules that can be
easily reused for multiple solutions and disciplines. These
components are well positioned to address the needs for distributed
mining and image processing services in web and grid applications.
|ADaM's component architecture
is designed to take advantage of emerging computational environments
such as the Web and information Grids. Individual ADaM operations
can execute in a stand-alone fashion, facilitating their use
in distributed and parallel processing systems. The operations
- organized as toolkits - provide pattern recognition, image
processing, optimization, and association rule mining capabilities.
Components are packaged in several ways, including C/C++
libraries, executables, and Python modules. Multi-interface
component packaging facilitates rapid prototyping and efficient,
performance-critical data mining application development. This
approach also facilitates the use of ADaM components by and
with third-party analysis and visualization systems.
|ADaM components can
be accessed via multiple external interfaces. This flexibility
facilitates the implementation of data mining and image processing
components as Web and Grid services. Consistent and well documented
execution protocols support the incorporation of ADaM components
into applications that are developed using common network-enabled
scripting languages such as Perl and Python. The incorporation
of data interchange technologies such as the Earth
Science Markup Language (ESML) yields distributed interoperability
across heterogeneous scientific data sets.
can be generated from the toolkits of mining and image processing
components, perhaps combined with other specialized software
modules. One example is the use of ADaM to detect
tropical cyclones and estimate their maximum sustained winds.
This operational application uses a combination of general-purpose
image analysis modules plus special purpose modules developed
specifically for the problem. The near real-time storm information
can be viewed on the web at http://pm-esip.nsstc.nasa.gov/cyclone/.
and the National
Science Foundation are actively pursuing computational Grid
data mining technologies are currently in use in both areas.
ADaM is the first data mining application to execute on the
NASA Information Power Grid. The ADaM toolkits can be made available
as a set of Open Grid Services Architecture components that
easily translate to the Grid environment.