NASA SBIR 2007 Solicitation

FORM B - PROPOSAL SUMMARY


PROPOSAL NUMBER: 07-1 A1.05-9348
SUBTOPIC TITLE: Data Mining for Integrated Vehicle Health Management
PROPOSAL TITLE: DATA MINING FOR IVHM USING SPARSE BINARY ENSEMBLES

SMALL BUSINESS CONCERN (Firm Name, Mail Address, City/State/Zip, Phone)
MICHIGAN AEROSPACE CORPORATION
1777 Highland Dr., Suite B
Ann Arbor, MI 48108 - 2285
(734) 975-8777

PRINCIPAL INVESTIGATOR/PROJECT MANAGER (Name, E-mail, Mail Address, City/State/Zip, Phone)
John M. Trenkle
jtrenkle@michiganaerospace.com
1777 Highland Dr., Suite B
Ann Arbor , MI 48108 - 2285
(734) 975-8777

Expected Technology Readiness Level (TRL) upon completion of contract: 3 to 4

TECHNICAL ABSTRACT (Limit 2000 characters, approximately 200 words)
In response to NASA SBIR topic A1.05, "Data Mining for Integrated Vehicle Health Management", Michigan Aerospace Corporation (MAC) asserts that our unique SPADE (Sparse Processing Applied to Data Exploitation) technology meets a significant fraction of the stated criteria and has functionality that enables it to handle many applications within the aircraft lifecycle. SPADE distills input data into highly quantized features and uses MAC's novel techniques for constructing Ensembles of Decision Trees to develop extremely accurate diagnostic/prognostic models for classification, regression, clustering, anomaly detection and semi-supervised learning tasks. These techniques are currently being employed to do Threat Assessment for satellites in conjunction with researchers at the Air Force Research Lab. Significant advantages to this approach include: 1) completely data driven; 2) training and evaluation are faster than conventional methods; 3) operates effectively on huge datasets (> billion samples X > million features), 4) proven to be as accurate as state-of-the-art techniques in many significant real-world applications. The specific goals for Phase 1 will be to work with domain experts at NASA and with our partners Boeing, SpaceX and GMV Space Systems to delineate a subset of problems that are particularly well-suited to this approach and to determine requirements for deploying algorithms on platforms of opportunity.

POTENTIAL NASA COMMERCIAL APPLICATIONS (Limit 1500 characters, approximately 150 words)
MAC's SPADE data mining system has a large potential market in both government and civil aviation as well as for other arenas with costly and complex vehicles such as marine craft. The need for next-generation data mining tools for aid in lifecycle issues for aircraft/spacecraft/satellites/ships is now widely recognized by both the private and public sectors, as exemplified by the scope of the solicitation for this program. The techniques used by MAC are amenable to deployment on any platform of opportunity including Clusters, airborne platforms, Laptops, FPGAs, Graphical Processing Units (GPUs), and others depending on the needs of the application.

POTENTIAL NON-NASA COMMERCIAL APPLICATIONS (Limit 1500 characters, approximately 150 words)
The data mining techniques embodied in MAC's SPADE system have a broad commercial market. Potential arenas include: data fusion approaches to computer network security, intelligence, and public health monitoring; real-time quality control and damage detection for continuous physical processes (chemical & pharmaceutical plants, manufacturing facilities); text stream monitoring for news, email, IMs; financial event detection – monitor accounting or investment portfolio management systems to detect unexpected classes of price or cost changes which may signify problems; sales opportunity/threat identification – detect inter-product sales relationships, fad identification, competitor's pricing changes, seasonal and geographic changes; insurance claim monitoring for fraud; micro-climate change monitoring using digital imagery; gene expression profiling for medical diagnosis and understanding of diseases; proteomic data analysis and pattern recognition for medical diagnosis and biomarker discovery, and numerous other high-profile segments in which this system could be invaluable.

NASA's technology taxonomy has been developed by the SBIR-STTR program to disseminate awareness of proposed and awarded R/R&D in the agency. It is a listing of over 100 technologies, sorted into broad categories, of interest to NASA.

TECHNOLOGY TAXONOMY MAPPING
Autonomous Reasoning/Artificial Intelligence
On-Board Computing and Data Management


Form Generated on 09-18-07 17:50