A Data-Driven Approach to In-Transit Visibility Navy SBIR FY2015.2 Sol No.: Navy SBIR FY2015.2 Topic No.: N152-122 Topic Title: A Data-Driven Approach to In-Transit Visibility Proposal No.: N152-122-0756 Firm: Optimal Synthesis Inc. 95 First Street Suite 240 Los Altos, California 94022-2777 Contact: Bong-Jun Yang Phone: (650) 559-8585 Abstract: Military operations and logistics are inextricably linked. The importance of In-Transit Visibility (ITV) capability for reliable tracking and delivery of logistical items has well been recognized across Department of Defense (DoD) logistics programs. The current state-of-the-art solution to ITV employs a Radio-Frequency Identification (RFID) network, which comprises a large number of read-and-write stations and hence requires high cost and intensive manpower. Motivated by past experiences on air traffic management and machine learning, Optimal Synthesis Inc. (OSI) proposes an alternative approach that exploits existing variety of data sources, a good example of which is the IDE/GTN Convergence (IGC) that is a unified data service across DoD cargo movement and tracking. The approach combines machine learning techniques with the estimation and prediction methodologies for tracking the cargo movement and predicting the time-of-arrival in each mission leg. By performing on-line risk monitoring, a decision support tool that generates automated alerts for human intervention is also developed using a stochastic decision framework. The proof-of-concept demonstration is planned in Phase I, and the software prototype is planned to be developed in Phase II for functional demonstration. Benefits: In-Transit Visibility (ITV) is the ability to track the status and location of logistical items from origin to destination and has been recognized as a critical element in reliable logistics operations. As demonstrated by the Army�s Radio-Frequency Identification (RFID) networks, the ITV capability generally tends to require a large number of hardware and manpower. The ITV tool proposed in this research relies on recently advanced technologies on machine learning and big-data analytics and provides a very cost-effective solution to ITV. Therefore, once developed, the tool will directly benefit the Navy, Marine Corps, and Coast Guard Logistics Programs that have adopted the Transportation Exploitation Tool as the Naval Logistics Initiative. Besides, the idea behind the ITV functional well prevails to any logistics domain in which a large data set is available for extracting actionable knowledge. Therefore, the tool will benefit all the logistics services and programs across DoD and commercial sectors. Return