team photo
no video icon

This video contains proprietary information and cannot be shared publicly at this time.

Figure 1
project photo

Computer Science and Engineering
Team 11

Team Members

Faculty Advisor

Leonard Adams III
Travis Bugbee
Klauss Preising
Joseph Warmus
Daniel Zhang

Steven Demurjian


Lockheed Martin

sponsored by
sponsor logo

Lockheed Martin Rotary and Mission Systems (RMS) labs are moving from traditional on-premise servers located in computer rooms across the infrastructure to Amazon Web Services (AWS). The goal is to reduce costs while also creating new data management, access and sharing capability across the RMS portfolio. Data that resides in the labs is stored in a variety of application formats. Moving the data to AWS requires that the data type is properly identified prior to transfer. Data stored within the lab environments can be categorized as export control, third party proprietary, Lockheed Martin Proprietary, or Covered Defense Information (DFARS 254.204-7012). Prior to moving the data to AWS, the current procedure is to manually review the information to ensure that it is labeled or tagged with the correct data category. The process of manually opening every file and applying a label or meta tag is extremely time consuming and inefficient. We here at Lockheed Martin RMS would like the UConn Senior Design Team to create a machine learning solution that can analyze and categorize the data. The solution should allow the data owner the ability to provide input into the recommended categorization and key terms for their program prior to moving the data into AWS.