Page 36 - FCW, November, December 2018

Public Sector Innovations
are using it for hydroelectric dams, military aircraft and ships. Data flows from networks into RockNSM for scanning without decreasing network usability, stability or reliability.
By taking the project open source, MOCYBER created a cybersecurity community that spans the National Guard, industry, and domestic and foreign government agencies. The result is a constantly evolving capability that allows the military to respond more quickly and effectively to cyber adversaries.
PROJECT: OC Ballot Express Orange County, Calif., Registrar of Voters
Making voting by mail more
accountable
In Orange County, Calif., 55 percent of the votes cast in each election come via vote- by-mail ballots. To make the process more efficient and increase public confidence, the county’s Registrar of Voters pilot-tested an ambitious effort to enable voters to track their ballots during the primary election in June.
The agency added bar codes to the ballots mailed to voters and created an online dashboard where voters can track their ballots through every stage of the process and find out if there is an issue with their acceptance.
The Registrar of Voters collaborated with the U.S. Postal Service to develop the bar codes. “We’ve been working with the Postal Service for years because we are a large mailer in Orange County,” Registrar of Voters Neal Kelley said. “When we
were expanding our mailing system, we worked closely with their data folks to start integrating the data that we needed on our end.”
Kelley said the majority of voters were satisfied with the pilot process but noted that his office needs to do a better job of notifying the voters who submit vote-by-mail ballots in person at their polling places on Election Day.
“Since those ballots are not going through
BEST IN CLASS - DEFENSE
36 November/December 2018 FCW.COM
PROJECT: Unstructured Data on Machinery Repair for Navy Ships
Military Sealift Command, U.S. Navy
Preventive maintenance through predictive analytics
When the Navy’s Military Sealift Command realized that its decades-long horde of unstructured maintenance data was hampering strategic decision- making, officials turned to machine learning for help.
The command teamed up with Abeyon, a firm that specializes in artificial intelligence solutions, to create the data analysis tool Clarifi — a preventive capability that monitors the condition and reliability of all 100 of the command’s ships.
Using sample documents representing the larger unstructured dataset, the team built a machine learning-based text analysis model to explore and identify relationships among the equipment data and entities.
The tool’s pilot version turned nearly 30 years’ worth of data locked in Word documents into educated decisions regarding ships and their maintenance. Overall, the tool has increased operational efficiency and helped lower costs by millions of dollars.
As the technology matures, Clarifi could offer recommendations on equipment health, condition and potential for failure. Instead of guessing whether a machine has reached its end, the command can now look to the past to predict problems and preempt them.