The November-December 2014 edition of the National Fire Protection Association’s NFPA Journal features an article describing the New York City Fire Department’s (FDNY) success in harnessing big data to enhance fire prevention throughout the city. Big data can be defined as data sets too large and complex to analyze using traditional data processing applications. Using a computerized risk-based inspection system (RBIS), FDNY can sift through years of data about individual buildings from multiple city agencies, score each building’s fire risk and generate prioritized lists of buildings most in need of fire inspection. According to the article, “Fire Department officials credit the technology for easing workloads, simplifying an incredibly complex task and, most importantly, getting New York firefighters into some of the city’s most fire-prone buildings, some of which haven’t been inspected in years.”
FDNY’s use of a RBIS is a prime example of “smart firefighting,” a concept in which the fire service utilizes ever more sophisticated sensors and analytical tools not only to fight fires more effectively and safely, but also to prevent them from happening at all. It is a concept drawing serious attention from many in the fire service, industry and academia, and forging working partnerships between organizations as prominent as the National Fire Protection Association’s Fire Protection Research Foundation and the Fire Fighting Technology Group of the National Institute of Standards and Technology’s Fire Research Division.
Firefighters are not the only responders looking for an advantage in big data. Law enforcement also is putting advanced analytics to work. In 2009, the Department of Justice Bureau of Justice Assistance (BJA) launched its Smart Policing Initiative (SPI) to identify tactics and strategies that police departments can use to effectively reduce crime in an environment of tight budgets and limited staffing.
A collaboration among BJA, CNA Corporation and more than 30 law enforcement agencies across the country, SPI builds on the concepts of offender-based and place-based (“hotspot”) policing and encourages exploration of new solutions to public safety problems. Research shows that a small number of offenders commit a disproportionate amount of crime and that crime reports and calls for service often cluster at specific locations or in easily defined areas. In addition, while random patrols and rapid response do not measurably reduce crime, place-based policing can reduce violent crime and neighborhood disorder. Los Angeles, Philadelphia and Detroit are three of the cities where data analysis has paid off.
To identify places where the potential for crime is high, law enforcement might rely on data as varied as zoning applications to sell alcohol (bars and liquor and convenience stores are frequent targets of crime), building and renovation permits (signaling a potential for theft of construction materials or equipment), foreclosure notices, and emergency medical calls that involve violence or drug overdoses. Also important are census and demographic data. Accurately analyzing information from so many sources is a big data challenge.
To meet the challenge, SPI offers grants to local agencies in support of programs that leverage data in law enforcement. Since 2009, the SPI has funded 35 projects.
Analyzing big data is only half the challenge. The other half is generating results that are usable. In many cases, this means converting analysis results into visual formats that are easy to comprehend. Developing those visual tools is the mission of the Visual Analytics for Command, Control, and Interoperability Environments Center (VACCINE), a U.S. Department of Homeland Security Center of Excellence. Co-led by Purdue University and Rutgers University, VACCINE develops methods and tools to analyze and display vast amounts of information for all mission areas of homeland security.
Among the big data tools VACCINE has developed is Visual Analytics Law Enforcement Technology (VALET). VALET provides analytical tools coupled with an interactive visual interface that allows law enforcement officials, crime analysts and patrol officers observe patterns in criminal, traffic and civil incidents, and quickly identify areas with higher probabilities of activity.
Initiatives such as FDNY’s and BJA’s are multiplying among public safety agencies nationwide. Combined with the growing number of available big data tools and technologies, these efforts are shaping dramatic new approaches to public safety.