Defense Advanced Research Projects AgencyTagged Content List

Analytics for Data at Massive Scales

Extracting information from large data sets

Showing 63 results for Analytics RSS
Understanding the complex and increasingly data-intensive world around us relies on the construction of robust empirical models, i.e., representations of real, complex systems that enable decision makers to predict behaviors and answer “what-if” questions. Today, construction of complex empirical models is largely a manual process requiring a team of subject matter experts and data scientists.
Department of Defense (DoD) operators and analysts collect and process copious amounts of data from a wide range of sources to create and assess plans and execute missions. However, depending on context, much of the information that could support DoD missions may be implicit rather than explicitly expressed. Having the capability to automatically extract operationally relevant information that is only referenced indirectly would greatly assist analysts in efficiently processing data.
As a result of combat exposure, warfighters may return home from deployments with psychological health challenges and find it difficult to reconnect with family and society at large. According to the Department of Veteran Affairs’ National Center for PTSD, studies show that between 12 and 25 percent of military personnel who had returned from Afghanistan and Iraq as of 2008 may suffer from PTSD. (1) Despite best efforts to improve awareness and care, additional studies reveal that only a small fraction of warfighters seek help dealing with psychological health issues.
The United States military is heavily dependent on networked communication to fulfill its missions. The wide-area network (WAN) infrastructure that supports this communication is vulnerable to a wide range of failures and cyber attacks that can severely impair connectivity and mission effectiveness at critical junctures. Examples include inadvertent or malicious misconfiguration of network devices, hardware and software failures, extended delays in Internet Protocol (IP) route convergence, denial of service (DoS) flooding attacks, and a variety of control-plane and data-plane attacks resulting from malicious code embedded within network devices.
Training, which is conducted in classroom, field, and virtual settings, is a critical element of military readiness. Large-scale social networks, interactive content, and ubiquitous mobile access are emerging as driving technologies in education and training. At the same time, education analytics presents new opportunities for assessing the effectiveness of training strategies, understanding trends and effects in large volumes of education data, and relating these back to alternative modes of instruction.