You are here

Contextual Sociocultural Reasoning in Weak Signal Environments


TECHNOLOGY AREAS: Information Systems, Human Systems

OBJECTIVE: Develop a method and implement a technique to correlate a variety of sociocultural, environmental, and geospatial data gathered from a region of interest to perform correlations and forecast likely future impacts of observations.

DESCRIPTION:  Irregular warfare, non-state terrorism movements, and uncertain environmental patterns that trigger major weather disasters are producing a reality for military and government leaders where traditional physics-based sensors alone are insufficient to plan current and future actions in a region on interest or need.  Context awareness is a critical requirement for decision makers because it provides important information about situations and dynamics relevant to goals, functions, and data needs [1].  Strategies for achieving contextual understanding can include observational data, a priori knowledge models, and inductive knowledge [2].  Contextual understanding is generally achieved through a combination of human and computer processing techniques that take advantage of a person’s cognitive ability to fuse and assimilate multiple sources and types of information for new insights [3].  In the domains identified earlier in this topic, it is critical to incorporate both hard and soft data to gain an understanding of the delicate balance between individuals and groups in society and the environments (geopolitical, social, agricultural, etc.) upon which they depend.  Test and evaluation of methods that fuse hard and soft data are challenging due to the nature of the data, the test environment, and the metrics for determining outcomes [4].  Unlike traditional military test and evaluation, however, data sources for this new type of problem are not classified or difficult to obtain; open source data is available and plentiful but it is collected by a diverse group of researchers.  The challenge becomes correlating data of many different types that represent various aspects of a region of interest.  This approach is similar to the signal processing approach of weak signal detection, that is used to extract received signals [5], identify images in noisy backgrounds [6], and conduct remote sensing of land and water resources for sustainable development of natural resources [7].  A novel approach to correlating a variety of data sources to understand problems in an area and forecast conflict is described by [8].  In this example, the potential conflict is the weak signal that is detected through the correlation of diverse datasets describing many features of the region, to include demographic, political, social, economic, educational, agricultural, weather, etc.  A key challenge in integrating these disparate data is the semantic meaning implicit in the components of the overall structure of the region.

The challenges with this approach include the following.  First, a method for collecting various datasets for a region of interest and correlating these for overall understanding and meaning is a nontrivial task.  Many of the datasets are based on different scales and involve different referents to the population or the environment.  Second, a weighting scale must be developed sufficient to provide representational meaning and inferential capabilities to the reasoning tool.  Third, a visual representation must be developed sufficient for a human to reason about the correlations; a display that provides all of the facts but does not suggest inferences is insufficient and meaningless.  Finally, a performance measurement capability is needed to compare the reasoning analytics to reasonable expectations for use of such a tool.  Quantitative and qualitative metrics will be needed for such an application.

This topic seeks to address these challenges by developing and implementing a technique for correlating multiple datasets for a region of interest, weighting significant factors, and producing a set of forecasting alerts for a human user sufficient to trigger planning and course of action considerations. 

PHASE I:  Define requirements for developing and implementing a technique for building a technique that can be used to detect a ‘weak signal’ or troublesome behavior in a population or region of interest.  Requirements definition must include: a description of the model components and the supporting relationships, the computational processing technique that will be used and a description of the integration mechanisms, a determination of the types and characteristics of the metrics that will be captured and used, a detailed discussion of the specific domain to be represented, and a discussion of analysis and assessment techniques to be used.  Phase II plans should also be provided, to include key component technological milestones and plans for testing and validation of the proposed system and its components.  

PHASE II: Produce a prototype system based on the preliminary design from Phase I.  All appropriate engineering testing will be performed, and a critical design review will be performed to finalize the design.  Phase II deliverables will include a working prototype of the system, specification for its development, and a demonstration and validation of the ability to both accurately represent the model of the soft information fusion and the collaborative visual analytics representation of the data.

PHASE III: This technology will have broad application in military, government, and commercial settings.  Within the military and government, there is an increasing emphasis on understanding and forecasting group behaviors or regions that are prone to conflict or environmental degredation.  Currently, fusing information from these multiple and divergent sources is extremely labor intensive and costly in terms of labor and time.  Developing models that can forecast likely disruptions to fragile populations or environments will be a powerful addition to strategic, operational, and tactical decision making.  The proposed effort will enable the delivery of more informed courses of action supported by tractable information sources in a display environment that provides multiple views into the problem space.  Commercially, the advanced sensor technologies have produced unprecedented amount of digital information and applications by which to sort, collect, and share data.  This sector has also witnessed a surge in analytic processing, dissemination, and display capabilities.  Harnessing these for multiple uses will reduce the cost of integrating these techniques and improve the human decision making process.

US Flag An Official Website of the United States Government