You are here

Collaborative Visual Analytics Approach for Reasoning in Soft Information Fusion Domains


TECHNOLOGY AREAS: Information Systems

OBJECTIVE: Develop a method and implement a technique for using a collaborative visual analytics approach to the soft information fusion domain to enable humans to reason more efficiently in this complex information space.

DESCRIPTION:  Increasingly, information fusion for strategic and tactical military decisions is driven less by the traditional physical domain and more by human or ‘soft’ sensor collectors and data products [1].  Recent trends in social networking and advanced computing have contributed to a significant change in the ways in which humans are represented in the information fusion domain; as targets and as sources of information [2].  As targets of the fusion system, individuals and groups, operating as open or hidden networks, are less tractable by physical sensors and the resulting behavior is difficult to infer and understand in advance of trigger events [3].  As information sources, human reports are subject to reporting bias, uncertainty, incompleteness, ambiguity, corruption, and perceptual/social bias [2, 6].  Finally, as decision makers, humans are distributed in time and space and require access to collaborative technologies to synchronize data, share information, and visualize potential courses of action [4].  In this extremely complicated space, understanding the data and manipulating the reasoning and display technologies through a user interface are basic starting points for more advanced capabilities [5].  The field of visual analytics has contributed tools to allow humans to solve analytical problems similar to those described above, albeit in a single user environment [7] or in a co-located team [8].  Collaborative Visual Analytics (CVA) is explored by [9], who describe an environment to allow remote-collaborative information exploration and task sharing with linked graphical interfaces.   CVA has been used by an interdisciplinary team to predict the impact of global climate change on US power grids [10] and emergency response management [12].  The power of CVA for decision making in the soft information fusion domain stems from the inclusion of the social process of effort sharing, discussion, and consensus building [11] as well as the technical ability for team members to share representations, translate differing perspectives, articulate arguments, update conclusions, and justify actions [13]. 

The challenges with this topic are twofold.  First, the soft information fusion domain is often described as ‘data rich and model poor’, which leads to the underlying need for a model that is flexible enough to incorporate disparate data and structured enough to support a decision maker’s need to reason about the data.  Second, collaborative visual analytics that can display information relationships and a team of users’ individual reasoning requirements over those data artifacts is a complicated proposition and demands careful study and technical design. 

The current topic seeks to address those challenges by developing and implementing a technique for building a collaborative visual analytics application for reasoning in a soft information fusion domain.  The desired approach includes three elements.  The first element includes developing a semantic model that can incorporate and parse elements of data into meaningful representations that are amenable to visual representation and manipulation.  The second element is a performance evaluation and scoring mechanism by which a user community can be rated on ability to extract meaningful representations from the data.  The last element requires demonstrating the effectiveness of this capability to model adaptations based on information inputs and also to assess user decision making as a function of the collaborative visual applications in a small team.

PHASE I: Define requirements for developing and implementing a technique for building a semantic model of soft information fusion that can be used in a collaborative visual analytics application for a small distributed team.  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 from social media and online social communities in foreign nations that are potentially hostile to US and Coalition interests.  Currently, fusing information from these sources is extremely labor intensive and costly in terms of labor and time.  Developing models that can be adaptive to new information and that can be utilized by a team of people with collaborative visual analytics reasoning tools 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 online social blogs and social networking sites 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