Douglas Boulware

SAWA: an assistant for higher-level fusion and situation awareness

Situation awareness involves the identification and monitoring of relationships among level-one objects. This problem in general is intractable (i.e., there is a potentially infinite number of relations that could be tracked) and thus requires additional constraints and guidance defined by the user if there is to be any hope of creating practical situation awareness systems. This paper describes a Situation Awareness Assistant (SAWA) that facilitates the development of user-defined domain knowledge in the form of formal ontologies and rule sets and then permits the application of the domain knowledge to the monitoring of relevant relations as they occur in evolving situations. SAWA includes tools for developing ontologies in OWL and rules in SWRL and provides runtime components for collecting event data, storing and querying the data, monitoring relevant relations and viewing the results through a graphical user interface. An application of SAWA to a scenario from the domain of supply logistics is also presented.

Realizing situation awareness within a cyber environment

Situation Awareness (SA) problems all require an understanding of current activities, an ability to anticipate what may happen next, and techniques to analyze the threat or impact of current activities and predictions. These processes of SA are common regardless of the domain and can be applied to the detection of cyber attacks. This paper will describe the application of a SA framework to implementing Cyber SA, describe some metrics for measuring and evaluating systems implementing Cyber SA, and discuss ongoing work in this area. We conclude with some ideas for future activities.

Evaluating algorithmic techniques in supporting situation awareness

How well does an algorithm support its purpose and user base? Has automation provided the user with the ability to augment their production, quality or responsiveness? In a number of systems today these questions can be answered by either Measures of Performance (MOP) or Measures of Effectiveness (MOE). However, the fusion community has not yet developed sufficient measures and has only recently devoted a concerted effort to address this deficiency. In this paper, we will summarize work in metrics for the lower levels of fusion (object ID, tracking, etc) and discuss whether these same metrics still apply to the higher levels (Situation Awareness), or if other approaches are necessary. We conclude this paper with a set of future activities and direction.

A situation awareness model applied to multiple domains

Full Spectrum Dominance, or as defined by Joint Vision 2020, the ability to be persuasive in peace, decisive in war and preeminent in any form of conflict, cannot be accomplished without the ability to know what the adversary is currently doing as well as the capacity to correctly anticipate the adversarys future actions. A key component in the ability to predict the adversarys intention is Situation Awareness (SA). In this paper we provide a discussion of an SA model, examine a specific instantiation of the model and demonstrate how it has been applied to two specific domains: Global Monitoring and Cyber Awareness. We conclude this paper with a discussion on future work.

Lessons learned from developing SAWA: a situation awareness assistant

SAWA is a situation awareness assistant being developed by Versatile Information Systems, Inc. During the process of its development, several lessons were learned about advantages and limitations of certain approaches, techniques, and technologies as they are applied to situation awareness. This paper begins with an overview of SAWA and then focuses on some of the more significant lessons learned. These include the pros and cons of leveraging semantic Web technologies, the handling of time-varying attributes, and the processing of uncertainty.

A Parallel Spatial Co-location Mining Algorithm Based on MapReduce

Spatial association rule mining is a useful tool for discovering correlations and interesting relationships among spatial objects. Co-locations, or sets of spatial events which are frequently observed together in close proximity, are particularly useful for discovering their spatial dependencies. Although a number of spatial co-location mining algorithms have been developed, the computation of co-location pattern discovery remains prohibitively expensive with large data size and dense neighborhoods. We propose to leverage the power of parallel processing, in particular, the MapReduce framework to achieve higher spatial mining processing efficiency. MapReduce-like systems have been proven to be an efficient framework for large-scale data processing on clusters of commodity machines, and for big data analysis for many applications. The proposed parallel co-location mining algorithm was developed on MapReduce. The experimental result of the developed algorithm shows scalability in computational performance.

Mobile agent-based distributed fusion (MADFUSION) system

This paper considers a system architecture referred to as the mobile agent-based distributed fusion (MADFUSION) system. The system environment consists of a peer-to-peer ad-hoc network in which information may be dynamically distributed and collected via publish/subscribe functionality implemented at each node of the network to facilitate data sharing and decision making in Level 2 fusion. The Level 2 decision making process implemented in the system consists of the enhanced doctrinal template matching (EDTM) algorithm which is shown to be an improvement over the pre-existing doctrinal template matching algorithm. This algorithm is developed to operates on information obtained from lower layer fusion processes in order to identify aggregated groups of entities. The template matching algorithm is shown to be an improvement over a previously existing algorithm. The MADFUSION system is proposed to extend the client/server architecture of various publish/subscribe applications to an architecture providing decentralization, re-configurability, mobility, attainability and prevention of single points of failure. The system is implemented in a wireless ad-hoc network (802.11b) and performs the publish/subscribe functionality through the implementation of a mobile agent based framework. The software agents travel deterministically from node-to-node carrying a data payload consisting of information which may be subscribed to by users within the network. Within this system, situation awareness (Level 2 fusion) can be sought by using these multi-domain information sources (GMTI, Video, or SAR) for evaluation at each node with different distributed information fusion algorithms.

Incremental and parallel spatial association mining

Spatial association mining has been used for discovering frequent spatial association patterns from large static spatial databases. When a large spatial database is updated, it is computationally expensive to redo the pattern discovery process for the updated database. This work presents the problem of finding spatial association patterns incrementally from evolving databases which are constantly updated with fresh data. The proposed method is implemented on the MapReduce framework for large-scale spatial data processing, and empirically evaluated. The developed algorithm shows substantial performance improvements when compared with an iterative and non-incremental spatial association mining algorithm.

A framework of spatial co-location mining on MapReduce

Spatial association rule mining is a useful tool for discovering interesting relationships among spatial objects. Co-locations, or sets of spatial events which are frequently observed together in close proximity, are particularly useful for discovering their spatial dependencies. The computation of co-location mining is prohibitively expensive with increase in data size and spatial neighborhood. In this work, we propose to parallelize spatial co-location mining on distributed machines. A framework of parallel co-location mining based on MapReduce is presented.

Knowledge representation requirements for situation awareness

Full spectrum dominance (FSD), as defined by Joint Vision 2020, is the ability to be persuasive in peace, decisive in war and preeminent in any form of conflict. FSD cannot be accomplished without the capability to know what the adversary is currently doing as well as the capacity to correctly anticipate the adversarys future actions. This ability has been referred to as situation awareness (SA). An effective SA capability must seamlessly combine data driven bottom up approaches with top down goal directed approaches. A requirement that cuts across many of the functions required to provide SA is knowledge representation. In this paper, we provide an overview of SA, describe a framework that can assist in building SA systems, and provide a discussion on current issues with database and knowledge representation.