Within the dynamic environment of an Air Operations Center (AOC), effective decision-making is highly dependent on
timely and accurate situation assessment. In previous research efforts the capabilities and potential of a Bayesian belief
network (BN) model-based approach to support situation assessment have been demonstrated. In our own prior research,
we have presented and formalized a hybrid process for situation assessment model development that seeks to ameliorate
specific concerns and drawbacks associated with using a BN-based model construct. Specifically, our hybrid
methodology addresses the significant knowledge acquisition requirements and the associated subjective nature of using
subject matter experts (SMEs) for model development. Our methodology consists of two distinct functional elements: an
off-line mechanism for rapid construction of a Bayesian belief network (BN) library of situation assessment models
tailored to different situations and derived from knowledge elicitation with SMEs; and an on-line machine-learning-based
mechanism to learn, tune, or adapt BN model parameters and structure. The adaptation supports the ability to
adjust the models over time to respond to novel situations not initially available or anticipated during initial model
construction, thus ensuring that the models continue to meet the dynamic requirements of performing the situation
assessment function within dynamic application environments such as an AOC. In this paper, we apply and demonstrate
the hybrid approach within the specific context of an AOC-based air campaign monitoring scenario. We detail both the
initial knowledge elicitation and subsequent machine learning phases of the model development process, as well as
demonstrate model performance within an operational context.
Recent military operations have demonstrated the use by adversaries of non-traditional or asymmetric military tactics to offset US military might. Rogue nations with links to trans-national terrorists have created a highly unpredictable and potential dangerous environment for US military operations. Several characteristics of these threats include extremism in beliefs, global in nature, non-state oriented, and highly networked and adaptive, thus making these adversaries less vulnerable to conventional military approaches. Additionally, US forces must also contend with more traditional state-based threats that are further evolving their military fighting strategies and capabilities. What are needed are solutions to assist our forces in the prosecution of operations against these diverse threat types and their atypical strategies and tactics. To address this issue, we present a system that allows for the adaptation of a multi-resolution adversarial model. The developed model can then be used to support both training and simulation based acquisition requirements to effectively respond to such an adversary. The described system produces a combined adversarial model by merging behavior modeling at the individual level with aspects at the group and organizational level via network analysis. Adaptation of this adversarial model is performed by means of an evolutionary algorithm to build a suitable model for the chosen adversary.
In dynamic environments (e.g. an Air Operations Center (AOC)), effective real-time monitoring of mission execution is highly dependent on situation awareness (SA). But whereas an individual's perception of mission progress is biased by his or her immediate tasks and environment, the combined perspectives of key individuals provides an effects-based assessment of the mission overall. Belief networks (BNs) are an ideal tool for modeling and meeting the requirements of SA: at the individual level BNs emulate a skilled human's information fusion and reasoning process in a multi-task environment in the presence of uncertainty. At the mission level, BNs are intelligently combined to yield a common operating picture. While belief networks offer significant advantages for SA in this manner, the work of defining and combining the models is difficult due to factors such as multiple-counting and conflicting reports. To address these issues, we develop a system consisting of three distinct functional elements: an off-line mechanism for rapid construction of a BN library of SA models tailored to different air combat operation situations and derived from knowledge elicitation with subject matter experts; an off-line mechanism to adapt and combine BN models that supports the ability to adjust the SA models over time and in response to novel situations not initially available or anticipated during model construction; and an on-line combination of SA models to support an enhanced SA and the ability to
monitor execution status in real time and informed by and responsive to the individuals and situations involved.
The pervasiveness of software and networked information systems is evident across a broad spectrum of business and government sectors. Such reliance provides an ample opportunity not only for the nefarious exploits of lone wolf computer hackers, but for more systematic software attacks from organized entities. Much effort and focus has been placed on preventing and ameliorating network and OS attacks, a concomitant emphasis is required to address protection of mission critical software. Typical software protection technique and methodology evaluation and verification and validation (V&V) involves the use of a team of subject matter experts (SMEs) to mimic potential attackers or hackers. This manpower intensive, time-consuming, and potentially cost-prohibitive approach is not amenable to performing the necessary multiple non-subjective analyses required to support quantifying software protection levels. To facilitate the evaluation and V&V of software protection solutions, we have designed and developed a prototype adaptive cyber attack modeling system. Our approach integrates an off-line mechanism for rapid construction of Bayesian belief network (BN) attack models with an on-line model instantiation, adaptation and knowledge acquisition scheme. Off-line model construction is supported via a knowledge elicitation approach for identifying key domain requirements and a process for translating these requirements into a library of BN-based cyber-attack models. On-line attack modeling and knowledge acquisition is supported via BN evidence propagation and model parameter learning.
Dynamic resource allocation for sensor management is a problem that demands solutions beyond traditional approaches to optimization. Market-based optimization applies solutions from economic theory, particularly game theory, to the resource allocation problem by creating an artificial market for sensor information and computational resources. Intelligent agents are the buyers and sellers in this market, and they represent all the elements of the sensor network, from sensors to sensor platforms to computational resources. These agents interact based on a negotiation mechanism that determines their bidding strategies. This negotiation mechanism and the agents' bidding strategies are based on game theory, and they are designed so that the aggregate result of the multi-agent negotiation process is a market in competitive equilibrium, which guarantees an optimal allocation of resources throughout the sensor network. This paper makes two contributions to the field of market-based optimization: First, we develop a market protocol to handle heterogeneous goods in a dynamic setting. Second, we develop arbitrage agents to improve the efficiency in the market in light of its dynamic nature.
Within the context of military air operations, Time-sensitive targets (TSTs) are targets where modifiers such, “emerging, perishable, high-payoff, short dwell, or highly mobile” can be used. Time-critical targets (TCTs) further the criticality of TSTs with respect to achievement of mission objectives and a limited window of opportunity for attack. The importance of TST/TCTs within military air operations has been met with a significant investment in advanced technologies and platforms to meet these challenges. Developments in ISR systems, manned and unmanned air platforms, precision guided munitions, and network-centric warfare have made significant strides for ensuring timely prosecution of TSTs/TCTs. However, additional investments are needed to further decrease the targeting decision cycle. Given the operational needs for decision support systems to enable time-sensitive/time-critical targeting, we present a tool for the rapid generation and analysis of mission plan solutions to address TSTs/TCTs. Our system employs a genetic algorithm-based multi-objective optimization scheme that is well suited to the rapid generation of approximate solutions in a dynamic environment. Genetic Algorithms (GAs) allow for the effective exploration of the search space for potentially novel solutions, while addressing the multiple conflicting objectives that characterize the prosecution of TSTs/TCTs (e.g. probability of target destruction, time to accomplish task, level of disruption to other mission priorities, level of risk to friendly assets, etc.).
Military services require C4I systems that support a full spectrum of operations. This is specifically relevant to the theatre missile defense (TMD) mission planning and analysis community where there have been several recent concept changes; advancements in information technology, sensors, and weapons; and expansion in the diversity and capabilities of potential adversaries. To fully support campaign development and analysis in this new environment, there is a need for systems and tools that enhance understanding of adversarial behavior, assess potential threat capabilities and vulnerabilities, perform C4I system trades, and provide methods to identify macro-level novel or emergent combat tactics and behavior derived from simpler micro-level rules. Such systems must also be interactive, collaborative, and semi-autonomous, providing the INTEL analyst with the means for exploration and potential exploitation of novel enemy behavior patterns. To address these issues we have developed an Intelligent Threat Assessment Processor (ITAP) to provide prediction and interpretation of enemy courses of actions (eCOAs) for the TMD domain. This system uses a combination of genetic algorithm-based optimization in tandem with the spatial analysis and visualization capabilities of a commercial-off-the-shelf (COTS) geographic information system to generate and evaluate potential eCOAs.