A Context-Driven Framework for Proactive Decision Support With Applications
A Context-Driven Framework for Proactive Decision Support With Applications
复制标题
通过应用程序提供主动决策支持的上下文驱动框架
DOI：
10.1109/access.2017.2707091
复制
发表时间：
2017
期刊：
影响因子：
3.9
通讯作者：
D. Kleinman
中科院分区：
文献类型：
--
作者：
Manisha Mishra;D. Sidoti;G. V. Avvari;Pujitha Mannaru;D. F. M. Ayala;K. Pattipati;D. Kleinman
预计未来C4ISR（指挥、控制、通信、计算机、情报、监视和侦察）作战的主要挑战包括在高度动态、不对称、不可预测和网络中心环境下的快速任务规划/再规划。为这种复杂的任务环境开发决策支持需要使用大量结构化、非结构化和半结构化数据自动处理、解释和开发前瞻性决策，同时减少达成决策所需的时间。为了克服这种数据泛滥，需要通过在正确的任务背景下从正确的来源获取、融合和将正确的数据/信息/知识在正确的时间为正确的目的传递给正确的决策者（DM）来掌握信息优势（6R）。实现6R的根本挑战是构思一个通用框架，该框架包括相关情境要素的动态、它们与当前和不断变化的形势的相互依存和相关性，同时考虑到决策管理的认知状态。在本文中，我们提出了一个情境驱动的主动决策支持（PDS）框架，该框架包括：1)基于自适应模型的动态图模型（例如，动态层次贝叶斯网络）和伴随的用于上下文表示、推理和预测的推理算法；2)用于上下文驱动操作的信息选择、评估和优先排序方法，包括不确定性管理方法；3)将PDS概念应用于具有代表性的海上作业的行动方案建议。
Major challenges anticipated in the future C4ISR (command, control, communications, computers, intelligence, surveillance, and reconnaissance) operations involve rapid mission planning/ re-planning in highly dynamic, asymmetric, unpredictable, and network-centric environments. Developing decision support for such complex mission environments requires automated processing, interpretation, and development of proactive decisions using large volumes of structured, unstructured, and semi-structured data, while simultaneously decreasing the time necessary to arrive at a decision. To overcome this data deluge, there is a need for mastering information dominance via acquisition, fusion, and transfer of the right data/information/knowledge from the right sources in the right mission context to the right decision-maker (DM) at the right time for the right purpose (6R). The fundamental challenge in achieving the 6R is to conceive a generic framework that encompasses the dynamics of relevant contextual elements, their interdependence and correlation to the current and evolving situation, while taking into account the cognitive status of the DM. In this paper, we propose a context-driven proactive decision support (PDS) framework that comprises: 1) adaptive model-based dynamic graph models (e.g., Dynamic Hierarchical Bayesian Networks) and the concomitant inference algorithms for context representation, inference, and forecasting, 2) information selection, valuation, and prioritization methods for context-driven operations, including uncertainty management approaches, and 3) application of PDS concepts for courses of action recommendations across representative maritime operations.