Software agents have been heralded as the most important emerging technology of the decade. As software development firms eagerly attempt to integrate these autonomous programs into their products, researchers attempt to define the concept of agency and to develop architectures that will improve agent capabilities. Decision Support System (DSS) researchers have been eager to integrate agents into their applications, and exploratory works in which agents have been used within a DSS have been documented. This dissertation attempts to further this exploration by studying the agent features and underlying architectures that can lead to the successful integration of agents in DSS. This exploration is carried out in three parts. In the first part, a review of the relevant research streams is provided. The history and current status of software agents is first discussed. Similarly, a historical and current view of DSS research is provided. Lastly, a historical and tutorial-type of discussion is provided on the topic of Artificial Intelligence (AI) planning. This review of the relevant literature provides a general background for the conceptual analyses and implementations that are carried out in the next two sections. In the second part, the literature on software agents is synthesized to develop a definition of agency applicable to DSS. Using this definition, an agent-integrated DSS that supports variance-analysis is designed and developed. Following this implementation, a general framework for agent-enabling DSS is suggested. The use of this framework promises to raise some DSS to a new level of capability whereby "what-if" systems are transformed into real-time, proactive systems. The third part utilizes this general framework to agent-enable a corporate-planning system DSS and extends the framework in the second section through the introduction of an automated-planning agent. The agent uses AI planning to generate decision-making alternatives, providing a means to integrate and sequence the models in the DSS. The architecture used to support this planning agent is described. This new kind of DSS enables not only the monitoring of goals, but also the maintenance of these goals through agent-generated plans. The conclusion summarizes the contributions of this work and outlines in considerable detail potential research opportunities in the realm of software agents, DSS, and planning. / Ph. D.

In this paper, we present solutions concerning communications resource allocation for tactical communication networking. Given a mission definition (which defines communication needs among participants) and participant capabilities (such as processing power and bandwidth), algorithms are presented to determine if the mission as presented is feasible. The mathematical foundation of the problem is presented, and a "static" model to determine feasibility is shown. Further evolution of the algorithm into a "dynamic" model and the reasons for the more demanding requirements are presented. Reasoning behind use of the Netflo algorithm in the dynamic model is also discussed. The inclusion of the algorithm in a stand-alone program is discussed, including overall program structure, graphical user interface components and alternative output (such as the generation of high level network policy). Finally, future work in this area is discussed. / Master of Science

A significant increase in campus-based emergencies warrants the investigation into emergency management information systems that serve a novice crisis decision-maker. Institutions of higher education that are not large enough to have dedicated emergency management offices generally press novice decision-makers into emergency management roles. An investigation was conducted to assess the impact of an emergency management geospatial information system on the decision performance of novice crisis managers through the use of a scenario-based simulation. A mixed method sequential explanatory method was used to collect quasi-experimental data on decision time, decision accuracy and situational awareness. Qualitative analysis was conducted through interviews with participants. Statistical results indicate the decision accuracy is positively affected by the use of an emergency management geospatial information system. Data Envelopment Analysis (DEA) is non-parametric linear programming method used to identify decision-making units in a data set that are optimal in their use of single or a set of resources (inputs) in delivering a set of expected results (outputs). DEA indicated that efficiency ratios from the geospatial information system group outperform the traditional group. Geospatial information systems hold much promise in providing systems that are easy to use, promote heightened levels of situational awareness and decision support.

No description available.

No description available.

Nuclear govemment-oversight-agency (GOA) managers face increasing numbers of strategic decisions with fewer people to support their strategic decision processes. There is an increasing need to find new means of strategic decision support for nuclear GOA managers. This exploratory research contributes toward meeting this need by: (1) developing a set of contextual models of strategic decision making that link mental activities with information needs; (2) deriving a methodology to study the characteristics of the information needed by nuclear GOA managers when formulating strategic problems; and (3) demonstrating the methodology's use in drawing implications for designing decision tools. The literature reviewed in the areas of management. strategic management, decision making, decision tools, and information characteristics formed the foundation for the development of three contextual models of individual, strategic decision making. The most detailed model. the Elementary Mental Activities Model, links the mental activities of strategic decision making with types of information, providing a perspective for strategic information. An experiment was designed to engage nuclear GOA managers in realistic, strategic decision situations. Concurrent verbalizations yielded verbal protocols. Units of information used were identified according to the types of information-entities, attributes, values. relationships. and operators-in the Elementary Mental Activities Model. Unique units of information were identified during coding. "Frequency of use" and "use" by subject and by exercise were calculated for each unit of information. The information characteristics source. level of detail, class, internal/external, and relationship complexity were assigned to entities, relationships. or operators. Thirteen analyses of the data demonstrated the methodology's value for research in strategic decision processes, in strategic information, and in decision tools. All but one of the results were supported in the literature on strategic decision processes. The research led to the following, overall conclusions. 1. The Elementary Mental Activities Model represents the information use of nuclear GOA managers engaged in strategic decision processes and characterizes their strategic decision processes in terms of information use. 2. The methodology developed is useful in measuring the information use of nuclear GOA managers engaged in strategic decision processes for the purposes of determining information needs for designing decision tools. / Ph. D.

Improved strategic location of an Emergency Medical Service (EMS) facility can significantly increase EMS efficiency. Urban planners need to consider a location that satisfies multiple criteria in order to make an informed decision about a future EMS facility site. Apart from basic criteria such as parcel value and size, decision-makers need to consider area and population coverage from potential parcels. Geographic Information Systems (GIS) provide an adequate analysis environment for EMS facility siting as many considered criteria are of a spatial nature. However, urban planners making decisions about an EMS facility site often lack the necessary expertise to make full use of challenging GIS tools. In order to help urban planners in the analysis process, this research developed a Spatial Decision Support System (SDSS) for EMS facility siting. The system was developed in ESRI ArcGIS (9.3) using the Visual Basic for Applications (VBA) programming environment. The objective of the system was to integrate spatial data, analysis, and visualization in a single system to help users evaluate a facility siting problem. The system's performance was tested using data for the Town of Blacksburg, VA. In addition, the system was evaluated by local planners and GIS staff with experience in EMS facility siting. Planners agreed the system enables more comprehensive and straightforward use of GIS for EMS facility siting analysis than other available siting tools. Potential improvements include a simpler user interface, synthesis of geoprocessing techniques, reduction of analysis time through automation, and better decision-making by improved visualization of results. / Master of Science

No description available.

<p> The constantly changing and dynamic nature of medical knowledge has proven to be challenging for healthcare professionals. Due to reliance on human knowledge the practice of medicine in many cases is subject to errors that endanger patients' health and cause substantial financial loss to both public and governmental health sectors. Computer based clinical guidelines have been developed to help healthcare professionals in practicing medicine. Currently, the decision making steps within most guideline modeling languages are limited to the evaluation of basic logic expressions. On the other hand, data mining analyses aim at building descriptive or predictive mining models that contain valuable knowledge; and researchers in this field have been active to apply data mining techniques on health data. However, this type of knowledge can not be represented using the current guideline specification standards.</p> <p> In this thesis, we focus is on encoding, sharing and finally using the results obtained from a data mining study in the context of clinical care and in particular at the point of care. For this purpose, a knowledge management framework is proposed that addresses the issues of data and knowledge interoperability. Standards are adopted to represent both data and data mining results in an interoperable manner; and then the incorporation of data mining results into guideline-based Clinical Decision Support Systems is elaborated. A prototype tool has been developed as a part of this thesis that serves as the proof of concept which provides an environment for clinical guideline authoring and execution. Finally three real-world clinical case studies are presented.</p> / Thesis / Master of Applied Science (MASc)

Computerized decision aids are powerful tools to assist with decision-making. Decision models are designed to incorporate and analyze available data in order to present a recommended solution to a problem. Business decision makers, including accountants, have much to gain from integrating decision support technology with their own skills and experience. Several studies have determined that there are many instances in which these decision aids perform favorably to human decision-makers. Despite this fact, studies have shown that reliance upon these aids is incomplete, even when they process data in a highly efficient manner. On the other hand, decision aids have limitations. If such a decision support system is not updated to match changing conditions, relying on the aid can lead to suboptimal decision-making. This study uses a laboratory experiment involving a managerial accounting task: prediction of manufacturing overhead costs. In the experimental scenario, a decision support system's recommended solutions become inaccurate due to a shift in environmental conditions. The first research objective is to determine whether subjects rely on the aid's advice before this change and, to their detriment, after the change. The second research objective is to examine whether the feedback environment, the timing of the decision aid's inclusion into the task, or the inherent confidence level of the task participant affect the tendency to rely on the aid in both of these environmental conditions. The results of the study provide evidence that decision-makers rely on decision aids, and are susceptible to over-reliance on them. These findings add to the results of prior studies that only examine a single trial task. Additionally, it is determined that the timing of a decision aid's recommendation can affect the degree to which it is relied upon. Next, there is evidence that feedback environment can help reliance and mitigate over-reliance. There is no evidence that task confidence affects reliance. Lastly, decision aids result in longer amounts of time used to complete the task. / Ph. D.