智慧型決策支援系統(Intellignet Decision Support Systems)的特點是可以同時處理定性和定量資料於同一個系統中，以同時執行各種知識推論及數量模式之運算。黑板架構(Blackboard Architecture)的做法是將決策支援求解過程的資料、模式和知識運用情形記錄於一共同工作區─稱之為黑板(Blackboard)，將模式及知識記錄在所謂的知識源(Knowledge Sources)中，並提供較有彈性之控制機制，應可提供較佳的解釋功能。以黑板架構為基礎的智慧型系統多應用在科學及工程方面，在管理方面卻寥寥無幾；管理問題多半屬於半結構性或非結構性，良好的解釋應為智慧型決策系統之重要功能。本研究擬就銀行業之授信審查做為本系統之專業領域知識(Domain Knowledge)，運用黑板架構中的階層化問題表現方式及模組化知識源分類之特性，建立提供完善解釋功能之智慧型授信決策支援系統。 / Incorporating artificial intelligence (AI) technique is critical to improve the functionality of decision support systems. Explanation function for consultation-based systems has been emphasized in the literature and should be considered important in developing intelligent decision support systems. Blackboard architecture can support a well-organized explanation facility due to its structurization of problem solving space, modularization of domain knowledge, and flexibility of reasoning control. Applying blackboard systems to managerial domain gets attention recently. Since most managerial consultation problems are unstructured or semi-structured, good explanation facility should be able to enhance the consultation effectiveness. The thesis investigates the potential of developing an explanation facility on the blackboard architecture using the loan evaluation as an example. During the interactive consultation process, the system can answer questions such as "What?", "Why?", "How?", and "Where?" with a friendly user interface. In terms of contribution, the inclusion of explanation facility can potentially increase the willingness and confidence of decision makers in using intelligent decision support systems. On the other hand, applying the graphic user interface to the development of explanation facility based on the blackboard architecture can make the reasoning process transparent and enhance the acceptance of this AI technique to managerial problem solving.

It has been suggested 'expert systems' might have a significant role in the future through enabling many more people to access human experts. It is, therefore, important to understand how potential users interact with these computer systems. This study investigates the effect of extension agents' attitudes towards the features and use of an example expert system for rice disease diagnosis and management(POSOP). It also considers the effect of extension agents' personality traits and intelligence on their attitudes towards its use, and the agents' perception of control over using it. Answers to these questions lead to developing better systems and to increasing their adoption. Using structural equation modelling, two models - the extension agents' perceived usefulness of POSOP, and their attitude towards the use of POSOP, were developed (Models ATU and ATP). Two of POSOP's features (its value as a decision support tool, and its user interface), two personality traits (Openness (0) and Extraversion (E)), and the agents' intelligence, proved to be significant, and were evaluated. The agents' attitude towards POSOP's value had a substantial impact on their perceived usefulness and their attitude towards using it, and thus their intention to use POSOP. Their attitude towards POSOP's user interface also had an impact on their attitude towards its perceived usefulness, but had no impact on their attitude towards using it. However, the user interface did contribute to its value. In Model ATU, neither Openness (0) nor Extraversion (E) had an impact on the agents' perceived usefulness indicating POSOP was considered useful regardless of the agents' personality background. However, Extraversion (E) had a negative impact on their intention to use POSOP in Model ATP indicating that 'introverted' agents had a clear intention to use POSOP relative to the 'extroverted' agents. Extension agents' intelligence, in terms of their GPA, had neither an impact on their attitude, nor their subjective norm (expectation of 'others' beliefs), to the use of POSOP. It also had no association with any of the variables in both models. Both models explain and predict that it is likely that the agents will use POSOP. However, the availability of computers, particularly their capacity, are likely to impede its use. Although the agents believed using POSOP would not be difficult, they still believed training would be beneficial. To be a useful decision support tool, the expert system's value and user interface as well as its usefulness and ease of use, are all crucially important to the preliminary acceptance of a system. Most importantly, the users' problems and needs should be assessed and taken into account as a first priority in developing an expert system. Furthermore, the users should be involved in the system development. The results emphasise that the use of an expert system is not only determined by the system's value and its user interface, but also the agents' perceived usefulness, and their attitude towards using it. In addition, the agents' perception of control over using it is also a significant factor. The results suggested improvements to the system's value and its user interface would increase its potential use, and also providing suitable computers, coupled with training, would encourage its use.

Demensvården i Sverige och i andra delar av världen har på olika sätt varit i fokus de senaste åren där man påtalat behovet att utveckla metoder och riktlinjer för hur vården ska bedrivas. Detta för att möta den växande andelen äldre människor som också utvecklar demenssjukdomar. Nationella projekt har drivits, företrädesvis i syfte att förbättra vård och omsorg av personer med demenssjukdom, men även för att förbättra diagnosticering och behandling. I denna avhandling beskrivs utvecklingen av det dator-baserade beslutsstödet för demensutredning, DMSS (Dementia Management and Support System), som syftar till att fungera som ett stöd för personer som arbetar med att diagnosticera och behandla personer med kognitiv sjukdom. Domänen valdes även på grund av dess komplicerade kunskapsinnehåll, där bland annat en spännvidd av olika typer av symptom, komplexa kliniska mätmetoder sett ur ett formaliseringsperspektiv, starkt teamorienterat arbetssätt, ställer krav på hur kunskap ska och är möjlig att formaliseras och integreras i ett beslutsstödsystem för att det ska bli användbart i kliniskt arbete. De olika studierna och delprojekten som beskrivs i avhandlingen syftar till att tillsammans skapa en grund för utveckling av ett kliniskt kognitivt verktyg som stödjer och utvecklar användarens kognitiva processer (lärande, beslutsfattande, resonemang, etc.), samtidigt som det stödjer utvecklingen av det kliniska arbetet vari systemet ingår. I detta arbete fokuseras demensutredning som applikationsomr åde. Analyser har gjorts av den vidare användarkontexten, resonemangsprocesser, domän- och processkunskapen uttryckt i evidensbaserad litteratur och integrerad i klinisk praktik, terminologier samt formaliseringstekniker som kan hantera domänkunskapens egenskaper och användarsituationens krav. Prototyper har utvecklats och utvärderats i en iterativ process i samarbete med domänexperter, för användande i klinisk praktik i Sverige och Japan. För dessa studier har kvalitativa metoder använts i syfte att fånga så många olika aspekter som möjligt angående formalisering och interaktion, samt av praktiska skäl då det funnits begränsad tillgång till expertanvändare och patienter. Triangulering av metoder har tillämpats för att validera resultat. Kliniska utredningsverksamheter är komplexa processer, som är situerade, emergenta och styrda av individens behov, men även begränsade eller möjliggjorda av tillgängliga resurser på olika vårdnivåer i vårdprocessen. Det behövs metoder och verktyg som kan användas vid utveckling av system som syftar till att stödja dessa verksamheter. Det finns exempel på metoder som utvecklats för transformation av informell klinisk kunskap till en formell struktur som kan implementeras i ett beslutsstödsystem, där verktyg har utvecklats primärt i syfte att hjälpa kliniska experter att transformera sin kunskap till något en systemutvecklare kan använda. Den största nackdelen med dessa angreppssätt är att de är tidskrävande för experterna att sätta sej in i och använda. En metod har tillämpats i detta arbete där en teoribildning, som är gemensam för flera forskningsområden, använts för att strukturera klinisk process- och domänkunskap i en form som kan användas i formaliseringsarbete. Den konceptuella modellen av kliniskt arbete som utvecklats är baserad på verksamhetsteorin, kompletterad med general logics som kategoriskt, formellt teoretiskt ramverk för att möjliggöra transformationer mellan olika logiska språk och flexibel representation av riktlinjer och kunskap. Genom att göra en grundlig verksamhetsanalys utifrån ett aktivitetsperspektiv med hjälp av modellen, kan komponenter identifieras som kan formaliseras i en kunskapsbas och/eller kompletteras genom en design och implementation av ett gränssnitt som stödjer ett interaktivt resonemang och den kliniska processen. Resultatet av verkamhetsanalys och andra studier som presenteras i denna avhandling kommer att ligga till grund för vidare utveckling av DMSS för olika användarmiljöer, till att börja med i Sverige och Japan. Extensioner av systemet kommer att utvecklas som stödjer de olika ingående professionerna på olika vårdnivåer. Den konceptuella modellen kommer att utvecklas och tillämpas i framtida utvecklingsprojekt där beslutsstöd är en central komponent. Det formella ramverket kommer att utvecklas i syfte att kunna analysera och förfina kunskap i perspektivet av exempelvis olika set av kliniska riktlinjer som ställer olika krav på komplexitet hos logiken. Stödet till ett interaktivt resonemang vid användandet av systemet ska utvecklas med en kunskapsbas och ett dynamiskt gränssnitt speciellt utformat för ändamålet. Hittills har i första hand kvalitativa aspekter och syften varit i fokus i de olika projekten. Därför behöver varje utvecklingslinje ytterligare utvecklas med kvantitativa mål. Utvidgade utvärderingsstudier pågår, som syftar till att undersöka fördelning mellan olika nivåer av komplexitet hos patienter och vilken typ av stöd som behövs för respektive. När systemet är integrerat i daglig verksamhet kan faktorer som hur användande av systemet påverkar användaren och verksamheten undersökas. / There is a need to improve dementia care in Sweden. The main issues discussed are how to improve the competence of medical personnel and the quality of diagnosis and intervention. In this thesis the process of developing a decision-support system for the investigation of dementia is described, as one means to meet the need. The resulting prototype system DMSS (Dementia Management Support System) has been developed in cooperation with domain experts, and has been evaluated and redesigned in the process in an iterative development process. The process involves the assessment of evidence-based domain knowledge and its characteristics, the assessment of the procedural knowledge residing in clinical practice, and reasoning processes. Further, the terminology and main reasoning process integrated in the system have been validated. Qualitative methods have been used for these parts of the project for the purpose of assessing as many different aspects as possible, and for practical reasons due to the limited access to domain experts, patients and primary care physicians in the area. Triangulation of methods has been applied in order to validate results in the process. The development has been extended to also include prototypes for Japanese clinical environments. Clinical investigation activities are complex processes, which are situated, emergent and directed by the individual need of the patient, but also restricted or enhanced by the available resources at different points and at different care levels in the process. For the purpose of creating a system which provides support throughout the investigation process, the domain knowledge and the clinical investigation process was analysed and formalised in a conceptual model of clinical activity, developed based on activity theory and case studies of patients. The need for methods for the transformation of informal results from field studies into formal knowledge and design is addressed by providing the framework, which integrates the conceptual model of clinical activity and a method for the assessment and transformation of the knowledge to be integrated in a decision-support system. The model was used to identify actions and their characteristics suitable for formalisation in a decision-support system. Several sources of domain knowledge need to be integrated that express the knowledge differently, which increases the demands on a formalism for representation. The work towards formalising the diagnostic reasoning process in both typical and atypical patient's cases is presented, where the evidence in ambiguous cases is valued within different frames of references in order to improve specificity. Different logical frameworks have been applied, evaluated and developed using case studies of patients. Two lines of work towards a dementia logic and flexible guideline representation is presented; the defeasible, non-monotonic approach where many-valued dictionaries are used in a context-based argumentation framework; and the monotonic approach of integrating reasoning in a fundamental view of transformations between logics, using general logics as generalised and categorical framework.

Sensor networks are being used in several emerging applications not even imagined some years ago due to advances in sensing, computing, and communication techniques. However, these advances also pose various challenges that must be faced. One important challenge is related to the autonomous capability needed to setup and adapt the networks, which decentralizes the control of the network, saving communication and energy resources. Middleware technology helps in addressing this kind of problem, but there is still a need for additional solutions, particularly considering dynamic changes in users' requirements and operation conditions. This paper presents an agent-based framework acting as an integral part of a middleware to support autonomous setup and adaptation of sensor networks. It adds interoperability among heterogeneous nodes in the network, by means of autonomous behavior and reasoning. These features also address the needs for system setup and adaptations in the network, reducing the communication overhead and decentralizing the decision making mechanism. Additionally, preliminary results are also presented.

Layout Decision Analysis and Design is a ubiquitous problem in a variety of work domains that is important from both strategic and operational perspectives. It is largely a complex, vague, difficult, and ill-structured problem that requires intelligent and sophisticated decision analysis and design support. <br /><br /> Inadequate information availability, combinatorial complexity, subjective and uncertain preferences, and cognitive biases of decision makers often hamper the procurement of a superior layout configuration. Consequently, it is desirable to develop an intelligent decision support system for layout design that could deal with such challenging issues by providing efficient and effective means of generating, analyzing, enumerating, ranking, and manipulating superior alternative layouts. <br ><br /> We present a research framework and a functional prototype for an interactive Intelligent System for Decision Support and Expert Analysis in Multi-Attribute Layout Optimization (IDEAL) based on soft computing tools. A fundamental issue in layout design is efficient production of superior alternatives through the incorporation of subjective and uncertain design preferences. Consequently, we have developed an efficient and Intelligent Layout Design Generator (ILG) using a generic two-dimensional bin-packing formulation that utilizes multiple preference weights furnished by a fuzzy Preference Inferencing Agent (PIA). The sub-cognitive, intuitive, multi-facet, and dynamic nature of design preferences indicates that an automated Preference Discovery Agent (PDA) could be an important component of such a system. A user-friendly, interactive, and effective User Interface is deemed critical for the success of the system. The effectiveness of the proposed solution paradigm and the implemented prototype is demonstrated through examples and cases. <br /><br /> This research framework and prototype contribute to the field of layout decision analysis and design by enabling explicit representation of experts? knowledge, formal modeling of fuzzy user preferences, and swift generation and manipulation of superior layout alternatives. Such efforts are expected to afford efficient procurement of superior outcomes and to facilitate cognitive, ergonomic, and economic efficiency of layout designers as well as future research in related areas. <br /><br /> Applications of this research are broad ranging including facilities layout design, VLSI circuit layout design, newspaper layout design, cutting and packing, adaptive user interfaces, dynamic memory allocation, multi-processor scheduling, metacomputing, etc.

Layout Decision Analysis and Design is a ubiquitous problem in a variety of work domains that is important from both strategic and operational perspectives. It is largely a complex, vague, difficult, and ill-structured problem that requires intelligent and sophisticated decision analysis and design support. <br /><br /> Inadequate information availability, combinatorial complexity, subjective and uncertain preferences, and cognitive biases of decision makers often hamper the procurement of a superior layout configuration. Consequently, it is desirable to develop an intelligent decision support system for layout design that could deal with such challenging issues by providing efficient and effective means of generating, analyzing, enumerating, ranking, and manipulating superior alternative layouts. <br ><br /> We present a research framework and a functional prototype for an interactive Intelligent System for Decision Support and Expert Analysis in Multi-Attribute Layout Optimization (IDEAL) based on soft computing tools. A fundamental issue in layout design is efficient production of superior alternatives through the incorporation of subjective and uncertain design preferences. Consequently, we have developed an efficient and Intelligent Layout Design Generator (ILG) using a generic two-dimensional bin-packing formulation that utilizes multiple preference weights furnished by a fuzzy Preference Inferencing Agent (PIA). The sub-cognitive, intuitive, multi-facet, and dynamic nature of design preferences indicates that an automated Preference Discovery Agent (PDA) could be an important component of such a system. A user-friendly, interactive, and effective User Interface is deemed critical for the success of the system. The effectiveness of the proposed solution paradigm and the implemented prototype is demonstrated through examples and cases. <br /><br /> This research framework and prototype contribute to the field of layout decision analysis and design by enabling explicit representation of experts? knowledge, formal modeling of fuzzy user preferences, and swift generation and manipulation of superior layout alternatives. Such efforts are expected to afford efficient procurement of superior outcomes and to facilitate cognitive, ergonomic, and economic efficiency of layout designers as well as future research in related areas. <br /><br /> Applications of this research are broad ranging including facilities layout design, VLSI circuit layout design, newspaper layout design, cutting and packing, adaptive user interfaces, dynamic memory allocation, multi-processor scheduling, metacomputing, etc.

Problem: Engineering design decisions require the integration of information from multiple and disparate sources. However, this information is often independently created, limited to a single perspective, and not formally represented, thus making it difficult to formulate decisions. Hence, the primary challenge is the development of computational representations that facilitate the exchange of information for decision support. Approach: First, the scope of this research is limited to representing design decisions as compromise decision support problems (cDSP). To address this challenge, the primary hypothesis is that a formal language will enable the semantics of cDSP to be captured, thus providing a digital interface through which design information can be exchanged. The primary hypothesis is answered through the development of a description logic (DL) based formal language. The primary research question is addressed in four sub-questions. The first two research questions relate to the development of a vocabulary for representing the semantics of the cDSP. The first hypothesis used to answer this question is that formal information modeling techniques can be used to explicitly capture the semantics and structure of the cDSP. The second research question is focused on the realization of a computer-processible representation. The hypothesis used to answer this question is that DL can be used for developing computational-based representations. The third research question is related to the organization and retrieval of decision information. The hypothesis used to answer this question is DL reasoning algorithms can be used to support organization and retrieval. Validation: The formal language developed in this dissertation is theoretically and empirically validated using the validation square approach. Validation of the hypotheses is achieved by systematically building confidence through example problems. Examples include the cDSP construct, analysis support models, the design of a cantilever beam, and design of a structural fin array heat sink. Contributions: The primary contribution from this dissertation is a formal language for capturing the semantics of cDSPs and analysis support models comprised of: (1) a systematic methodology for decision formulation, (2) a cDSP vocabulary, (3) a graphical information model, and (4) a DL-based representation. The components, collectively, provide a means for exchanging cDSP information.

The use of computer modeling is fast increasing in almost every scientific, engineering and business arena. This dissertation investigates some challenging issues in design, modeling and analysis of computer experiments, which will consist of four major parts. In the first part, a new approach is developed to combine data from approximate and detailed simulations to build a surrogate model based on some stochastic models. In the second part, we propose some Bayesian hierarchical Gaussian process models to integrate data from different types of experiments. The third part concerns the development of latent variable models for computer experiments with multivariate response with application to data center temperature modeling. The last chapter is devoted to the development of nested space-filling designs for multiple experiments with different levels of accuracy.

A paradigm shift is emerging in system reliability and maintainability. The military and industrial sectors are moving away from the traditional breakdown and scheduled maintenance to adopt concepts referred to as Condition Based Maintenance (CBM) and Prognostic Health Management (PHM). In addition to signal processing and subsequent diagnostic and prognostic algorithms these new technologies involve storage of large volumes of both quantitative and qualitative information to carry out maintenance tasks effectively. This not only requires research and development in advanced technologies but also the means to store, organize and access this knowledge in a timely and efficient fashion. Knowledge-based expert systems have been shown to possess capabilities to manage vast amounts of knowledge, but an intelligent systems approach calls for attributes like learning and adaptation in building autonomous decision support systems. This research presents an integrated knowledge-based approach to diagnostic reasoning for CBM of engineering systems. A two level diagnosis scheme has been conceptualized in which first a fault is hypothesized using the observational symptoms from the system and then a more specific diagnostic test is carried out using only the relevant sensor measurements to confirm the hypothesis. Utilizing the qualitative (textual) information obtained from these systems in combination with quantitative (sensory) information reduces the computational burden by carrying out a more informed testing. An Industrial Language Processing (ILP) technique has been developed for processing textual information from industrial systems. Compared to other automated methods that are computationally expensive, this technique manipulates standardized language messages by taking advantage of their semi-structured nature and domain limited vocabulary in a tractable manner. A Dynamic Case-based reasoning (DCBR) framework provides a hybrid platform for diagnostic reasoning and an integration mechanism for the operational infrastructure of an autonomous Decision Support System (DSS) for CBM. This integration involves data gathering, information extraction procedures, and real-time reasoning frameworks to facilitate the strategies and maintenance of critical systems. As a step further towards autonomy, DCBR builds on a self-evolving knowledgebase that learns from its performance feedback and reorganizes itself to deal with non-stationary environments. A unique Human-in-the-Loop Learning (HITLL) approach has been adopted to incorporate human feedback in the traditional Reinforcement Learning (RL) algorithm.

The lack of system capability, budget, and schedule robustness against technology performance and development uncertainties has led to major setbacks in recent acquisition programs. This lack of robustness stems from the fact that immature technologies have uncertainties in their expected performance and development times and costs that translate to variations in system effectiveness and program development budget and schedule requirements. As such, the objective of this thesis is to formulate an assessment process that better informs acquisition decision-makers of program requirements robustness against such uncertainties. To meet the stated research objective, a conceptual methodology for assessing acquisition requirements robustness against technology performance and development uncertainties was formulated. This general approach provides a structured process for integrating probabilistic and quantitative forecasting, multi-criteria decision-making, and decision-support techniques to generate the statistical data needed to quantitatively predict requirements robustness. The results of the robustness assessment indicates to the decision-makers whether or not the technology or set of technologies being developed for the program will result in system capabilities and program budget and schedule that meet decision-maker requirements and preferences. This results in a more informed and justifiable selection of program technologies during initial program definition as well as formulation of program development and risk management strategies.