Here are some examples of articles that are associated with the topic of the seminar. The articles can be viewed only inside HUT campus area.
Intelligent Decision Support Systems (DSSs) use expert systems technology to enhance the capabilities of decision makers (DMs) in understanding a decision problem and selecting a sound alternative. Because of the people-centred focus of such technologies, it is important not only to assess their technical aspects and overall performance but also to seek the views of potential users. This paper draws from the literature to classify methods for assessing intelligent Decision Support Systems and discusses our experiences in developing, operating and evaluating an intelligent decision support system for nuclear emergencies. The system assists decision makers in the formulation and ranking of alternatives and communicates its recommendation in a natural language form. The application highlights insights from the development process and shortcomings of existing assessment methods. Lessons learned from the study, challenges encountered and recommendations for future practices are discussed.
The warfare command decision support system is more and more important in war. Firstly, this paper discusses the weakness of existed DSS (Decision Support System). Secondly, the architecture of Weboriented Warfare Command DSS based on Agent and Data Warehouse (WOWC-DSS) is proposed. Thirdly, agent and data warehouse involved in such a system is discussed in detail. Fourthly, the Interface Agent based on MVC is introduced. Furthermore, this paper extends Struts framework by establishing a new description file of Struts framework to implement the Interface Agent, which makes the client web browse interface more friendly and easy to configure. Finally, B/S three-tire architecture based on J2EE is constructed, which improves the ability to cooperate with others.
This paper describes a generic decision support system based on an additive multiattribute utility model that is intended to allay many of the operational difficulties involved in the multicriteria decision-making process. The system accounts for uncertainty about the alternative consequences and admits incomplete information about the decision-makers preferences, which leads to classes of utility functions and weight intervals. The additive model is used to assess, on the one hand, average overall utilities, on which the ranking of alternatives is based and, on the other, minimum and maximum overall utilities, which give further insight into the robustness of this ranking. When the information obtained is not meaningful enough so as to definitively recommend an alternative, an iteration process can be carried out by tightening the imprecise parameters and assessing the non-dominated and potentially optimal alternatives or using Monte Carlo simulation techniques to determine useful information about dominance among the alternatives.
The practice of software verification and validation (V&V) has been overlooked in many safety-related expert systems even though it is central to a system being ultimately used to prevent hazards. This article examines the process of internal V&V of an expert system, explains those aspects of importance to an S&E manager or design engineer, and reviews reusability issues of the actual metrics of V&V.
The research and application of the operation optimization are very active now, but there are still some problems in this field, for example, the accurate process model is hard to establish for current complex industry process. So they can not instruct operation optimization very well. As more and more real-time data are sent and stored into database, abundantly valuable knowledge exists in the history data. This paper proposed the operation optimization decision support system based on data warehouse and data mining. The synthetic structure of the operation optimization DSS and the design scheme of its sub-systems are put forward and explicated, at the same time, the fuzzy association rule is introduced in this paper to mine the optimal operation value of a 300WM unit from large amount of history data in power plant. The optimal values are provided to the operators to guide the operation online and great success has been achieved in the industry process.
In this study, Decision Trees Algorithms were used with promising results in various critical problems, concerning heart sound diagnosis. In general this diagnostic problem can be divided in many sub problems, each one dealing either with one morphological characteristic of the heart sound or with difficult to distinguish heart diseases. The sub problems of the discrimination of Aortic Stenosis from Mitral Regurgitation and the discrimination between the second heart sound split, opening snap and third heart sound, are used as case studies. Using signalprocessing methods, we extracted the heart sound feature vector. Relevance analysis was performed using the Uncertainty Coefficient. Then for each heart sound diagnosis sub problem, a Specific Decision Tree (DT) was constructed. Decision Tree pruning was also investigated. Finally, a General Decision Support System Architecture for the Heart Sound Diagnosis problem, is proposed. The partial diagnosis, given by these DT, can be combined using arbitration rules to give the final diagnosis. These rules can be implemented by another DT, or can be based on different methods, algorithms, or even on expert knowledge. All these can lead to an Integrated Decision Support System Architecture for Heart Sound Diagnosis.
Leakage detection is an important issue in many chemical sensing applications. Leakage detection hy thresholds suffers from important drawbacks when sensors have serious drifts or they are affected by cross-sensitivities. Here we present an adaptive method based in a Dynamic Principal Component Analysis that models the relationships between the sensors in the may. In normal conditions a certain variance distribution characterizes sensor signals. However, in the presence of a new source of variance the PCA decomposition changes drastically. In order to prevent the influence of sensor drifts the model is adaptive and it is calculated in a recursive manner with minimum computational effort. The behavior of this technique is studied with synthetic signals and with real signals arising by oil vapor leakages in an air compressor. Results clearly demonstrate the efficiency of the proposed method.
There are a number of different quantitative models that can be used in a medical diagnostic decision support system (MDSS) including parametric methods (linear discriminant analysis or logistic regression), non-parametric models (K nearest neighbor, or kernel density) and several neural network models. The complexity of the diagnostic task is thought to be one of the prime determinants of model selection. Unfortunately, there is no theory available to guide model selection. Practitioners are left to either choose a favorite model or to test a small subset using cross validation methods. This paper illustrates the use of a self-organizing map (SOM) to guide model selection for a breast cancer MDSS. The topological ordering properties of the SOM are used to de®ne targets for an ideal accuracy level similar to a Bayes optimal level. These targets can then be used in model selection, variable reduction, parameter determination, and to assess the adequacy of the clinical measurement system. These ideas are applied to a successful model selection for a real-world breast cancer database. Diagnostic accuracy results are reported for individual models, for ensembles of neural networks, and for stacked predictors.#2000 Published by Elsevier Science B.V.