We introduce a new method for modeling rating (utility) functions which employs techniques from fuzzy set theory. The main idea is to build a hierarchical model, called a fuzzy operator tree (FOT), by recursively deco...
详细信息
We introduce a new method for modeling rating (utility) functions which employs techniques from fuzzy set theory. The main idea is to build a hierarchical model, called a fuzzy operator tree (FOT), by recursively decomposing a rating criterion into sub-criteria, and to combine the evaluations of these sub-criteria by means of suitable aggregation operators. Apart from the model conception itself, we propose an evolutionary method for model calibration that fits the parameters of an FOT to exemplary ratings. The possibility to adapt an FOT to a given set of data makes the approach also interesting from a machine learning point of view. The performance of the approach is evaluated by means of a suitable experimental study.
The delivery of multimedia content often needs the adaptation of the content in order to satisfy user constraints. With the Digital Item Adaptation part, the MPEG-21 standard already defines a useful frame-work to han...
详细信息
The delivery of multimedia content often needs the adaptation of the content in order to satisfy user constraints. With the Digital Item Adaptation part, the MPEG-21 standard already defines a useful frame-work to handle this task. However, in modern service-oriented architectures the functionality of adaptation is split over several services. Hence, the central instantiation of a suitable service chain needs to tackle a complex multi-objective optimization problem. In this problem between content choice and possible adaptations the current preference model in the MPEG-7/21 standard still lacks expressiveness. In the course of this paper we demonstrate this shortcoming and how the integration of more powerful models can ease the instantiation problem. Furthermore we explain how to efficiently evaluate preference trade-offs by evaluating skyline queries as currently investigated in the field of information systems. As a running example we use preference-based content adaptation in a typical media streaming application with Web services as basic modules. The contribution of our framework is to enable a central coordinator to instantiate an executable service composition chain by integrating all needed Web services to adapt the multimedia content in the best possible fashion in the sense of Pareto optimality.
We present a family of algebraic structures, called rectangular bilattices, which serve as a natural accommodation and powerful generalization to both intuitionistic fuzzy sets (IFSs) and interval-valued fuzzy sets (I...
详细信息
We present a family of algebraic structures, called rectangular bilattices, which serve as a natural accommodation and powerful generalization to both intuitionistic fuzzy sets (IFSs) and interval-valued fuzzy sets (IVFSs). These structures are useful on one hand to clarify the exact nature of the relationship between the above two common extensions of fuzzy sets, and on the other hand provide an intuitively attractive framework for the representation of uncertain and potentially conflicting information. We also provide these structures with adequately defined graded versions of the basic logical connectives, and study their properties and relationship. Application potential and intuitive appeal of the proposed framework are illustrated in the context of preference modeling.
Simulation optimization provides a structured approach to system design and configuration when analytical expressions for input/output relationships are unavailable. This research focuses on the development of a new s...
详细信息
Simulation optimization provides a structured approach to system design and configuration when analytical expressions for input/output relationships are unavailable. This research focuses on the development of a new simulation optimization technique applicable to systems having multiple performance measures. The aim of this research is to incorporate a simulation end user's preference towards risk and uncertainty into the search process for the best decision alternative. Automation of the optimization procedure is a necessity. Therefore, this paper proposes a simulation optimization method that involves a preference model, specifically adapted for decision making with simulation models. The proposed simulation optimization method is evaluated against two simulation optimization methods with embedded deterministic, multiple criteria decision making strategies. It is shown on average to obtain significantly better solutions in multiple types of experimental settings having normally distributed simulation performance measures. (c) 2006 Elsevier B.V. All rights reserved.
Many companies use product families in order to offer product variants that appeal to different market segments while minimizing costs. Because the market demand is generally not uniform for all possible product varia...
详细信息
Many companies use product families in order to offer product variants that appeal to different market segments while minimizing costs. Because the market demand is generally not uniform for all possible product variants, during the design phase a decision must be made as to which variants will be offered and how many. This thesis presents a new approach to solving this problem. The product is defined in terms of performance parameters. The market demand is captured in a preference model and applied to these parameters in order to represent the total potential market. The number and placement of the product variants are optimized in order to maximize percentage of the potential market that they span. This method is applied to a family of mountain bikes and a family of flow-regulating disks used in industrial applications. These examples show that usage of this method can result in a significant increase in potential market and a significant reduction in production costs.
This paper concerns problems of applying the approach based on rough sets and rule induction to a software engineering data analysis. More precisely, we focus our interest on a software cost estimation problem, which ...
详细信息
This paper concerns problems of applying the approach based on rough sets and rule induction to a software engineering data analysis. More precisely, we focus our interest on a software cost estimation problem, which includes predicting the effort required to develop a software system basing on values of cost factors. The case study of analysing the COCOMO data set, containing descriptions of representative historical projects, allows us to discuss how this approach could be used to: identify the most discriminatory cost factors, extract meaningful rule representation of classification knowledge from data, construct accurate rule based classifiers.
The majority of approaches to multicriteria optimization are based on quantitative representations of preferences of a decision maker, in which numerical procedures of multicriteria analysis are used for aggregation p...
详细信息
The majority of approaches to multicriteria optimization are based on quantitative representations of preferences of a decision maker, in which numerical procedures of multicriteria analysis are used for aggregation purposes. However, very often qualitative data cannot be known in terms of absolute values so that a qualitative approach is needed. Moreover, the multicriteria methods are directly applicable when alternatives are individuals-then they may be explicitly listed and ordered by an agent. However, sometimes the set of alternatives has combinatorial structure and it must be selected from the set of Cartesian products of value domains of attributes satisfying certain constraints. Then, the space of possible alternatives has a size exponential in the number of variables and ranking all alternatives explicitly is a complex and tedious task. In this paper we propose logic programming with ordered disjunction as a qualitative approach to combinatorial multicriteria decision making, allowing a concise representation of the preference structures, and a human-like form of expressions, being close to natural language, hence providing a good readability and simplicity. A combinatorial multicriteria decision making problem is encoded as a logic program, in which preferences of the decision maker are represented qualitatively. The optimal decision corresponds exactly to the preferred answer set of the program, obtained via the well-known methods of multicriteria analysis.
A rational decision-making process does not exclude the possibility of decision makers expressing different preferences and disagreeing regarding the effects of consequences and optimal course of actions. This point o...
详细信息
A rational decision-making process does not exclude the possibility of decision makers expressing different preferences and disagreeing regarding the effects of consequences and optimal course of actions. This point of view is explored in depth in this paper. A framework is developed that includes several decision makers (instead of just one) and allows for the variability of preferences among these decision makers. The information provided by the varying opinions of decision makers can be used to optimize our own decision-making. To achieve this, likelihood functions are developed for stated preferences among both discrete and continuous alternatives, and stated preference rankings of alternatives. Two applications are pursued: the optimization of the lifecycle utility of a structural system subject to consequences of failure proportional to the intensity of hazards exceeding a variable threshold, and to follow-up consequences. Also, the problem of tight decisions or close calls is investigated in order to explore the efficiency of a Bayesian approach using stated preferences and stated rankings. (c) 2005 Elsevier Ltd. All rights reserved.
It is difficult if not impossible to derive a model to adequately describe the entire visual, cognitive and preference decision process of image quality evaluation and to replace it with objective alternatives. Even i...
详细信息
ISBN:
(纸本)0819456411
It is difficult if not impossible to derive a model to adequately describe the entire visual, cognitive and preference decision process of image quality evaluation and to replace it with objective alternatives. Even if some parts of the process can be modeled based on the current knowledge of the visual system, there is often a lack of sufficient data to support the modeling process. On the other hand, image quality evaluation is constantly required for those working on imaging devices and software. Measurements and surveys are regularly conducted to test a newer processing algorithm or a methodology. Large scale subjective measurement or surveys are often conducted before a product is released. Here we propose to combine the two processes and apply data mining techniques to achieve both goals of routine subjective testing and modeling. Specifically, we propose to use relational databases to log and store regular evaluation processes. When combined with web applications, the relational databases approach allow one to maximally improve the efficiency of designing, conducting, analyzing, and reporting test data. The collection of large amounts of data makes it possible to apply data mining techniques to discover knowledge and patterns in the data. Here we report one such system for printing quality evaluation and some theories on data mining including data visualization, observer mining, text comment mining, test case mining, model mining. We also present some preliminary results based on some of these techniques.
The research within the multicriteria classification field is mainly focused on the assignment of actions to pre-defined classes. Nevertheless the building of multicriteria categories remains a theoretical question st...
详细信息
The research within the multicriteria classification field is mainly focused on the assignment of actions to pre-defined classes. Nevertheless the building of multicriteria categories remains a theoretical question still not studied in detail. To tackle this problem, we propose an extension of the well-known k-means algorithm to the multicriteria framework. This extension relies on the definition of a multicriteria distance based on the preference structure defined by the decision maker. Thus, two alternatives will be similar if they are preferred, indifferent and incomparable to more or less the same actions. Armed with this multicriteria distance, we will be able to partition the set of alternatives into classes that are meaningful from a multicriteria perspective. Finally, the examples of the country risk problem and the diagnosis of firms will be treated to illustrate the applicability of this method. (C) 2003 Elsevier B.V. All rights reserved.
暂无评论