Pub Date : 2007-04-01DOI: 10.1109/MCDM.2007.369119
A. R. Podgaets, W. Ockels
This paper deals with assessing stability of optimal solutions. Two ways are considered: introducing stochastic stability based on Lyapunov's stability as constraints in a single-objective optimization problem and using it as a second objective. The problem from the field of wind energy is taken $optimization of electricity production with a novel wind power concept called Laddermill. Due to the multi-objectiveness of the second approach both problems are programmed with an algorithm based on a modification of Pareto-optimization. The main conclusion is that multi-objectiveness makes problem statement more transparent and also easier to implement and faster to compute which makes multi-objective formulation desirable for the class of robust optimal control problems
{"title":"Stability of Optimal Solutions: Multi- and Single-Objective Approaches","authors":"A. R. Podgaets, W. Ockels","doi":"10.1109/MCDM.2007.369119","DOIUrl":"https://doi.org/10.1109/MCDM.2007.369119","url":null,"abstract":"This paper deals with assessing stability of optimal solutions. Two ways are considered: introducing stochastic stability based on Lyapunov's stability as constraints in a single-objective optimization problem and using it as a second objective. The problem from the field of wind energy is taken $optimization of electricity production with a novel wind power concept called Laddermill. Due to the multi-objectiveness of the second approach both problems are programmed with an algorithm based on a modification of Pareto-optimization. The main conclusion is that multi-objectiveness makes problem statement more transparent and also easier to implement and faster to compute which makes multi-objective formulation desirable for the class of robust optimal control problems","PeriodicalId":306422,"journal":{"name":"2007 IEEE Symposium on Computational Intelligence in Multi-Criteria Decision-Making","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127204193","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2007-04-01DOI: 10.1109/MCDM.2007.369412
Elena Kornyshova, C. Salinesi
A large number of multicriteria techniques have been developed to deal with different kinds of problems. Whereas each technique has pros and cons and can be more or less useful depending on the situation, few approaches were proposed to guide the selection of a technique adapted to a given situation. This paper presents a state of the art of the existing approaches for selecting MCDM techniques. The state of the art is structured with a framework that guides the analysis of each selection approach according to its own characteristics, and to the characteristics of the MCDM techniques that the approach helps to select. The state of the art has two outcomes: a comparative analysis of the presented approaches, and a collection of requirements for a "good" selection approach
{"title":"MCDM Techniques Selection Approaches: State of the Art","authors":"Elena Kornyshova, C. Salinesi","doi":"10.1109/MCDM.2007.369412","DOIUrl":"https://doi.org/10.1109/MCDM.2007.369412","url":null,"abstract":"A large number of multicriteria techniques have been developed to deal with different kinds of problems. Whereas each technique has pros and cons and can be more or less useful depending on the situation, few approaches were proposed to guide the selection of a technique adapted to a given situation. This paper presents a state of the art of the existing approaches for selecting MCDM techniques. The state of the art is structured with a framework that guides the analysis of each selection approach according to its own characteristics, and to the characteristics of the MCDM techniques that the approach helps to select. The state of the art has two outcomes: a comparative analysis of the presented approaches, and a collection of requirements for a \"good\" selection approach","PeriodicalId":306422,"journal":{"name":"2007 IEEE Symposium on Computational Intelligence in Multi-Criteria Decision-Making","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129322211","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2007-04-01DOI: 10.1109/MCDM.2007.369438
Ankit Soni, Nees Jan van Eck, U. Kaymak
Visualization of textual data may reveal interesting properties regarding the information conveyed in a group of documents. In this paper, we study whether the structure revealed by a visualization method can be used as inputs for improved classifiers. In particular, we study whether the locations of news items on a concept map could be used as inputs for improving the prediction of stock price movements from the news. We propose a method based on information visualization and text classification for achieving this. We apply the proposed approach to the prediction of the stock price movements of companies within the oil and natural gas sector. In a case study, we show that our proposed approach performs better than a naive approach and a bag-of-words approach
{"title":"Prediction of Stock Price Movements Based on Concept Map Information","authors":"Ankit Soni, Nees Jan van Eck, U. Kaymak","doi":"10.1109/MCDM.2007.369438","DOIUrl":"https://doi.org/10.1109/MCDM.2007.369438","url":null,"abstract":"Visualization of textual data may reveal interesting properties regarding the information conveyed in a group of documents. In this paper, we study whether the structure revealed by a visualization method can be used as inputs for improved classifiers. In particular, we study whether the locations of news items on a concept map could be used as inputs for improving the prediction of stock price movements from the news. We propose a method based on information visualization and text classification for achieving this. We apply the proposed approach to the prediction of the stock price movements of companies within the oil and natural gas sector. In a case study, we show that our proposed approach performs better than a naive approach and a bag-of-words approach","PeriodicalId":306422,"journal":{"name":"2007 IEEE Symposium on Computational Intelligence in Multi-Criteria Decision-Making","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114810845","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2007-04-01DOI: 10.1109/MCDM.2007.369109
Harold Soh, Y. Ong, Mohamed Salahuddin, Terence Hung, Bu-Sung Lee
This paper presents a method of integrating computational intelligence with the operators used in evolutionary algorithms. We investigate approximation models of the objective function and its inverse and propose two simple algorithms that use these coupled approximators to optimize multi-objective functions. This method is a break from traditional approach used by standard cross-over and mutation operators, which only explore the objective space through "near-blind" manipulation of solutions in the parameter space. Fundamentally, our proposed intelligent operators use learned models of the coupling between the objective space and the parameter space to generate successively better solutions by extrapolating (or interpolating) from known solutions directly in the objective space. We term our implementation of the developed techniques as the coupled approximators evolutionary algorithm (CAEA). Promising empirical results with the DTLZ test suite prompt us to suggest several avenues for future research including combination with local search methods, incorporation of domain-knowledge and more efficient search algorithms.
{"title":"Playing in the Objective Space: Coupled Approximators for Multi-Objective Optimization","authors":"Harold Soh, Y. Ong, Mohamed Salahuddin, Terence Hung, Bu-Sung Lee","doi":"10.1109/MCDM.2007.369109","DOIUrl":"https://doi.org/10.1109/MCDM.2007.369109","url":null,"abstract":"This paper presents a method of integrating computational intelligence with the operators used in evolutionary algorithms. We investigate approximation models of the objective function and its inverse and propose two simple algorithms that use these coupled approximators to optimize multi-objective functions. This method is a break from traditional approach used by standard cross-over and mutation operators, which only explore the objective space through \"near-blind\" manipulation of solutions in the parameter space. Fundamentally, our proposed intelligent operators use learned models of the coupling between the objective space and the parameter space to generate successively better solutions by extrapolating (or interpolating) from known solutions directly in the objective space. We term our implementation of the developed techniques as the coupled approximators evolutionary algorithm (CAEA). Promising empirical results with the DTLZ test suite prompt us to suggest several avenues for future research including combination with local search methods, incorporation of domain-knowledge and more efficient search algorithms.","PeriodicalId":306422,"journal":{"name":"2007 IEEE Symposium on Computational Intelligence in Multi-Criteria Decision-Making","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126379416","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2007-04-01DOI: 10.1109/MCDM.2007.369413
L. Sánchez, Inés Couso, J. Casillas
Multicriteria genetic algorithms can produce fuzzy models with a good balance between their precision and their complexity. The accuracy of a model is usually measured by the mean squared error of its residual. When vague training data is used, the residual becomes a fuzzy number, and it is needed to optimize a combination of crisp and fuzzy objectives in order to learn balanced models. In this paper, we will extend the NSGA-II algorithm to this last case, and test it over a practical problem of causal modeling in marketing. Different setups of this algorithm are compared, and it is shown that the algorithm proposed here is able to improve the generalization properties of those models obtained from the defuzzified training data.
{"title":"Modeling Vague Data with Genetic Fuzzy Systems under a Combination of Crisp and Imprecise Criteria","authors":"L. Sánchez, Inés Couso, J. Casillas","doi":"10.1109/MCDM.2007.369413","DOIUrl":"https://doi.org/10.1109/MCDM.2007.369413","url":null,"abstract":"Multicriteria genetic algorithms can produce fuzzy models with a good balance between their precision and their complexity. The accuracy of a model is usually measured by the mean squared error of its residual. When vague training data is used, the residual becomes a fuzzy number, and it is needed to optimize a combination of crisp and fuzzy objectives in order to learn balanced models. In this paper, we will extend the NSGA-II algorithm to this last case, and test it over a practical problem of causal modeling in marketing. Different setups of this algorithm are compared, and it is shown that the algorithm proposed here is able to improve the generalization properties of those models obtained from the defuzzified training data.","PeriodicalId":306422,"journal":{"name":"2007 IEEE Symposium on Computational Intelligence in Multi-Criteria Decision-Making","volume":"111 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115852426","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2007-04-01DOI: 10.1109/MCDM.2007.369443
B. Chandrasekaran
Summary form only given. Rational decision-making is often modeled as choosing the alternative that maximizes utility for the decision maker. Over the last few decades, much evidence has been produced to demonstrate that human decision-making is subject to irrationalities, such as intransitivity and framing biases. The author seeks an explanation for how these irrationalities arise, specifically, how they relate to the intrinsic nature of problem solving as setting up and searching in problem spaces, guided by knowledge. Even in simple decision-making problems where the alternatives are small in number and clearly specified, problem solving is required to evaluate the alternatives. One source of the explanation of the irrationalities is the characteristic strategies that are used to evaluate the alternatives. When decision-making problems are complex, additional opportunities arise for sub-optimal decisions. The author also attempts to relate the traditional decision-making model of maximizing a single real-valued utility function to the common situation where decision-making is modeled as multi-criterial. The author ends with some ideas for how decision support system designers can use the analysis to reduce the opportunities for irrationalities
{"title":"Multi-criterial Decision-Making and the Cognitive Architecture of Problem Solving","authors":"B. Chandrasekaran","doi":"10.1109/MCDM.2007.369443","DOIUrl":"https://doi.org/10.1109/MCDM.2007.369443","url":null,"abstract":"Summary form only given. Rational decision-making is often modeled as choosing the alternative that maximizes utility for the decision maker. Over the last few decades, much evidence has been produced to demonstrate that human decision-making is subject to irrationalities, such as intransitivity and framing biases. The author seeks an explanation for how these irrationalities arise, specifically, how they relate to the intrinsic nature of problem solving as setting up and searching in problem spaces, guided by knowledge. Even in simple decision-making problems where the alternatives are small in number and clearly specified, problem solving is required to evaluate the alternatives. One source of the explanation of the irrationalities is the characteristic strategies that are used to evaluate the alternatives. When decision-making problems are complex, additional opportunities arise for sub-optimal decisions. The author also attempts to relate the traditional decision-making model of maximizing a single real-valued utility function to the common situation where decision-making is modeled as multi-criterial. The author ends with some ideas for how decision support system designers can use the analysis to reduce the opportunities for irrationalities","PeriodicalId":306422,"journal":{"name":"2007 IEEE Symposium on Computational Intelligence in Multi-Criteria Decision-Making","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128844358","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2007-04-01DOI: 10.1109/MCDM.2007.369445
H. Katagiri, I. Nishizaki, M. Sakawa, Kosuke Kato
This paper considers a two-level linear programming problem involving random variable coefficients to cope with hierarchical decision making problems under uncertainty. Two decision making models are provided to optimize the mean of the objective function value or to minimize the variance. It is shown that the original problem is transformed into a deterministic problem. The computational methods are constructed to obtain the Stackelberg solution to the two-level programming problems. An illustrative numerical example is provided to understand the geometrical properties of the solutions
{"title":"Stackelberg solutions to stochastic two-level linear programming problems","authors":"H. Katagiri, I. Nishizaki, M. Sakawa, Kosuke Kato","doi":"10.1109/MCDM.2007.369445","DOIUrl":"https://doi.org/10.1109/MCDM.2007.369445","url":null,"abstract":"This paper considers a two-level linear programming problem involving random variable coefficients to cope with hierarchical decision making problems under uncertainty. Two decision making models are provided to optimize the mean of the objective function value or to minimize the variance. It is shown that the original problem is transformed into a deterministic problem. The computational methods are constructed to obtain the Stackelberg solution to the two-level programming problems. An illustrative numerical example is provided to understand the geometrical properties of the solutions","PeriodicalId":306422,"journal":{"name":"2007 IEEE Symposium on Computational Intelligence in Multi-Criteria Decision-Making","volume":"316 5","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120879792","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2007-04-01DOI: 10.1109/MCDM.2007.369437
S. Yeung, K. Man, W. Chan
A design methodology of an ISM band folded patch antenna is presented in this paper. The antenna is designed for covering three ISM band at 2.400-2.480 GHz, 5.150-5.350 GHz, and 5.725-5.825 GHz, which is ideally suitable for short-range wireless applications. Jumping genes evolutionary algorithm is used for optimizing the antenna performance, and the non-dominated solution set of antenna dimensional parameters is obtained. Then, a fuzzy-based multiattribute decision method is designed for selecting the most suitable antenna solution in the non-dominated solution set. Finally, the selection solution is compared with the other solutions for demonstrating the effectiveness of the scheme
{"title":"ISM Band Antenna Design Based on Fuzzy MCDM Selection Technique","authors":"S. Yeung, K. Man, W. Chan","doi":"10.1109/MCDM.2007.369437","DOIUrl":"https://doi.org/10.1109/MCDM.2007.369437","url":null,"abstract":"A design methodology of an ISM band folded patch antenna is presented in this paper. The antenna is designed for covering three ISM band at 2.400-2.480 GHz, 5.150-5.350 GHz, and 5.725-5.825 GHz, which is ideally suitable for short-range wireless applications. Jumping genes evolutionary algorithm is used for optimizing the antenna performance, and the non-dominated solution set of antenna dimensional parameters is obtained. Then, a fuzzy-based multiattribute decision method is designed for selecting the most suitable antenna solution in the non-dominated solution set. Finally, the selection solution is compared with the other solutions for demonstrating the effectiveness of the scheme","PeriodicalId":306422,"journal":{"name":"2007 IEEE Symposium on Computational Intelligence in Multi-Criteria Decision-Making","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129860115","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2007-04-01DOI: 10.1109/MCDM.2007.369428
R. Subbu, P. Bonissone, Srinivas Bollapragada, K. Chalermkraivuth, N. Eklund, N. Iyer, R. Shah, Feng Xue, Weizhong Yan
Two industrial deployments of multi-criteria decision-making systems at General Electric are reviewed from the perspective of their multi-criteria decision-making component similarities and differences. The motivation is to present a framework for multi-criteria decision-making system development and deployment. The first deployment is a financial portfolio management system that integrates hybrid multi-objective optimization and interactive Pareto frontier decision-making techniques to optimally allocate financial assets while considering multiple measures of return and risk, and numerous regulatory constraints. The second deployment is a power plant management system that integrates predictive modeling based on neural networks, optimization based on multi-objective evolutionary algorithms, and automated decision-making based on Pareto frontier techniques. The integrated approach, embedded in a real-time plant optimization and control software environment dynamically optimizes emissions and efficiency while simultaneously meeting load demands and other operational constraints in a complex real-world power plant
{"title":"A Review of Two Industrial Deployments of Multi-criteria Decision-making Systems at General Electric","authors":"R. Subbu, P. Bonissone, Srinivas Bollapragada, K. Chalermkraivuth, N. Eklund, N. Iyer, R. Shah, Feng Xue, Weizhong Yan","doi":"10.1109/MCDM.2007.369428","DOIUrl":"https://doi.org/10.1109/MCDM.2007.369428","url":null,"abstract":"Two industrial deployments of multi-criteria decision-making systems at General Electric are reviewed from the perspective of their multi-criteria decision-making component similarities and differences. The motivation is to present a framework for multi-criteria decision-making system development and deployment. The first deployment is a financial portfolio management system that integrates hybrid multi-objective optimization and interactive Pareto frontier decision-making techniques to optimally allocate financial assets while considering multiple measures of return and risk, and numerous regulatory constraints. The second deployment is a power plant management system that integrates predictive modeling based on neural networks, optimization based on multi-objective evolutionary algorithms, and automated decision-making based on Pareto frontier techniques. The integrated approach, embedded in a real-time plant optimization and control software environment dynamically optimizes emissions and efficiency while simultaneously meeting load demands and other operational constraints in a complex real-world power plant","PeriodicalId":306422,"journal":{"name":"2007 IEEE Symposium on Computational Intelligence in Multi-Criteria Decision-Making","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130898931","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2007-04-01DOI: 10.1109/MCDM.2007.369118
S. Kulturel-Konak, D. Coit
In this paper, a new methodology is presented to solve multi-objective system redundancy allocation problems. A tabu search meta-heuristic approach is used to initially find the entire Pareto set, and then a Monte-Carlo simulation provides a decision maker with a pruned set of Pareto solutions based on decision maker's predefined objective function preferences. We are aiming to create a bridge between Pareto optimality and single solution approaches
{"title":"Determination of Pruned Pareto Sets for the Multi-Objective System Redundancy Allocation Problem","authors":"S. Kulturel-Konak, D. Coit","doi":"10.1109/MCDM.2007.369118","DOIUrl":"https://doi.org/10.1109/MCDM.2007.369118","url":null,"abstract":"In this paper, a new methodology is presented to solve multi-objective system redundancy allocation problems. A tabu search meta-heuristic approach is used to initially find the entire Pareto set, and then a Monte-Carlo simulation provides a decision maker with a pruned set of Pareto solutions based on decision maker's predefined objective function preferences. We are aiming to create a bridge between Pareto optimality and single solution approaches","PeriodicalId":306422,"journal":{"name":"2007 IEEE Symposium on Computational Intelligence in Multi-Criteria Decision-Making","volume":"92 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131698363","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：