A decision support tool coupling a causal model and a multi-objective genetic algorithm

Abstract

A significant class of decision making problems consists of choosing actions, to be carried out simultaneously, in order to achieve a trade-off between different objectives. When such decisions concern complex systems, decision support tools including formal methods of reasoning and probabilistic models are of noteworthy helpfulness. These models are often built through learning procedures, based on an available knowledge base. Nevertheless, in many fields of application (e.g. when dealing with complex political, economic and social systems), it is frequently not possible to determine the model automatically, and this must then largely be derived from the opinions and value judgements expressed by domain experts. The BayMODE decision support tool (Bayesian Multi Objective Decision Environment), which we describe in this paper, operates precisely in such contexts. The principal component of the program is a multi-objective Decision Network, where actions are executed simultaneously. If the noisy-OR assumptions are applicable, such a the model has a reasonably small number of parameters, even when actions are represented as non-binary variables. This makes the model building procedure accessible and easy. Moreover, BayMODE operates with a multi-objective approach, which provides the decision maker with a set of non-dominated solutions, computed using a multi-objective genetic algorithm. © Springer Science+Business Media, LLC 2007

Thermo-economic modeling and optimization of an irreversible solar-driven heat engine

“…The objective functions in the performed optimization, and the limitations which have been used, are identified by Eqs. (16), (18) and (20) and Eqs. (21)-(25) respectively.…”

“…Multi-objective optimization is a robust approach to solve different engineering problems at different research fields [14][15][16].…”

Optimization performance and thermodynamic analysis of an irreversible nano scale Brayton cycle operating with Maxwell–Boltzmann gas

“…Multi objective optimization is a great asset for solving engineering problems [36][37][38]. Özyer and colleagues [36] evolved an intellectual model for prospect calculation by using of evolutionary algorithms.…”

“…The multi-objective optimization is performed by various engineering issues such as vehicle routing problems with Time Windows [37]. Blecic and colleagues [38] illustrated a decision support system called Bay MODE on the basis of multi objective optimization and Bayesian analysis.…”

Multi-objective optimization of GPU3 Stirling engine using third order analysis

“…Evolutionary algorithms (EA) were applied in an attempt to stochastically solve problems of this generic class during the 18th century [13]. Inquiring a set of solutions, of which each satisfies the objectives at an acceptable level without being overcomed by any other solution, is a reasonable solving method to a multi-objective quandary [14].…”