A Survey of Multiobjective Evolutionary Algorithms for Data Mining: Part I

Testing vision-based control systems using learnable evolutionary algorithms

“…In the context of machine learning, multi-objective optimization algorithms have been used to improve supervised learning techniques such as SVM, artificial neural networks and decision trees [26,28] where the aim is to improve prediction accuracy of the resulting classifiers. Our work is related to software testing and uses decision trees to guide the search-based generation of tests faster towards the most critical regions.…”

A Hybrid Multi-objective Evolutionary Approach for Optimal Path Planning of a Hexapod Robot

“…The potential energy of the system will contribute to size the necessary work by the actuators and friction effects in the joints can be assumed as negligible as compared to the actions of actuators and brakes. Thus, we have considered convenient to use the work Wact done by the actuators in the first phase of the path motion as an optimality criterion for optimal path generation as given by the expression (13) in which tk is the k-th actuator torque; ̇ is the k-th shaft angular velocity of the actuator; and tk is the time coordinate value delimiting the first phase of path motion with increasing speed of the k-th actuator.…”

“…In general, MOEAs differ on the fitness assignment method, but most of them are part of a family, called Pareto-based, which use the Pareto dominance concept as the foundation to discriminate solutions to guide their search [10]. For examples, the interested reader can refer to several surveys of multi-objective optimization methods, such as for engineering [11][12], for data mining [13][14][15], for bioinformatics [16], for portfolio and other financial problems [17]. A previous attempt of using an MOEA to optimize the design of a leg mechanism has been presented in [18], where the authors compared the performance with that of an earlier study and in all cases the superiority and flexibility of the EMO approach was demonstrated.…”

DocGenealogy – Visualizing the doctoral advisors and mentors genealogic tree

“…The techniques for mining knowledge from different kinds of databases, including relational, transactional, object-oriented, spatial and active databases, as well as global information systems were also examined by them in addition to potential data mining applications and some research issues. (LIAO et al, 2012) Recently, applications of evolutionary algorithms have been found to be particularly useful for automatic processing of large quantities of raw noisy data for optimal parameter setting and to discover significant and meaningful information (MUKHOPADHYAY et al, 2014). Many real-life data mining problems involve multiple conflicting measures of performance, or objectives, which need to be optimized simultaneously.…”