Browsing by Issue Date, starting with "2005-11"
Now showing 1 - 3 of 3
Results Per Page
Sort Options
- Simple Geometric Approach of Identification and Control Using Floating Basis Vectors for RepresentationPublication . Tar, József K.; Rudas, Imre J.; Rontó, Miklós; Tenreiro Machado, J. A.As a plausible alternative of certain sophisticated soft computing approaches trying to identify complete and static system models, a simple adaptive controller is outlined that creates only a temporal model. This model can be built up and maintained step-by-step on the basis of slowly fading information by the use of simple updating rules consisting of finite algebraic steps of lucid geometric interpretation. The method may be used for filling in the lookup tables or rule bases of the above representations experimentally. The method is tested by the use of a simple dynamic system as a typical paradigm via simulation.
- A Memetic Algorithm for Logic Circuit DesignPublication . Reis, Cecília; Tenreiro Machado, J. A.; Cunha, J. BoaventuraMemetic Algorithms (MAs) have shown to be very effective in solving many hard combinatorial optimization problems. In this perspective, this paper presents a MA for combinational logic circuits synthesis. The proposed MA combines a Genetic Algorithm (GA) for digital circuit design with the gate type local search (GTLS). The combination of a global and a local search is a strategy used by many successful hybrid optimization approaches. The main idea is to apply a local refinement to an Evolutionary Algorithm (EA) in order to improve the fitness of the individuals in the population. The obtained results indicate that the MA reduces the number of generations required to reach the solutions and its standard deviation while improves the final fitness function.
- Statistical modelling of dual-arm robotic systemsPublication . Tenreiro Machado, J. A.; Galhano, Alexandra; Ferreira, N. M.; Cunha, J. BoaventuraThe article presents a new approach to the analysis and design of two-arm robotic systems. Usually, system descriptions are based on a set of differential equations which require laborious computations. This motivates the need of alternative models based on other mathematical concepts. The proposed statistical method gives clear guidelines towards the robotic systems analysis and development.