Abstract
The technique of genetic algorithms is proposed as a means of auto-tuning PID controllers. The technique revolves firstly using on-line data and the genetic algorithm to identify a model of the process. Then the identified model, the genetic algorithm and simulation methods, are used to off-line tune the PID controller, so as to minimize a time-domain based cost function. Finally, the genetically tuned controller is implemented on-line on the real process. The results of the genetic auto-tuner are illustrated by auto-tuning a PID controller on a laboratory heat exchanger, and comparing the genetic auto-tuning technique with the Astrom-relay auto-tuning technique.

Abstract

Abstract
Diffusion of innovation is a research topic which has been subject to several works in the last years. The diffusion of innovation theory aims to explain how new ideas and practices are disseminated between the members of a social system. A significant part of the existing models are based on the use of parameters which determine the process of innovation adoption, and rely on simple mathematical functions centered in the observation and description of diffusion patterns. This models enable a more explicit diffusion process study, but its use involves the estimation of diffusion coefficients, usually obtained from historical data or chronological series. This raises some problems, for instance when there is no data or it is insufficient. This paper proposes the use of evolutionary computation is an alternative approach for the simulation of innovation diffusion within organizations, in order to overcome some of the problems inherent to the existing models.

Abstract
The scheduling problem is considered in complexity theory as a NP-hard combinatorial optimization problem. Meta-heuristics proved to be very useful in the resolution of this class of problems. However, these techniques require parameter tuning which is a very hard task to perform. A Case-based Reasoning module is proposed in order to solve the parameter tuning problem in a Multi-Agent Scheduling System. A computational study is performed in order to evaluate the proposed CBR module performance.

Abstract
This paper proposes a new algorithm which promotes well distributed non-dominated fronts in the parameters space when a single-objective function is optimized. This algorithm is based on e-dominance concept and maxmin sorting scheme. Besides that, the paper also presents the results of the algorithm when it is used in the automated synthesis of optimum performance CMOS radio-frequency and microwave binary-weighted differential switched capacitor arrays (RFDSCAs). The genetic synthesis tool optimizes a fitness function which is based on the performance parameter of the RFDSCAs. To validate the proposed design methodology, a CMOS RFDSCA is synthesized, using a 0.25 µm BiCMOS technology.

Abstract
This work presents a procedure to automate the design of Si-integrated radio frequency (RF) discrete tuning varactors (RFDTVs). The synthesis method, which is based on evolutionary algorithms, searches for optimum performance RF switched capacitor array circuits that fulfill the design restrictions. The design algorithm uses the c-dominance concept and the maximin sorting scheme to provide a set of different Solutions (circuits) well distributed along an optimal front in the parameter space (circuit size and component values). Since all the solutions present the same performance, the designer call Select the circuit that is best suited to be implemented in a particular integration technology. To assess the performance of the synthesis procedure, several RFDTV circuits, provided by the algorithm, were designed and simulated rising a 0.18 mu m CMOS technology and the Cadence Virtuoso Design Platform. The comparisons between the algorithm and circuit; simulation results show that they are very close, pointing out that; the proposed design procedure is a powerful design tool.