Abstract
This paper describes the study on example selection in regression problems using mu-SVM (Support Vector Machine) linear as prediction algorithm. The motivation case is a study done on real data for a problem of bus trip time prediction. In this study we use three different training sets: all the examples, examples from past days similar to the day where prediction is needed, and examples selected by a CART regression tree. Then, we verify if the CART based example selection approach is appropriate on different regression data sets. The experimental results obtained are promising.

Abstract
In this article is proposed a simple method for estimating or characterize the behaviour of complex systems, in particular when these are being studied throughout simulation. Usual ways of treating the complex output data obtained from the activity (real or simulated) of such a kind of systems, which in many cases people classify and analyse along the time domain, usually the most complex perspective, is herein substituted by the idea of representing such data in the frequency domain, somehow like what is commonly done in Fourier Analysis and in Quantum Mechanics. This is expected to give the analyst a more holistic perspective on the system's behaviour, as well as letting him/her choose almost freely the complex states in which such behaviour is to be projected. We hope this will lead to simpler processes in characterizing complex systems.

Abstract
The nature of warehouse design requires the manipulation of large amounts of data and is often an iterative process that forces the designer to go through the different design phases several times before reaching the final solution. This suggests an integrated computer environment that can give support to the user during all the design phases. The need for a flexible tool, easier to use, lead to the development of a Decision Support System: AWARD (Advanced WARehouse Design). This paper presents further developments of the DSS and shows a successful example of application of the new functionalities: a simulation model of a full automated warehouse developed for EFACEC, a large Portuguese company in the warehouse design, building and consultancy business.

Abstract
A simulation model of a full automated warehouse was custom developed for EFACEC, a large Portuguese company in the warehouse design, building and consultancy business. EFACEC was preparing a proposal for a client and they needed the model to evaluate and test their options. They also wanted to use the model as a marketing tool to gain the contract. Two persons with previous experience in simulation formed the development team. The model was developed in four months with full time dedication, but was inflexible to support significant changes after EFACEC won the bid. Furthermore, the increasing demand for warehouse design made the development of specific hard coded simulation models for EFACEC inadequate. The need for a flexible tool, easier to use, lead to the development of a Decision Support System: AWARD (Advanced WARehouse Design).

Abstract
In this work, a maintenance float system is considered. Equipments in workstation are submitted to overhauls carried out at regular time intervals. A mathematical model has been constructed to find out the best combination of three parameters: the number of standby units, R, the number of maintenance crews in the maintenance centre, L and the time between overhauls, T. The strategy to construct the model involved: the development of differential equations in order to determine system state probabilities; the definition of an operating cycle; the calculation of the cycle duration and respective total maintenance system cost incurred; and the utilization of a search method to find out the combination of parameters that minimizes the total cost of a specific system.

Abstract
The GRMODGRASP, a new algorithm for the container-loading problem (CLP) based on the greedy randomized adaptive search procedure (GRASP) approach, is discussed. Based on a wall-building, constructive heuristic, it can achieve high levels of cargo stability without compromising the container's volume use. The algorithm builds a solution, and then it improves the solution with a local-search algorithm. If it finds a better solution, this new solution replaces the old and a new neighborhood is built around it. The algorithm uses a first better strategy when more than one better solution exists.