Abstract
The values selected for the free parameters of Artificial Neural Networks usually have a high impact on their performance. As a result, several works investigate the use of optimization techniques, mainly metaheuristics, for the selection of values related to the network architecture, like number of hidden neurons, number of hidden layers, activation function, and to the learning algorithm, like learning rate, momentum coefficient, etc. A large number of these works use Genetic Algorithms for parameter optimization. Lately, other bioinspired optimization techniques, like Ant Colony optimization, Particle Swarm Optimization, among others, have been successfully used. Although bioinspired optimization techniques have been successfully adopted to tune neural networks parameter values, little is known about the relation between the quality of the estimates of the fitness of a solution used during the search process and the quality of the solution obtained by the optimization method. In this paper, we describe an empirical study on this issue. To focus our analysis, we restricted the datasets to the domain of gene expression analysis. Our results indicate that, although the computational power saved by using simpler estimation methods can be used to increase the number of solutions tested in the search process, the use of accurate estimates to guide that search is the most important factor to obtain good solutions.

Abstract
Recent advances in wireless networks and mobile devices have brought about new scenes for the provision of services to end-users. Besides traditional services, new ones may be provided that transparently adjust and adapt to the user context. The user would have more choice and flexibility if, besides using the services, he could also compose his own services in an ad-hoe way. This paper presents iCas, an architecture to create context-aware services on the fly and discusses its main components. Also an application scenario is briefly described.

Abstract
A virtual enterprise (VE) is a temporary organization that pools the core competencies of its member enterprises and exploits fast changing market opportunities. The success of such an organization is strongly dependent on its composition, and the selection of partners becomes therefore a crucial issue. This problem is particularly difficult because of the uncertainties related to information, market dynamics, customer expectations and technology speed up. In this paper we propose an integrated approach to rank alternative VE configurations in business environments with uncertainty, using an extension of the TOPSIS method for fuzzy data, improved through the use of a stochastic multiobjective tabu search meta-heuristic. Preliminary computational results clearly demonstrate the potential of this approach for practical application.

Abstract

Abstract
The widespread usage of technology for service provision to customers has created a new and challenging environment for the design of interactive systems, with the emergence of technology enabled multi-channel services. Requirements engineers involved in the design of such service systems must actively work together with interaction designers and service managers to better integrate customer service experience and technology components, requiring unifying methods and tools within the emerging field of service science management and engineering. This paper proposes the service experience blueprint (SEB), a multidisciplinary method for the design of technology enabled multi-channel service systems and illustrates its application in two examples of redesign of banking services that involved an extensive study with more than 4,000 bank customers. The SEB method is based on concepts and tools from RE and interaction design, such as goal-oriented analysis and conceptual modeling, but also uses methods developed in the service and marketing fields, such as service blueprinting. SEB brings marketing research methods to the requirements process, as they can provide a useful contribution for the elicitation of customer experience requirements in service environments. By bringing together goal-oriented modeling and use case modeling from requirements engineering, with service blueprinting from service design, the SEB method contributes to creating a shared understanding and a unifying language to better support the design of new technology enabled multi-channel service systems, where technology and service issues are deeply intertwined.

Abstract
As companies employ a larger number of models, the problem of algorithm (and parameter) selection is becoming increasingly important. Two approaches to obtain empirical knowledge that is useful for that purpose are empirical studies and metalearning. However, most empirical (meta)knowledge is obtained from a, relatively small set, of datasets. In this paper, we propose a method to obtain a large number of datasets which is based on a simple transformation of existing datasets, referred to as datasetoids. We test our approach on the problem of using metalearning to predict when to prune decision trees. The results show significant; improvement when using datasetoids. Additionally, we identify a number of potential anomalies in the generated datasetoids and propose methods to solve them.