In this paper we provide experimental results and extensions to our previous theoretical findings concerning the combination of forecasts that have been diversified by three different methods: with parameters learned at different data aggregation levels, by thick modeling and by the use of...

The parameter in negative correlation learning (NC) controls the degree of co-operation between individual networks. This paper looks at the way the choice of in the NC algorithm affects the complexity of the function NC can fit, and shows that it acts as a complexity control allowing smooth...

Estimation of the generalization ability of a predictive model is an important issue, as it indicates expected performance on previously unseen data and is also used for model selection. Currently used generalization error estimation procedures like cross–validation (CV) or bootstrap are...

There are no algorithms that generally perform better or worse than random when looking at all possible data sets according to the no-free-lunch theorem. A specific forecasting method will hence naturally have different performances in different empirical studies. This makes it impossible to...

Process modelling is gaining increasing acceptance by software engineers as a useful discipline to facilitate both process understanding and improvement activities. This position paper builds upon previous work reported at the 1997 ICSE workshop on process models and empirical studies of...

Over the years, there has been much interest in modelling processes. Processes include those associated with the development of software and those business processes that make use of software systems. Recent research in Systems Engineering for Business Process Change highlights the importance of...

By providing a route from model to architecture, Model Driven Architecture (MDA) promises, among other things, to narrow the gap between business users and software developers. That is, the approach is intended to involve stakeholders in modelling, so that, by transformation from Computationally...

A system has been developed that analyses the emotional content of web pages. Text is extracted from an embedded Internet browser and sent to a text-to-emotion engine that identifies the emotive content. An experiment was conducted that examines the effect the emotional content of the web page...

This article reports on the latest developments of our Emotional Stock Analyser application. The original application automatically analyses the text that is input by the user, using a text-to-emotion engine that identifies the emotive content. The whole text of newspaper articles about the...

One of the motivations for a model driven approach to software development is to increase the involvement for a range of stakeholders in the requirements phases. This inevitably leads to a greater diversity of roles being involved in the production of models, and one of the issues with such...