Selecting the best-suited machine-learning classiication algorithms for data-mining tasks is a meta-learning activity of the METAL project. Two alternative approaches for providing a user with anàdvi-sor'-a ranked preference list of algorithms-have been implemented. In this paper results of experiments designed to test thoroughly the consistency of these… (More)
The main goal of the ESPRIT METAL project is to use meta-learning to develop an incrementally adaptable assistant system to provide user-support in machine learning and data mining. Meta data consists of performance outcomes of ML algorithms on known datasets. Using new models of data envelopment analysis to deal with multiple criteria, an ordered ranking… (More)
**The contents of the study do not necessarily reflect the opinion or position of the European Commission. Thanks go to the IHS project team members Niki Graf and Hermann Kuschej, and to the many correspondents at professional bodies, member states' statistical offices and Eurostat.
The study quantifies the amount of water embodied in Austrian imports of selected agricultural products. These imports are analysed by a dynamic model that is based on the water footprint concept. The model quantifies the water savings potential using a database including more than 200 countries and regions. Austria could save up to 28% of the water… (More)
EXTENDED ABSTRACT In a simple growth model we explore the current and future growth effects of the population structure. Regional growth in 227 regions of 6 countries in central Europe (see Figure 1.0) is explored as how they depend on the young and old dependency ratio. The young dependency ratio (YDR) is defined as ratio of the less than 20 years old and… (More)