This paper is concerned with the use of Dempster-Shafer theory in `fusion' classifiers. We argue that the use of predictive accuracy for basic probability assignments can improve the overall system performance when compared to `traditional' mass assignment techniques. We demonstrate the effectiveness of this approach in a case study involving the detection of static thermostatic valve faults in a diesel engine cooling system.

The World Wide Web has been discovered by market researchers. Useful information about new markets, market volumes, or the development of existing markets can be found and compiled from Web documents. This paper focuses on the task of market forecast summarization and how it can be automated by the combination of Web-based information retrieval and information extraction techniques. Market forecast summarization is essential for investment strategists who base their investment decisions on predicted market developments. Against this background, we break down the complex analysis of market developments into three specific questions concerned with turnover estimation. The contributions of the paper relate to technology for automatically collecting and analyzing documents to answer these questions: focused search, document type assessment and filtering, time extraction, shallow parsing, and plausibility analysis. We have developed a prototype that operationalizes the technology and conducted a case study from the field of new technology assessment in order to demonstrate the ideas.

Abstract not found