A Chapman & Hall book

Includes bibliographical references (pages 193-201) and index

ch. 1. Distributed knowledge discovery : an overview -- ch. 2. Service-oriented computing for data analysis -- ch. 3. Designing services for distributed knowledge discovery -- ch. 4. Workflows of services for data analysis -- ch. 5. Services and grids : the knowledge grid -- ch. 6. Mining tasks as services : the case of Weka4WS -- ch. 7. How services can support mobile data mining -- ch. 8. Knowledge discovery applications -- ch. 9. Sketching the future pervasive data services

Preface Data analysis techniques and services are needed to mine the massive amount of data available and to extract useful knowledge from it. The service-oriented architecture (SOA) is used today as a model to develop software systems as a collection of services that are units of functionality and are interoperable in an open programming scenario. Service-oriented architectures can offer tools, techniques, and environments to support analysis, inference, and discovery processes over large data repositories available in many scientific and business areas. Knowledge discovery services, based on the availability of huge operation and application data and on the exploitation of data mining techniques, support and enable largescale knowledge discovery applications on service-oriented architectures such as Web servers, Grids, and Cloud computing platforms. This new approach can be referred to as service-oriented knowledge discovery. It addresses issues related to distributed knowledge discovery algorithms, data services composition, data and knowledge integration, and service-oriented data mining workflow, which provide the main components for extracting useful knowledge from the often unmanageable data volumes available today from many sources. This is done by exploiting data mining and machine learning distributed models and techniques in service-oriented infrastructures