DECISION SUPPORT COMPONENT IN INTELLIGENT E-LEARNING SYSTEMS

1. DECISION SUPPORT COMPONENT IN INTELLIGENT E-LEARNING SYSTEMS Enn Õunapuu Estonia enn@cc.ttu.ee

2. Content • Outlines • Web service • Service agent • Service oriented architecture • Instructional support system architecture • Decision support component • Conclusions • Questions

3. Outlines This presentation describes a solution to the educational systems creation: a architecture and methodology of educational system creation based on web services, service agents and decision support component

4. Web service • Software services are discrete units of application logic that expose message-based interfaces suitable for being accessed across a network. • Interoperability www.ws-i.org • Basic profile standards • SOAP • WSDL • UDDI

5. Service agent A service agent is a service that helps you work with other services. Often supplied by the provider of the target service, the agent runs topologically close to the application consuming the service. It helps both to prepare requests to a service and to interpret responses from the service.

6. Service oriented architecture • Service oriented architecture is one where application is cut on the pieces called services • Each service is invoked by messaging • The semantics of the operations are around business functions

7. System architecture

8. Instructional support system architecture

9. Decision support component Our goal is to find best web service among multiple offerings. Decision support component represent a possible solution for the problem. In this component the multi-criteria analysis methods are implemented. In this approach, we consider service execution statistics, service availability statistics and consumer preferences as input for the multi-criteria analysis techniques.

10. Multi-criteria analysis • A standard feature of multi-criteria analysis is a performance matrix, or consequence table, in which each row describes an option and each column describes the performance of the options against each criterion. The individual performance assessments are often numerical, but may also be expressed as 'bullet point' scores, or colour coding.

11. Methods of multi-criteria analysis • Linear additive model • The Analytical Hierarchy Process • Outranking method

12. Linear additive model • The linear model shows how an option's values on the many criteria can be combined into one overall value. This is done by multiplying the value score on each criterion by the weight of that criterion, and then adding all those weighted scores together.

13. The Analytical Hierarchy Process • The Analytic Hierarchy Process (AHP) also develops a linear additive model, but, in its standard format, uses procedures for deriving the weights and the scores achieved by alternatives which are based, respectively, on pair wise comparisons between criteria and between options.

14. Outranking method • The methods that have evolved all use outranking to seek to eliminate alternatives that are, in a particular sense, 'dominated'. Dominance within the outranking frame of reference uses weights to give more influence to some criteria than others.

15. Results of using multi-criteria methods • For the choosing the best option all mentioned methods are more all less equals • For the practical point of view the combinition of methods gets best results • The data are more important than methods

16. Conclusions • Web services and Service agent based interoperability enables the creation of the scalable and flexible global educational systems • To create global educational systems we need a modular suite of specifications that enables enterprises of any size and in any geographical location to conduct interactions over the Internet. • IMS Global learning Consortium offers such specifications • Multi-criteria analysis methods makes possible to make our systems more intelligent

17. Questions??