The advanced information technologies have made it possible for individuals to carry out cooperative learning efficiently and effectively from anywhere and at any time. To capitalize on the individual need and address the issues associated with the late entry into the e-learning area, it has great significance to study the service mechanism of CSCL on e-learning service and e-learning service computing modeling. This paper proposes an e-learning service model supporting for the life-cycle process management. The proposed model is developed by considering the learner's behaviours during e-learning services, the scheduling policies, and the monitoring mechanism of learning activities. Business process modeling for e-learning services can be taken according to the study ordering of the knowledge points by using workflow modeling technology and process enactment mechanism. The overall life-cycle process management of knowledge is addressed by combining knowledge product modeling, knowledge resource modeling, and credit polices for member selection in research team by considering trust value of learners, advisers and providers in e-learning services. The proposed method can be used for supporting the sustainable development of e-learning services from planning and design, organizing e-learning process, maintenance of the e-learning process, to process improvement, as well as to support learners and advisers to effectively complete innovative team study and complex computation study. Lastly, an extended topic map tool has been developed by adding a knowledge requirement level and an information extraction tool to validate the proposed methodology. These tools can used to guide learners to concentrate on the required knowledge topics and drive knowledge providers to redevelop outdated knowledge hierarchy.

No abstract

Service-Oriented Architecture (SOA) promotes the combination of workflow and service composition technology, and it provides important technical supports for cross-organizational workflow applications. This paper proposes an analysis and prediction model based on time series using Particle Swarm Optimization based Back Propagation Neural Network (PSO-BPNN) model, to predict the dynamic performance of workflow systems. When the predicted value out of the preset range, we analyze the issues according to data of Quality of Service (QoS) detected at runtime, to find why cause service performance failure, which suggests more suitable recovery strategies for service composition. The results of simulation experiment have validated the effectiveness of the proposed approach.

No abstract

No abstract