Search

In this study, we developed a visualization tool that shows learners΄ interactive activities graphically during computer-supported collaborative learning (CSCL). The tool helps teachers to monitor and evaluate the interac tion activities among students, and thus it makes it easier to develop more ef fective instructional design for CSCL. For experiments, we used a web-based discussion group of 112 students. We investigated the effects of visualization of interactions on web discussion CSCL. Also, in lesson practice with this tool, we verified the effects through questionnaire and interviews. Our result show that the visualization tool provides a teacher with patterns of collaborative activities very clearly and insights of how to promote students΄ interactions more effi ciently. [ABSTRACT FROM AUTHOR]

Symbolic rules play an important role in HIV-1 protease cleavage site prediction. Recently, some studies have done on extraction of the prediction rules with some success. In this paper, we demonstrated a decompositional approach for rule extraction from nonlinear neural networks. We also compared the prediction rules to the ones extracted by other approaches and methods. Empirical experiments are also shown. [ABSTRACT FROM AUTHOR]

A new method is proposed for generating if-then rules to predict peptide binding to class I MHC proteins, from the amino acid sequence of any protein with known binders and non-binders. In this paper, we present an approach based on artificial neural networks (ANN) and knowledge-based genetic algorithm (KBGA) to predict the binding of peptides to MHC class I molecules. Our method includes rule extraction from a trained neural network and then enhancing the extracted rules by genetic evolution. Experimental results show that the method could generate new rules for MHC class I binding peptides prediction. [ABSTRACT FROM AUTHOR]

In this paper, we demonstrate that the machine learning approach of rule extraction from a trained neural network can be successfully applied to SARS-coronavirus cleavage site analysis. The extracted rules predict cleavage sites better than consensus patterns. Empirical experiments are also shown. [ABSTRACT FROM AUTHOR]

Cleavage site prediction is an important issue in molecular biology. We present a new method that generates prediction rules for SARS-CoV protease cleavage sites. Our method includes rule extraction from a trained neural network and then enhancing the extracted rules by genetic evolution to improve its quality. Experimental results show that the method could generate new rules for cleavage site prediction, which are more general and accurate than consensus patterns. [ABSTRACT FROM AUTHOR]