Use Partition Algorithms for Clustering and Cognition Diagnosis on Concepts of Examination for Registered Nurse.

Purpose: The purpose of this study is to provide individualized concept structure analysis based on the comparisons with concept structure of expert. Fuzzy clustering can distinguish characteristics of concept structures on assessment of examination for registered nurse. Design/methodology/approach: This study adds a regulating factor of covariance matrix to each class in objective function and deletes the constraint of the determinant of covariance matrices. The fuzzy covariance matrices in the Mahalanobis distance with recursive process iteratively can be directly derived by minimizing the objective function and can overcome the drawback of Euclidean distance. Hence, we could extend the distance measure to alternative distance. Findings: To get a more stable partition clustering algorithm, this study replaces all the covariance matrices with the same common covariance matrix and solves the problem of the singular problem for the inverse covariance matrix. Each cluster of data can easily describe features of knowledge structures. Manage the knowledge structures of assessment of examination for registered nurse to construct the model of features in the pattern recognition completely. Practical implications: Provide the empirical data for concepts of Professional and Technical Examination for Registered Nurse from junior college students of learning deficiencies. The results show that students with different response patterns and total score own varied concept structures. Originality/value: Based on the findings and results, some suggestions and recommendations for future research are provided. Integrated algorithm could improve the assessment methodology of cognition diagnosis and manage the knowledge structures of Professional and Technical Examination for Registered Nurse's concepts easily. [ABSTRACT FROM AUTHOR]