For test-sheet composition systems, it is important to adaptively compose test sheets with\r\ndiverse conceptual scopes, discrimination and difficulty degrees to meet various assessment\r\nrequirements during real learning situations. Computation time and item exposure rate also\r\ninfluence performance and item bank security. Therefore, this study proposes an Adaptive Test\r\nSheet Generation ATSG mechanism, where a Candidate Item Selection Strategy adaptively\r\ndetermines candidate test items and conceptual granularities according to desired conceptual\r\nscopes, and an Aggregate Objective Function applies Genetic Algorithm GA to figure out the\r\napproximate solution of mixed integer programming problem for the test-sheet composition.\r\nExperimental results show that the ATSG mechanism can efficiently, precisely generate test\r\nsheets to meet the various assessment requirements than existing ones. Furthermore, according\r\nto experimental finding, Fractal Time Series approach can be applied to analyze the self-similarity\r\ncharacteristics of GA�s fitness scores for improving the quality of the test-sheet composition in the\r\nnear future.
Loading....