Application of Fuzzy Inference System (fis) to Criterion-referenced Assessment with a Case Study

In this paper, the use of fuzzy inference system in criterion-referenced assessment was investigated. The aim of criterion-referenced assessment (CRA) was to report student achievement with reference to their objective reference points. To ease the assessment as in common practice, scores were given to each item or task. In this paper, we focus on CRA that utilizes rubric. Rubric is an essential scoring tool for subjectivity assessment. Scores on different assessments tasks are added together and then projected or aggregated, usually linearly. Component score maybe weighted before being added to reflect their relative importance of each task. With regards to Fuzzy Inference System (FIS), it can be viewed as a method where a multiple-input model can be constructed in an easy manner, via a set of fuzzy rule base. In this paper, we present a novel FIS-based CRA model that provides an aggregated score as a measure of overall achievement where subjectivity is involved. Our proposed model allows relationship between the aggregated score and to score given to each single task or item to be modelled in an easy manner. It can be viewed as an alternative method how the score given to each single task or item can be aggregated, and an aggregated score is produced. The use of our model is investigated with a real case study relating student project assessment.