Data-driven fuzzy rule generation and its application for student academic performance evaluation

Khairul Rasmani, Qiang Shen

Research output: Contribution to journalArticlepeer-review

62 Citations (SciVal)
229 Downloads (Pure)

Abstract

Several approaches using fuzzy techniques have been proposed to provide a practical method for evaluating student academic performance. However, these approaches are largely based on expert opinions and are difficult to explore and utilize valuable information embedded in collected data. This paper proposes a new method for evaluating student academic performance based on data-driven fuzzy rule induction. A suitable fuzzy inference mechanism and associated Rule Induction Algorithm is given. The new method has been applied to perform Criterion-Referenced Evaluation (CRE) and comparisons are made with typical existing methods, revealing significant advantages of the present work. The new method has also been applied to perform Norm-Referenced Evaluation (NRE), demonstrating its potential as an extended method of evaluation that can produce new and informative scores based on information gathered from data.
Original languageEnglish
Pages (from-to)305-319
Number of pages15
JournalApplied Intelligence
Volume25
Issue number3
DOIs
Publication statusPublished - 01 Dec 2006

Keywords

  • data-driven learning
  • fuzzy rule induction
  • student performance evaluation

Fingerprint

Dive into the research topics of 'Data-driven fuzzy rule generation and its application for student academic performance evaluation'. Together they form a unique fingerprint.

Cite this