论文信息 - Evaluation of Fuzzy Intelligent Learning Systems

Evaluation of Fuzzy Intelligent Learning Systems

The evaluation of Intelligent Learning Systems yielding complex models as formal representations of student’s behavior is still an open problem. Standards so far do not provide suitable methods for the evaluation of competence. The paper discusses some guidelines according to the APA Standards spirit and apply them to the evaluation of FINANCE, a system derived from NEOCAMPUS2, a long effort project, devoted to coaching and the acceleration of the transfer of novices into experts. Results show its high reliability and important consequential and evidential validity.

Mustapha El Alami | Fernando De Arriaga | Araceli Arriaga

[1] Ashok Patel,et al. A Classification of Evaluation Methods for Intelligent Tutoring Systems , 1999, Software-Ergonomie.

[2] Stephen B. Dunbar,et al. Complex, Performance-Based Assessment: Expectations and Validation Criteria , 1991 .

[3] S. Messick. The Interplay of Evidence and Consequences in the Validation of Performance Assessments , 1994 .

[4] Susy Macqueen,et al. Validity , 1973, Just Algorithms.

[5] Joel D. Martin,et al. J. Evaluation on an assessment system based on Bayesian student modeling , 1997 .

[6] Javier Ramírez,et al. FUZZY LOGIC APPLICATIONS TO STUDENTS' EVALUATION IN INTELLIGENT LEARNING SYSTEMS , 2003 .

[7] Fernando de Arriaga,et al. Multi-agent architecture for intelligent E-learning , 2003, 10th IEEE International Conference on Electronics, Circuits and Systems, 2003. ICECS 2003. Proceedings of the 2003.