Use of Fuzzy Modeling Techniques in a Coached Practice Environment for Electronics Troubleshooting.
Saved in:
| Title: | Use of Fuzzy Modeling Techniques in a Coached Practice Environment for Electronics Troubleshooting. |
|---|---|
| Language: | English |
| Authors: | Katz, Sandra, Lesgold, Alan |
| Peer Reviewed: | N |
| Page Count: | 27 |
| Publication Date: | 1992 |
| Document Type: | Reports - Research Speeches/Meeting Papers |
| Descriptors: | Artificial Intelligence, Computer Assisted Instruction, Computer Simulation, Electronics, Knowledge Level, Models, Problem Solving, Programed Tutoring, Technical Education, Troubleshooting |
| Abstract: | Student modeling--the task of building dynamic models of student ability--is fraught with uncertainty, caused by such factors as multiple sources of student errors, careless errors and lucky guesses, learning and forgetting. Within the context of the Sherlock intelligent tutoring systems project, we have been experimenting with various ways of making the task of modeling student knowledge more tractable. The philosophical basis underlying each approach is that student models do not need to be precise and accurate to be useful. We describe these approaches, focusing on the one we have developed furthest thus far. The approach, which is based on fuzzy set theory, aims at building imprecise, or "fuzzy" diagnostic student models (e.g., Hawkes et al., 1990). We have built upon this approach by developing techniques for representing and updating discrete student knowledge variables in our avionics troubleshooting tutor, Sherlock II. We describe these techniques and, more broadly, the student modeling component in this tutor. We frame our discussion of the "fuzzy" student modeling approach we are developing with a description of its more crude predecessor, and of our plans for future work on imprecise student modeling using Bayesian inferencing techniques. (Contains 52 references.) (Author/BBM) |
| Entry Date: | 1993 |
| Accession Number: | ED349964 |
| Database: | ERIC |
| Abstract: | Student modeling--the task of building dynamic models of student ability--is fraught with uncertainty, caused by such factors as multiple sources of student errors, careless errors and lucky guesses, learning and forgetting. Within the context of the Sherlock intelligent tutoring systems project, we have been experimenting with various ways of making the task of modeling student knowledge more tractable. The philosophical basis underlying each approach is that student models do not need to be precise and accurate to be useful. We describe these approaches, focusing on the one we have developed furthest thus far. The approach, which is based on fuzzy set theory, aims at building imprecise, or "fuzzy" diagnostic student models (e.g., Hawkes et al., 1990). We have built upon this approach by developing techniques for representing and updating discrete student knowledge variables in our avionics troubleshooting tutor, Sherlock II. We describe these techniques and, more broadly, the student modeling component in this tutor. We frame our discussion of the "fuzzy" student modeling approach we are developing with a description of its more crude predecessor, and of our plans for future work on imprecise student modeling using Bayesian inferencing techniques. (Contains 52 references.) (Author/BBM) |
|---|
