Toward predicting the performance of novice CAD users based on their profiled technical attributes

In previously published research (Hamade et al., 2005, 2007, 2009; Hamade and Artail, 2008) the authors developed a framework for analyzing the technical profiles of novice computer-aided design (CAD) trainees as they set to start training in a formal setting. The research included conducting a questionnaire to establish the trainees’ CAD-relevant technical foundation which served as the basis to statistically correlate this data to other experimental data collected for measuring the trainees’ performance over the duration of training. In this paper, we build on that work and attempt to forecast the performance of these CAD users based on their technical profiled attributes. For this purpose, we utilize three Artificial Neural Networks, ANN, techniques: Feed-Forward Back propagation, Elman Back propagation, and Generalized Regression with their capabilities are compared to those of Simulated Annealing as well as to those of linear regression techniques. Based on their profiled technical attributes, the Generalized regression neural network (GRNN) method is found to be most successful in discriminating the trainees including their predicted initial performance as well as their progress.