This paper describes an analysis of the relationship between the menu items of application software and a neural network that represents task and menu selection. In this study, the authors developed a system to infer the users' intention from their input operations by means of a neural network. The meanings of hidden layer's cells in the neural network were analyzed. Furthermore, a simulation was conducted in order to evaluate how the hidden layer's cells in the neural network store the concepts about the target application. As a result, we found that the cells in the hidden layer of the neural network may have fundamental concepts in using the application software. We developed a support system that can suggest tasks the user may want to do as candidates and give the correct operation. This support system has been found to be helpful for the users.

View full abstract

This paper described the correlation between an employee's personal data at the beginning of employment (such as the capabilities obtained before joining the company, performance shown during new employee training and their personality profiled by instructors) and the wage ranking (personnel evaluations) at their 10th year of employment. The null hypotheses were rejected at the 5% significance level between entry records of "Technical Expertise, " "Mathematics" and "English" scores in the employment examination and the "Basic Knowledge on Information Science" course in the employee training and the wage ranking at the 10th year. Multiple regression analysis and the Hayashi's quantification analysis Type were conducted for the classification of the wage ranking from the entry and the training records. A 66.3% correct classification was attained by the latter method of analysis. The major significant items contributing to the results of the analysis were "Technical Expertise" at the employment examination, "Hard Worker" and "Exactness on Work" in their personality profiles, and "Basic Knowledge on Information Science" in new employee training. This shows that basic and fundamental knowledge, including "Technical Expertise, " acquired before employment and "Basic Knowledge on Information Science" in the new employee training is correlated with the 10th year ratings.

View full abstract