Prediction of learning process of human-machine interface withintermissions through a neural network

摘要

In order to adapt a human-machine interface to individual user'slearning condition, while enabling the user to easily use the interface,the individual learning process should be studied. After a long termintermission in operating a machine, the efficiency of the machineoperation may worsen because the intermission weakens the learningresults. In this research a hierarchical neural network with anintermediate layer has been developed in order to forecast the user'slearning capability after the recommencement of the operation, based onthe data gathered in previous operations. The number of units in theintermediate layer was determined by cross validating the data ofexperiments