Characteristics analysis of a task switching during console operation based on the self-organising map
by S. Suzuki
International Journal of Advanced Mechatronic Systems (IJAMECHS), Vol. 2, No. 5/6, 2010

Abstract: On manipulation of usual machines, adequate selection of operational commands and optimal scheduling of tasks are significant for skilled operation. In the present research, an analysis procedure to make the task switching characteristics visible is presented by utilising self-organising map (SOM). For experimental verification, a remote operation system was built that simulates the operation of actual construction equipments, and the process of learning its operation was analysed. It was confirmed that the proposed method was effective through investigation of matching ratios between commands predicted by the trained SOM and actual ones. In addition, a transition analysis method of the learning processes is presented using geometrical distances and areas made by best matching nodes on an SOM planar map. This method was valid to an early phase SOM where clusters are not formed due to inexperienced feature of the operator. Several characteristics concerning the learning process were found, and an ability to show differences of the user skill level was confirmed.

Online publication date: Thu, 25-Nov-2010

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Advanced Mechatronic Systems (IJAMECHS):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com