You are here:

Development of K-nearest Neighbor Prediction System for Learners’ Scores in the Assembling Process of a Manufacturing Class PROCEEDINGS

, Ibaraki University, Japan ; , Hiroshima University, Japan

Society for Information Technology & Teacher Education International Conference, in Austin, Texas, USA ISBN 978-1-880094-92-1 Publisher: Association for the Advancement of Computing in Education (AACE), Chesapeake, VA

Abstract

The purpose of this paper is to develop a K-nearest neighbor prediction system for learners’ scores in the assembling process of a manufacturing class and to evaluate the degree of precision. A thinking scale test and an achievement test were administered to 274 junior high school students. They were divided into two groups: the training data group (n = 214) and the inspection data group (n = 60). We designed a K-nearest neighbor prediction system accumulated learning data. The result of the precision evaluation with inspection data showed that the correlation between the measured and predicted scores was 0.51, and the predicted scores for the range less than 0.1 occupy 81.7% of the total predicted scores.

Citation

Usuzaka, T. & Yamamoto, T. (2012). Development of K-nearest Neighbor Prediction System for Learners’ Scores in the Assembling Process of a Manufacturing Class. In P. Resta (Ed.), Proceedings of SITE 2012--Society for Information Technology & Teacher Education International Conference (pp. 2157-2163). Austin, Texas, USA: Association for the Advancement of Computing in Education (AACE). Retrieved July 17, 2018 from .