LikeSNU-서울대 중앙도서관 빅데이터 지식 플랫폼

Semi-supervised learning for the positioning of a smartphone-based robot

Author

유재현; 김현진

Journal Title

제어.로봇.시스템학회 논문지

Publication Year

2015

Topics

#Computer Science
#Artificial intelligence(AI)

Summary

This study proposes a semi-supervised learning algorithm that demonstrates superior performance with only a small amount of labeled data. Specifically, it represents unlabeled data as a spatial-temporal dataset considering the spatio-temporal characteristics of moving objects, thereby improving the accuracy of position estimation for a smartphone-based robot. The proposed algorithm exhibits more accurate location estimation performance compared to existing semi-supervised learning algorithms.

Go Source Add to Selection