원문정보
보안공학연구지원센터(IJHIT)
International Journal of Hybrid Information Technology
Vol.7 No.2
2014.03
pp.347-356
피인용수 : 0건 (자료제공 : 네이버학술정보)
초록
영어
This paper proposed a new weighted KNN data filling algorithm based on grey correlation analysis (GBWKNN) by researching the nearest neighbor of missing data filling method. It is aimed at that missing data is not sensitive to noise data and combined with grey system theory and the advantage of the K nearest neighbor algorithm. The experimental results on six UCI data sets showed that its filling accuracy is better than the traditional method of K nearest neighbor and filling algorithm presented by Huang and Lee.
목차
Abstract
1. Introduction
2. Grey Relational Analysis
3. GBWKNN based on Grey System Theory
3.1. GBWKNN Algorithm Description
3.2. Conditions for End of Algorithm
4. Experiment and Result Analysis
4.1. Convergence Analysis
4.2. Experimental Evaluation Standard of Prediction Accuracy
5. Conclusion
Acknowledgements
References
1. Introduction
2. Grey Relational Analysis
3. GBWKNN based on Grey System Theory
3.1. GBWKNN Algorithm Description
3.2. Conditions for End of Algorithm
4. Experiment and Result Analysis
4.1. Convergence Analysis
4.2. Experimental Evaluation Standard of Prediction Accuracy
5. Conclusion
Acknowledgements
References
저자정보
참고문헌
자료제공 : 네이버학술정보