Yan Zhang
School of Information Science and Technology, Beijing Forestry University, Beijing, China
Baoguo Wu
School of Information Science and Technology, Beijing Forestry University, Beijing, China
Danjv Lv
School of Computer and Information, Southwest Forestry University, Kunming, China
ABSTRACT
How to leverage the abundant unlabeled data with a few labeled training examples to construct a strong classification system is a focus issue. Both semi-supervised learning and active learning attempt to exploit the unlabeled data to improve the recognition rate of supervised learning algorithms and minimize the cost of data labeling. This paper proposed two approaches,Entropy Priority Sampling (EPS) and Simple Disagreement Sampling (SDS),to select samples in active learning , which are applied into the Tri-Training algorithm as Tri-EPS and Tri-SDS methods. Several experiments with these approaches on the UCI, remote sensing image and environmental audio datasets are carried out in order to illustrate the results of the proposed methods and compare their performance with that of Tri-Training algorithm. Experimental results show that the active learning combined with semi-supervised learning can effectively improve the performance.
PDF References Citation
How to cite this article
Yan Zhang, Baoguo Wu and Danjv Lv, 2013. Research on Combination of Tri-training with Active Learning. Information Technology Journal, 12: 7409-7415.
DOI: 10.3923/itj.2013.7409.7415
URL: https://scialert.net/abstract/?doi=itj.2013.7409.7415
DOI: 10.3923/itj.2013.7409.7415
URL: https://scialert.net/abstract/?doi=itj.2013.7409.7415
REFERENCES
- Deng, C. and M.Z. Guo, 2007. ADE-Tri-training: Tri-training with adaptive data editing. Chinese J. Comput., 30: 1213-1226.
Direct Link - Freund, Y., H.S. Seung, E. Shamir and N. Tishby, 1997. Selective sampling using the query by committee algorithm. Machine Learn., 28: 133-168.
CrossRef - Hady, M.F.A. and F. Schwenker, 2010. Combining committee-based semi-supervised learning and active learning. J. Comput. Sci. Technol., 25: 681-698.
CrossRef