Red Tide Algae Classification Using SVM-SNP and Semi-supervised FCM

摘要：

In this paper, a novel approach for classifying algal images was presented, which is used in flowcytometry-based real-time red tide monitoring system. Firstly, an ensemble of support vector machines (SVIYIs) was trained and the test samples were labeled by them based on the summation of negative probability (SNP). Secondly, those samples most likely mistakenly labeled were picked out and relabeled by semi-supervised fuzzy c-means (FCM) clustering algorithm. Experiments show that this new method improves the accuracy of algal images classification for the same subject with SVMs of different kernels.

关键词： red tide alga classifier SVM-SNP fuzzy c-means(FCM)

作者: Lili Xu Tao Jiang Jiezhen Xie Shaoping Zheng

作者单位: Department of Computer Science and Technology Xiamen University Xiamen, China College of Electronic Science and Engineering National University of Defense Technology Changsha, Ch

会议类型: 国际会议

会议名称: 2010 2nd International Conference on Education Technology and Computer(第二届IEEE教育技术与计算机国际会议 ICETC 2010)

会议地点: 上海

会议语种:英文

页码: 389-392

在线出版日期: 2010-06-22（万方平台首次上网日期，不代表论文的发表时间）