A chunk updating LS-SVMs based on block Gaussian elimination method

详细信息    查看全文

• 作者：Xiaoxin Song ^{s15090901@s.upc.edu.cn} ; Ling Jian ^{bebetter@upc.edu.cn} ; Yunquan Song ; ^{syqfly1980@upc.edu.cn}
• 关键词：Incremental online learning ; Chunk updating ; LS-SVMs ; Blast furnace ironmaking process ; Tendency prediction
• 刊名：Applied Soft Computing
• 出版年：2017
• 出版时间：February 2017
• 年：2017
• 卷：51
• 期：Complete
• 页码：96-104
• 全文大小：1777 K
• 卷排序：51

文摘

Propose an incremental online LS-SVMs learning algorithm to incorporate the support vectors chunk-by-chunk. Employ block Gaussian elimination method to dynamically update the LS-SVMs model. Theoretically, analyze the computational complexity of the proposed algorithm, which is demonstrated to be much lower than the state-of-the-arts. Experimental results on benchmark and real-world datasets show the validity and efficiency of the proposed algorithm.