摘要
对近年来基于支持向量机的时间序列预测算法研究现状进行了综述。时间序列预测是一个极其富有挑战性的研究领域,具有广阔的应用前景,同时支持向量算法是有着巨大潜力的工具,必将在不久的将来在该领域取得突破性的进展。考察了支持向量算法中数据集和预处理、核函数、参数选定、预测评价指标以及支持向量算法总体框架的改进等几个方面研究状况,认为当今研究趋向于支持向量算法与各种人工智能算法的结合。
This paper presents an overview on the study of algorithm for time series prediction based on support vector machine in recent years. Time series prediction is an extremely challenging research area with broad application prospects; while support vector algorithm is a tool with great potential and will definitely take a breakthrough in this area in the near future. After investigating the current researches on data sets,pre-processing,kernel function,parameter selection,and predictive evaluation indicators as well as framework of support vector algorithm,the conclusion we can draw is that the current study tends to combine the support vector algorithm with a variety of artificial intelligent algorithms.
出处
《计算机应用与软件》
CSCD
2010年第12期127-129,157,共4页
Computer Applications and Software
基金
上海师范大学产学研项目(DCL200801)
