基于LPP的时间序列半监督分类

Time series semi-supervised classification based on Locality Preserving Projections

在时间序列研究领域,半监督分类技术越来越受到广泛关注,绝大多数现有研究都是对原始时间序列直接进行半监督分类,一般情况下,时间序列的维数(长度)比较高,在半监督分类方法中选择合适的降维技术非常重要。本文提出了一种基于局部保持投影的时间序列半监督分类方法。该方法首先使用局部保持投影对时间序列样本进行维数约减,然后对降维后的数据进行半监督分类。在15个时间序列数据集的实验结果表明,该方法的分类性能显著地好于已有方法。

In the field of time series research,semi-supervised classification technology has attracted more and more attention.The existing research mainly focuses on semi-supervised classification of time series of raw data.In general,the dimension(length)of the time series is relatively high.It is very important to choose the appropriate dimensionality reduction technique in the semi-supervised classification method.This paper proposes a time-semi-supervised classification method based on Locality Preserving Projections.The method first uses the locality preserving projections to reduce the dimensionality of the time series samples,and then semi-supervised the reduced-dimensional data.The experimental results in 15 time series datasets show that the classification performance of this method is significantly better than the existing methods.