In addition, a new method of outlier detection in time series is proposed by combination of phase space theory and one-class classification method.
另外,结合一类分类方法和相空间重构理论,提出一种时间序列中的异常值检测方法。
A new method of outlier detection in time series is proposed in this paper, which is based on phase space reconstruction theory and one-class classification method.
论文结合相空间重构理论与一类分类方法提出一种时间序列中的异常值检测方法。
By making use of the proximity query method in computational geometry, the whole matching query, pattern query, inverse query and outlier detection in time series are studied.
提出了计算几何应用到时间序列挖掘的方法,实现了时间序列全序列匹配查询、模式查询、反向查询和异常检测,查询效率和准确性都有了比较大的提高。
应用推荐