A Significantly Faster Elastic-Ensemble for Time-Series Classification
A Significantly Faster Elastic-Ensemble for Time-Series Classification
复制标题
用于时间序列分类的明显更快的弹性集成
DOI：
10.1007/978-3-030-33607-3_48
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Jason Lines
中科院分区：
文献类型：
--
作者：
George Oastler;Jason Lines
在目前最先进的时间序列分类算法——基于转换的集成的分层投票集体（HIVE-COTE）[8]中，弹性集成[7]具有最长的构建时间之一。我们研究了两种简单直观的技术来减少训练弹性集合所花费的时间，从而减少HIVE-COTE训练时间。我们的技术减少每种组分的调优参数的近邻分类器的弹性。首先，减小各成分的参数空间，减少调优工作量；其次，我们限制每个最近邻分类器的训练序列的数量，以减少调优过程中参数选项的评估时间。超过10倍的UEA/UCR时间序列分类问题的实验表明，这两种技术都可以提供更快的构建时间，关键的是，两种技术的结合可以提供更大的加速，而且都没有明显的准确性损失。
The Elastic-Ensemble [7] has one of the longest build times of all constituents of the current state of the art algorithm for time series classification: the Hierarchical Vote Collective of Transformation-based Ensembles (HIVE-COTE) [8]. We investigate two simple and intuitive techniques to reduce the time spent training the Elastic Ensemble to consequently reduce HIVE-COTE train time. Our techniques reduce the effort involved in tuning parameters of each constituent nearest-neighbour classifier of the Elastic Ensemble. Firstly, we decrease the parameter space of each constituent to reduce tuning effort. Secondly, we limit the number of training series in each nearest neighbour classifier to reduce parameter option evaluation times during tuning. Experimentation over 10-folds of the UEA/UCR time-series classification problems show both techniques and give much faster build times and, crucially, the combination of both techniques give even greater speedup, all without significant loss in accuracy.