arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1312.6712cs.LG
收藏

时间序列的不变分解

Invariant Factorization Of Time-Series

University of Hildesheim(希尔德斯海姆大学)

Josif Grabocka, Lars Schmidt-Thieme

摘要:

时间序列分类是机器学习的一个重要研究领域,目前已经有大量的方法用于时间序列分类。在现有的方法相比,本研究提出了一种新的方法,该方法将时间序列数据集分解成潜在的模式和隶属权重的局部段这些模式。该过程被形式化为一个受约束的目标函数和定制的随机坐标下降优化。将时间序列投影到一个新的特征表示,该特征表示由成员权重的总和组成,该权重捕获局部模式的频率。来自不同滑动窗口大小的特征被连接起来,以便封装来自不同大小的模式的交互。最后,对6个最先进的基线和43个现实生活中的数据集进行了大规模的实验比较。所提出的方法优于所有的基线具有统计上显着的利润率方面的预测精度。

英文摘要:

Time-series classification is an important domain of machine learning and a plethora of methods have been developed for the task. In comparison to existing approaches, this study presents a novel method which decomposes a time-series dataset into latent patterns and membership weights of local segments to those patterns. The process is formalized as a constrained objective function and a tailored stochastic coordinate descent optimization is applied. The time-series are projected to a new feature representation consisting of the sums of the membership weights, which captures frequencies of local patterns. Features from various sliding window sizes are concatenated in order to encapsulate the interaction of patterns from different sizes. Finally, a large-scale experimental comparison against 6 state of the art baselines and 43 real life datasets is conducted. The proposed method outperforms all the baselines with statistically significant margins in terms of prediction accuracy.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑