当前位置: X-MOL 学术Appl. Soft Comput. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Time series classification using diversified Ensemble Deep Random Vector Functional Link and Resnet features
Applied Soft Computing ( IF 7.2 ) Pub Date : 2021-08-25 , DOI: 10.1016/j.asoc.2021.107826
Wen Xin Cheng 1 , P.N. Suganthan 1 , Rakesh Katuwal 1
Affiliation  

Random Vector Functional Link (RVFL) is popular among researchers in many areas of machine learning. RVFL is preferred by many researchers as RVFL can produce good performance with relatively little training time. Recent works extend RVFL into deep and ensemble versions. However, RVFL does not have effective feature extraction methods commonly used in time series classification. This results in poor performance of RVFL in time series classification tasks. Also, deep RVFL is a relatively new and evolving area of research. In this paper, we present a framework that extracts features from Residual Networks (Resnet) and trains Ensemble Deep Random Vector Functional Link (edRVFL). We use features extracted from every residual block to train an ensemble of edRVFLs. We propose the following enhancements to edRVFL. Firstly, we diversity the structure of edRVFL and the direct link features to encourage diversity. Secondly, we built an ensemble of edRVFLs with the top two activation functions. Thirdly, we use two-stage tuning to save computational costs. Lastly, we perform a weighted average of all decisions made by every edRVFL. Experiments on the 55 largest UCR datasets show that using features extracted from all Residual blocks improves performance. All our proposed enhancements help improve classification accuracy or computational effort. Consequently, our proposed framework outperforms all traditional and deep learning-based time series classification methods.



中文翻译:

使用多样化 Ensemble Deep Random Vector Functional Link 和 Resnet 特征的时间序列分类

随机向量函数链接 (RVFL) 在机器学习的许多领域的研究人员中都很受欢迎。RVFL 受到许多研究人员的青睐,因为 RVFL 可以在相对较少的训练时间下产生良好的性能。最近的工作将 RVFL 扩展到深度和集成版本。但是,RVFL 没有时间序列分类中常用的有效特征提取方法。这导致 RVFL 在时间序列分类任务中表现不佳。此外,深度 RVFL 是一个相对较新且不断发展的研究领域。在本文中,我们提出了一个从残差网络 (Resnet) 中提取特征并训练集成深度随机向量功能链接 (edRVFL) 的框架。我们使用从每个残差块中提取的特征来训练一组 edRVFL。我们建议对 edRVFL 进行以下增强。首先,我们使 edRVFL 的结构和直接链接特征多样化以鼓励多样性。其次,我们使用前两个激活函数构建了一个 edRVFL 集合。第三,我们使用两阶段调整来节省计算成本。最后,我们对每个 edRVFL 做出的所有决策进行加权平均。在 55 个最大的 UCR 数据集上的实验表明,使用从所有 Residual 块中提取的特征可以提高性能。我们提出的所有增强功能都有助于提高分类准确性或计算工作量。因此,我们提出的框架优于所有传统的和基于深度学习的时间序列分类方法。我们对每个 edRVFL 做出的所有决定进行加权平均。在 55 个最大的 UCR 数据集上的实验表明,使用从所有 Residual 块中提取的特征可以提高性能。我们提出的所有增强功能都有助于提高分类准确性或计算工作量。因此,我们提出的框架优于所有传统的和基于深度学习的时间序列分类方法。我们对每个 edRVFL 做出的所有决定进行加权平均。在 55 个最大的 UCR 数据集上的实验表明,使用从所有 Residual 块中提取的特征可以提高性能。我们提出的所有增强功能都有助于提高分类准确性或计算工作量。因此,我们提出的框架优于所有传统的和基于深度学习的时间序列分类方法。

更新日期:2021-09-04
down
wechat
bug