Abstract

Huge amount of time series data over several domains such as engineering, biomedical and finance, demands the development of efficient methods for the problem of time series classification. The classification of univariate and multivariate time series together using a single architecture is a very difficult task. In this work, a bio-inspired convolutional spiking neural network (CSNN) is proposed for both univariate and multivariate time series. For this, first we develop a simple transformation to convert raw time series sequences into matrices. The CSNN is a three staged framework which include convolutional feature extraction, spike encoding using soft leaky integrate and fire (Soft-LIf) and classification. As spikes generated are differentiable, thus the learning algorithm for CSNN uses error-backpropagation with cyclical learning rates (CLR) and RMSprop optimizer. Additionally, validation based stopping rules are employed to overcome the overfitting which also provides a set of parameters associated with low validation set loss. Thereafter, to demonstrate the accuracy and robustness of proposed CSNN model, we have used University of California (UCR) univariate as well as University of East Anglia (UEA) multivariate datasets to perform the experiments. Moreover, we conduct comparative empirical performance evaluation with benchmark methods and also with recent deep networks proposed for time series classification. Our results reveal that proposed CSNN advances the baseline methods by achieving higher performance accuracy for both univariate and multivariate datasets. It is shown that the CLR with RMSprop optimizer is able to achieve faster convergence, however CLR and adaptive rates are considered competitive to each other. In addition, we also address the optimal model selection and study the effects of different factors on the performance of proposed CSNN.

中文翻译：

---

基于CLR的深度卷积加标神经网络，基于验证的时间序列分类停止

摘要

在工程，生物医学和金融等多个领域的大量时间序列数据，要求开发有效的方法来解决时间序列分类问题。使用单个架构将单变量和多变量时间序列一起分类是一项非常困难的任务。在这项工作中，针对单变量和多变量时间序列，提出了一种生物启发式卷积加标神经网络（CSNN）。为此，我们首先开发一个简单的转换，将原始时间序列序列转换为矩阵。CSNN是一个三阶段框架，包括卷积特征提取，使用软泄漏积分和触发（Soft-LIf）和分类的尖峰编码。由于产生的尖峰是可区分的，因此，CSNN的学习算法使用带有循环学习率（CLR）和RMSprop优化器的错误反向传播。另外，采用基于验证的停止规则来克服过拟合，该过拟合还提供了与低验证集损失相关的一组参数。此后，为了证明所提出的CSNN模型的准确性和鲁棒性，我们使用了加利福尼亚大学（UCR）单变量和东英吉利大学（UEA）多元数据集来进行实验。此外，我们使用基准方法以及最近提出的用于时间序列分类的深层网络进行比较经验绩效评估。我们的结果表明，提出的CSNN通过对单变量和多变量数据集实现更高的性能精度来改进基线方法。结果表明，带有RMSprop优化器的CLR能够实现更快的收敛，但是CLR和自适应速率被认为是相互竞争的。此外，我们还将解决最佳模型选择问题，并研究不同因素对拟议CSNN性能的影响。