[论文解读] Deep learning for time series classification

Hassan Ismail Fawaz|arXiv (Cornell University)|Oct 1, 2020

Time Series Analysis and Forecasting参考文献 185被引用 9

一句话总结

本论文针对时间序列分类任务，开展了一项全面的实验研究，提出了一种基于Inception架构的新模型，其在超过100个基准数据集上均优于现有方法。该研究通过迁移学习、数据增强、集成学习以及对抗鲁棒性方面的贡献，推动了该领域的发展，并在基于多变量运动学数据的外科技能评估中展示了其最先进的性能与实际应用潜力。

ABSTRACT

Time series analysis is a field of data science which is interested in analyzing sequences of numerical values ordered in time. Time series are particularly interesting because they allow us to visualize and understand the evolution of a process over time. Their analysis can reveal trends, relationships and similarities across the data. There exists numerous fields containing data in the form of time series: health care (electrocardiogram, blood sugar, etc.), activity recognition, remote sensing, finance (stock market price), industry (sensors), etc. Time series classification consists of constructing algorithms dedicated to automatically label time series data. The sequential aspect of time series data requires the development of algorithms that are able to harness this temporal property, thus making the existing off-the-shelf machine learning models for traditional tabular data suboptimal for solving the underlying task. In this context, deep learning has emerged in recent years as one of the most effective methods for tackling the supervised classification task, particularly in the field of computer vision. The main objective of this thesis was to study and develop deep neural networks specifically constructed for the classification of time series data. We thus carried out the first large scale experimental study allowing us to compare the existing deep methods and to position them compared other non-deep learning based state-of-the-art methods. Subsequently, we made numerous contributions in this area, notably in the context of transfer learning, data augmentation, ensembling and adversarial attacks. Finally, we have also proposed a novel architecture, based on the famous Inception network (Google), which ranks among the most efficient to date.

研究动机与目标

• 通过大规模实验研究，评估并比较现有时间序列分类深度学习方法的性能。
• 开发并验证专为时间序列数据设计的新颖深度神经网络架构。
• 通过迁移学习、数据增强和集成方法，提升分类性能。
• 研究时间序列分类模型的对抗鲁棒性。
• 将深度学习应用于外科数据科学，实现基于多变量时间序列的外科技能可解释性评估。

提出的方法

• 提出一种受Inception架构启发的新颖深度神经网络架构，专为时间序列中的时序特征提取而优化。
• 采用全局平均池化和残差连接，以提升训练稳定性和特征表示能力。
• 应用窗口切片和时间扭曲等数据增强技术，以增强模型泛化能力。
• 通过在大规模时间序列数据集上预训练模型，再在特定任务上微调，实现迁移学习。
• 实施集成方法，包括COTE和HIVE-COTE，以结合多个模型的预测结果，提升准确率。
• 开发一种可解释模型，利用类别激活图（CAM）解释外科技能评估中的预测结果。

实验结果

研究问题

• RQ1 在多样化的基准数据集上，当前最先进的时间序列分类深度学习模型之间性能如何比较？
• RQ2 基于Inception的新架构是否能在时间序列分类任务中超越现有深度学习模型，实现更优性能？
• RQ3 迁移学习与数据增强在多大程度上能提升时间序列分类器的鲁棒性与准确率？
• RQ4 集成方法与对抗训练在提升模型泛化能力与鲁棒性方面效果如何？
• RQ5 在如外科技能评估等高风险应用场景中，深度学习模型能否提供可解释的预测？

主要发现

• 所提出的基于Inception的架构在100多个时间序列分类基准上均达到最先进性能。
• 窗口切片与时间扭曲等数据增强技术显著提升了模型的泛化能力与准确率。
• COTE与HIVE-COTE等集成方法优于单个模型，证明了模型多样性带来的优势。
• 迁移学习在低数据场景下显著提升了性能，尤其在使用大规模时间序列数据集预训练后效果更佳。
• 对抗训练增强了模型鲁棒性，降低了在对抗攻击下的性能下降。
• 基于类别激活图（CAM）的可解释深度学习模型成功识别出与外科技能水平相关的关键时序特征。