[论文解读] Multi-Scale Convolutional Neural Networks for Time Series Classification

Zhicheng Cui, Wenlin Chen+1 more|arXiv (Cornell University)|Mar 22, 2016

Time Series Analysis and Forecasting参考文献 15被引用 475

一句话总结

MCNN 是一个端到端的时间序列分类神经网络，通过多分支架构学习多尺度和多频特征，在基准数据集上实现了最先进的性能。

ABSTRACT

Time series classification (TSC), the problem of predicting class labels of time series, has been around for decades within the community of data mining and machine learning, and found many important applications such as biomedical engineering and clinical prediction. However, it still remains challenging and falls short of classification accuracy and efficiency. Traditional approaches typically involve extracting discriminative features from the original time series using dynamic time warping (DTW) or shapelet transformation, based on which an off-the-shelf classifier can be applied. These methods are ad-hoc and separate the feature extraction part with the classification part, which limits their accuracy performance. Plus, most existing methods fail to take into account the fact that time series often have features at different time scales. To address these problems, we propose a novel end-to-end neural network model, Multi-Scale Convolutional Neural Networks (MCNN), which incorporates feature extraction and classification in a single framework. Leveraging a novel multi-branch layer and learnable convolutional layers, MCNN automatically extracts features at different scales and frequencies, leading to superior feature representation. MCNN is also computationally efficient, as it naturally leverages GPU computing. We conduct comprehensive empirical evaluation with various existing methods on a large number of benchmark datasets, and show that MCNN advances the state-of-the-art by achieving superior accuracy performance than other leading methods.

研究动机与目标

• 推动在传统特征提取+分类器流水线之上提升 TSC 的准确性和效率。
• 提出一个端到端的 MCNN 架构，联合学习特征表示和分类。
• 集成跨时域和频域的变换以捕获多尺度信息。
• 利用数据增强在较小的 TSC 数据集上提高泛化能力。

提出的方法

• 引入带有三个阶段的 MCNN：变换、局部卷积和全卷积。
• 变换阶段通过下采样和移动平均得到多频谱，创建多尺度分支。
• 局部卷积阶段对每个分支应用独立的一维卷积，并进行多尺寸的最大池化。
• 全卷积阶段将分支输出连接后施加额外卷积并使用 softmax 分类器。
• 使用交叉熵损失和反向传播端到端训练模型。
• 通过窗口切片的数据增强来增加较小数据集的训练样本量。

实验结果

研究问题

• RQ1 MCNN 是否能够在不依赖手工特征的情况下自动学习用于 TSC 的判别特征？
• RQ2 与单尺度 CNN 相比，多尺度和多频分支是否提升分类准确性？
• RQ3 在标准基准（UCR 数据集）上，MCNN 与最先进的 TSC 方法相比如何？

主要发现

• MCNN 在大多数数据集上实现更高准确度，优于许多领先方法。
• 在 44 个 UCR 数据集中的 41 个上，MCNN 的表现超过了具有相同参数数量的标准 CNN。
• MCNN 的平均秩为 3.95，与顶尖的集成方法 COTE 相竞争，并优于大多数基线。
• 根据二项检验和威尔科克森符号秩检验，在 1% 水平，MCNN 明显优于大多数方法（除 BOSS 和 COTE 外）。
• 通过窗口切片进行数据增强有助于 MCNN 在较小数据集上的泛化；在较大数据集上不使用增强时，MCNN 仍然表现强劲。