Abstract: Imbalanced time series classification represents a significant challenge in the field of deep learning, especially when critical information is concentrated in the minority class. Conventional data augmentation techniques, such as undersampling and oversampling, are designed to increase the proportion of minority class samples. However, they often give rise to issues including information loss, elevated overfitting risk, and the introduction of noise. While "Dual Augmentation Joint Label Learning" (JobDA) has been proven effective in alleviating such problems to a certain extent, it still lacks explicit mechanisms tailored to the minority class. To address this issue, this study proposes a novel approach named "Dual Augmentation with Minority Class Label Merging" (DAMLM). Specifically, this method first expands the training set through dual augmentation of samples and labels, and then uses a label mapping mechanism to merge the minority class labels, which effectively increases the proportion of minority class samples compared with JobDA. In detail, the method performs sample augmentation by repeating the original data, thus avoiding noise introduction. Meanwhile, during the training process, it adopts joint labels for the majority class and retains the original labels for the minority class—this forms clearer classification boundaries compared with other methods. On 38 imbalanced datasets from the UCR archive, we conducted experiments with six time-series classification models and compared methods by averaging the results across these models. Compared with seven representative baseline augmentation methods, DAMLM improves the mean F1 score by 1.24–6.27 percentage points and achieves the best performance on G-mean and other metrics.

摘要： 平衡时间序列分类是深度学习领域的一项重大挑战，尤其是当关键信息集中于少数类时。传统的数据增强方法（如欠采样和过采样）旨在提升少数类样本比例，但往往会导致信息丢失、过拟合风险增加以及噪声引入等问题。尽管“双重增强联合标签学习”（JobDA）已被证明在一定程度上可缓解此类问题，但其并未对少数类做针对性的处理。针对这一难题，研究提出一种名为“少数类标签合并双重增强”（DAMLM）的新方法。该方法首先通过样本与标签的双重增强扩展训练集，随后利用标签映射机制对少数类标签进行融合，相比于JobDA有效提升了少数类样本的比例。具体而言，该方法通过重复原始数据的方式进行样本增强，避免了噪声引入。同时，在训练过程中对多数类采用联合标签、对少数类保留原始标签，相比于其他方法形成了更清晰的分类边界。在UCR档案的38个不平衡数据集上，本文在6种时间序列分类模型上分别开展实验，并对结果取平均进行比较。与7种代表性基线增强方法相比，DAMLM的平均F1提升1.24–6.27个百分点，并在G-mean等指标上取得最优。