Time-Series Mining (TSM) is an important research area since it shows great potential in practical applications. Deep learning models that rely on massive labeled data have been utilized for TSM successfully. However, constructing a large-scale well-labeled dataset is difficult due to data annotation costs. Recently, pre-trained models have gradually attracted attention in the time series domain due to their remarkable performance in computer vision and natural language processing. In this survey, we provide a comprehensive review of Time-Series Pre-Trained Models (TS-PTMs), aiming to guide the understanding, applying, and studying TS-PTMs. Specifically, we first briefly introduce the typical deep learning models employed in TSM. Then, we give an overview of TS-PTMs according to the pre-training techniques. The main categories we explore include supervised, unsupervised, and self-supervised TS-PTMs. Further, extensive experiments involving 27 methods, 434 datasets, and 679 transfer learning scenarios are conducted to analyze the advantages and disadvantages of transfer learning strategies, Transformer-based models, and representative TS-PTMs. Finally, we point out some potential directions of TS-PTMs for future work. The source code is available at https://github.com/qianlima-lab/time-series-ptms .

Semi-supervised learning (SSL) has been actively studied due to its ability to alleviate the reliance of deep learning models on labeled data. Although existing SSL methods based on pseudo-labeling strategies have made great progress, they rarely consider time-series data's intrinsic properties (e.g., temporal dependence). Learning representations by mining the inherent properties of time series has recently gained much attention. Nonetheless, how to utilize feature representations to design SSL paradigms for time series has not been explored. To this end, we propose a Time Series SSL framework via Temporal-Frequency Co-training (TS-TFC), leveraging the complementary information from two distinct views for unlabeled data learning. In particular, TS-TFC employs time-domain and frequency-domain views to train two deep neural networks simultaneously, and each view's pseudo-labels generated by label propagation in the representation space are adopted to guide the training of the other view's classifier. To enhance the discriminative of representations between categories, we propose a temporal-frequency supervised contrastive learning module, which integrates the learning difficulty of categories to improve the quality of pseudo-labels. Through co-training the pseudo-labels obtained from temporal-frequency representations, the complementary information in the two distinct views is exploited to enable the model to better learn the distribution of categories. Extensive experiments on 106 UCR datasets show that TS-TFC outperforms state-of-the-art methods, demonstrating the effectiveness and robustness of our proposed model.

Semi-supervised time-series classification could effectively alleviate the issue of lacking labeled data. However, existing approaches usually ignore model interpretability, making it difficult for humans to understand the principles behind the predictions of a model. Shapelets are a set of discriminative subsequences that show high interpretability in time series classification tasks. Shapelet learning-based methods have demonstrated promising classification performance. Unfortunately, without enough labeled data, the shapelets learned by existing methods are often poorly discriminative, and even dissimilar to any subsequence of the original time series. To address this issue, we propose the Diffusion Language-Shapelets model (DiffShape) for semi-supervised time series classification. In DiffShape, a self-supervised diffusion learning mechanism is designed, which uses real subsequences as a condition. This helps to increase the similarity between the learned shapelets and real subsequences by using a large amount of unlabeled data. Furthermore, we introduce a contrastive language-shapelets learning strategy that improves the discriminability of the learned shapelets by incorporating the natural language descriptions of the time series. Experiments have been conducted on the UCR time series archive, and the results reveal that the proposed DiffShape method achieves state-of-the-art performance and exhibits superior interpretability over baselines.

Vibration sensing data is an important resource for mechanical fault prediction, which is widely used in the industrial sector. Artificial neural networks (ANNs) are important tools for classifying vibration sensing data. However, their basic structures and hyperparameters must be manually adjusted, which results in the prediction accuracy easily falling into the local optimum. For data with high levels of uncertainty, it is difficult for an ANN to obtain correct prediction results. Therefore, we propose a multifeature fusion model based on Dempster-Shafer evidence theory combined with a particle swarm optimization algorithm and artificial neural network (PSO-ANN). The model first used the particle swarm optimization algorithm to optimize the structure and hyperparameters of the ANN, thereby improving its prediction accuracy. Then, the prediction error data of the multifeature fusion using a PSO-ANN is repredicted using multiple PSO-ANNs with different single feature training to obtain new prediction results. Finally, the Dempster-Shafer evidence theory was applied to the decision-level fusion of the new prediction results preprocessed with prediction accuracy and belief entropy, thus improving the model’s ability to process uncertain data. The experimental results indicated that compared to the K-nearest neighbor method, support vector machine, and long short-term memory neural networks, the proposed model can effectively improve the accuracy of fault prediction.

Noisy labels seriously degrade the generalization ability of Deep Neural Networks (DNNs) in various classification tasks. Existing studies on label-noise learning mainly focus on computer vision, while time series also suffer from the same issue. Directly applying the methods from computer vision to time series may reduce the temporal dependency due to different data characteristics. How to make use of the properties of time series to enable DNNs to learn robust representations in the presence of noisy labels has not been fully explored. To this end, this paper proposes a method that expands the distribution of Confident instances by Time-Warping (CTW) to learn robust representations of time series. Specifically, since applying the augmentation method to all data may introduce extra mislabeled data, we select confident instances to implement Time-Warping. In addition, we normalize the distribution of the training loss of each class to eliminate the model's selection preference for instances of different classes, alleviating the class imbalance caused by sample selection. Extensive experimental results show that CTW achieves state-of-the-art performance on the UCR datasets when dealing with different types of noise. Besides, the t-SNE visualization of our method verifies that augmenting confident data improves the generalization ability. Our code is available at https://github.com/qianlima-lab/CTW.