Time series analysis remains a major challenge due to its sparse
characteristics, high dimensionality, and inconsistent data quality. Recent
advancements in transformer-based techniques have enhanced capabilities in
forecasting and imputation; however, these methods are still resource-heavy,
lack adaptability, and face difficulties in integrating both local and global
attributes of time series. To tackle these challenges, we propose a new
architectural concept for time series analysis based on introspection. Central
to this concept is the self-supervised pretraining of Time Series
Representation Models (TSRMs), which once learned can be easily tailored and
fine-tuned for specific tasks, such as forecasting and imputation, in an
automated and resource-efficient manner. Our architecture is equipped with a
flexible and hierarchical representation learning process, which is robust
against missing data and outliers. It can capture and learn both local and
global features of the structure, semantics, and crucial patterns of a given
time series category, such as heart rate data. Our learned time series
representation models can be efficiently adapted to a specific task, such as
forecasting or imputation, without manual intervention. Furthermore, our
architecture's design supports explainability by highlighting the significance
of each input value for the task at hand. Our empirical study using four
benchmark datasets shows that, compared to investigated state-of-the-art
baseline methods, our architecture improves imputation and forecasting errors
by up to 90.34% and 71.54%, respectively, while reducing the required trainable
parameters by up to 92.43%. The source code is available at
this https URL

我们提出了一种基于内省的时间序列分析的新架构概念，其中关键是自监督预训练的时间序列表示模型（TSRM），可以在自动化和资源高效的方式下进行定制和微调，以实现特定任务，如预测和插补。我们的架构通过灵活和分层的表示学习过程对抗缺失数据和异常值，能够捕捉和学习给定时间序列类别（如心率数据）的结构、语义和关键模式的本地和全局特征。与现有方法相比，我们的架构提高了插补和预测误差，分别高达 90.34％和 71.54％，同时减少了可训练参数高达 92.43％。