RESUMEN
Time series are the primary data type used to record dynamic system measurements and generated in great volume by both physical sensors and online processes (virtual sensors). Time series analytics is therefore crucial to unlocking the wealth of information implicit in available data. With the recent advancements in graph neural networks (GNNs), there has been a surge in GNN-based approaches for time series analysis. These approaches can explicitly model inter-temporal and inter-variable relationships, which traditional and other deep neural network-based methods struggle to do. In this survey, we provide a comprehensive review of graph neural networks for time series analysis (GNN4TS), encompassing four fundamental dimensions: forecasting, classification, anomaly detection, and imputation. Our aim is to guide designers and practitioners to understand, build applications, and advance research of GNN4TS. At first, we provide a comprehensive task-oriented taxonomy of GNN4TS. Then, we present and discuss representative research works and introduce mainstream applications of GNN4TS. A comprehensive discussion of potential future research directions completes the survey. This survey, for the first time, brings together a vast array of knowledge on GNN-based time series research, highlighting foundations, practical applications, and opportunities of graph neural networks for time series analysis.
RESUMEN
Self-supervised learning (SSL) has recently achieved impressive performance on various time series tasks. The most prominent advantage of SSL is that it reduces the dependence on labeled data. Based on the pre-training and fine-tuning strategy, even a small amount of labeled data can achieve high performance. Compared with many published self-supervised surveys on computer vision and natural language processing, a comprehensive survey for time series SSL is still missing. To fill this gap, we review current state-of-the-art SSL methods for time series data in this article. To this end, we first comprehensively review existing surveys related to SSL and time series, and then provide a new taxonomy of existing time series SSL methods by summarizing them from three perspectives: generative-based, contrastive-based, and adversarial-based. These methods are further divided into ten subcategories with detailed reviews and discussions about their key intuitions, main frameworks, advantages and disadvantages. To facilitate the experiments and validation of time series SSL methods, we also summarize datasets commonly used in time series forecasting, classification, anomaly detection, and clustering tasks. Finally, we present the future directions of SSL for time series analysis.
RESUMEN
The title compound, C(25)H(24)ClNO(3), has three contiguous chiral centres. The absolute structure was determined by anomalous dispersion. The chloro-benzene ring is inclined to the two phenyl rings by 14.98â (9) and 59.05â (9)°. The two phenyl rings are inclined to one another by 49.51â (10)°. In the crystal, neighbouring mol-ecules are linked via C-Hâ¯O hydrogen bonds, forming chains propagating along [010]. There is also a C-Hâ¯π inter-action present that leads to the formation of a three-dimensional network.
RESUMEN
The title compound, [Ag(C(27)H(23)BrN(3)O(4))(CH(3)CN)(2)](PF(6))(2), is a mononuclear salt species in which the silver(I) atom is coordinated by one ligand and two acetonitrile mol-ecules and exhibits a distorted T-shaped coordination. The asymmetric unit contains one independent cation and two independent hexa-fluorido-phosphate anions, one of which is disordered over two positions in a 0.756â (11):0.244â (11) ratio. Weak π-π inter-actions between the anthraquinone ring systems [centroid-centroid distance = 3.676â (3)â Å], inter-molecular Ag-π inter-actions [Cgâ¯Ag = 3.405â Å] and C-Hâ¯π inter-actions between pairs of adjacent mol-ecules are observed.