A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detection.

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.

Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospects.

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.

(2R,3R)-1-(4-Chloro-phen-yl)-2-[(S)-2-nitro-1-phenyl-eth-yl]-3-phenyl-pentan-1-one.

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.

Diacetonitrile-(3-{2-[8-(2-bromo-eth-oxy)-9,10-dioxoanthracen-1-yl-oxy]eth-yl}-1-(2-pyridyl-meth-yl)imidazolium)silver(I) bis-(hexa-fluorido-phosphate).

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 0.756 (11):0.