In recent years, multivariate time-series classification (MTSC) has attracted considerable attention owing to the advancement of sensing technology. Existing deep-learning-based MTSC techniques, which mostly rely on convolutional or recurrent neural networks, focus primarily on the temporal dependency of a single time series. Based on this, complex pairwise dependencies among multivariate variables can be better described using advanced graph methods, where each variable is regarded as a node in the graph, and their dependencies are regarded as edges. Furthermore, current spatial–temporal modeling (e.g., graph classification) methodologies based on graph neural networks (GNNs) are inherently flat and cannot hierarchically aggregate node information. To address these limitations, we propose a novel graph-pooling-based framework, MTPool, to obtain an expressive global representation of MTS. We first convert MTS slices into graphs using the interactions of variables via a graph structure learning module and obtain the spatial–temporal graph node features via a temporal convolutional module. To obtain global graph-level representation, we design an “encoder-decoder”-based variational graph pooling module to create adaptive centroids for cluster assignments. Then, we combine GNNs and our proposed variational graph pooling layers for joint graph representation learning and graph coarsening, after which the graph is progressively coarsened to one node. Finally, a differentiable classifier uses this coarsened representation to obtain the final predicted class. Experiments on ten benchmark datasets showed that MTPool outperforms state-of-the-art strategies in the MTSC task.

Multivariate time series forecasting, which analyzes historical time series to predict future trends, can effectively help decision-making. Complex relations among variables in MTS, including static, dynamic, predictable, and latent relations, have made it possible to mining more features of MTS. Modeling complex relations are not only essential in characterizing latent dependency as well as modeling temporal dependence but also brings great challenges in the MTS forecasting task. However, existing methods mainly focus on modeling certain relations among MTS variables. In this paper, we propose a novel end-to-end deep learning model, termed Multivariate Time Series Forecasting via Heterogeneous Graph Neural Networks (MTHetGNN). To characterize complex relations among variables, a relation embedding module is designed in MTHetGNN, where each variable is regarded as a graph node, and each type of edge represents a specific static or dynamic relationship. Meanwhile, a temporal embedding module is introduced for time series features extraction, where involving convolutional neural network (CNN) filters with different perception scales. Finally, a heterogeneous graph embedding module is adopted to handle the complex structural information generated by the two modules. Three benchmark datasets from the real world are used to evaluate the proposed MTHetGNN. The comprehensive experiments show that MTHetGNN achieves state-of-the-art results in the MTS forecasting task.

Multivariate time series forecasting is widely used in various fields. Reasonable prediction results can assist people in planning and decision-making, generate benefits and avoid risks. Normally, there are two characteristics of time series, that is, long-term trend and short-term fluctuation. For example, stock prices will have a long-term upward trend with the market, but there may be a small decline in the short term. These two characteristics are often relatively independent of each other. However, the existing prediction methods often do not distinguish between them, which reduces the accuracy of the prediction model. In this paper, a MTS forecasting framework that can capture the long-term trends and short-term fluctuations of time series in parallel is proposed. This method uses the original time series and its first difference to characterize long-term trends and short-term fluctuations. Three prediction sub-networks are constructed to predict long-term trends, short-term fluctuations and the final value to be predicted. In the overall optimization goal, the idea of multi-task learning is used for reference, which is to make the prediction results of long-term trends and short-term fluctuations as close to the real values as possible while requiring to approximate the values to be predicted. In this way, the proposed method uses more supervision information and can more accurately capture the changing trend of the time series, thereby improving the forecasting performance.

4-Diazoisoquinolin-3-ones were prepared efficiently via TBAB-promoted rearrangement of 4-diazoisochroman-3-imines under mild reaction conditions. The resulted 4-diazoisoquinolin-3-ones could be conveniently applied for the synthesis of 4-aryltetrahydroisoquinolin-3-ones either by the TfOH-catalyzed reaction with electron-rich arenes or by the BF3-promoted reaction with aryl aldehydes.

4-Diazoisochroman-3-imines were investigated for their synthetic applications as a new class of metal carbene precursors. Under the catalysis from a Rh(II) complex, this class of α-diazo imidates reacted with alkenes and conjugated dienes through a formal [2 + 1] (i.e., cyclopropanation) or [4 + 3] cycloaddition to furnish spiro[cyclopropane-1,4'-isochroman]-3'-imines and tetrahydroisochromeno[3,4-b] azepines, respectively. When Rh(II)/AgOTf was used as cocatalyst, the formal [3 + 2] cycloaddition of 4-diazoisochroman-3-imines with terminal alkynes took place, leading to the synthesis of 2-aryl-3,5-dihydroisochromeno[3,4-b]pyrroles.

An entry from the Cambridge Structural Database, the world’s repository for small molecule crystal structures. The entry contains experimental data from a crystal diffraction study. The deposited dataset for this entry is freely available from the CCDC and typically includes 3D coordinates, cell parameters, space group, experimental conditions and quality measures.

4-Diazoisochroman-3-imines were prepared via the Cu(i)-catalyzed reaction of (2-ethynylphenyl)methanols with sulfonyl azides, and converted to 3,5-dihydroisochromeno[3,4-d][1,2,3]triazoles by reaction with primary amines under catalyst-free conditions.

An entry from the Cambridge Structural Database, the world’s repository for small molecule crystal structures. The entry contains experimental data from a crystal diffraction study. The deposited dataset for this entry is freely available from the CCDC and typically includes 3D coordinates, cell parameters, space group, experimental conditions and quality measures.

The rhodium-catalyzed reactions of 3-diazoindolin-2-imines with furans and dihydrofuran furnished 9H-pyrido [2,3-b] in doles and tetrahydrofuro [3',2':4,5]pyrrolo [2,3-b]indoles, respectively. A cascade reaction mechanism involving an alpha-imino rhodium carbene intermediate is proposed. The starting materials are readily available, and the procedure is facile and efficient.

A concise method for the preparation of tryptanthrins from indoles via the copper-catalyzed aerobic oxidation is described. The reactions can be carried out under mild reaction conditions with varying functional group tolerance.

The relative stabilities of the twenty-three possible isomers for C84O2 based on C84(D(2d)) were studied by using density functional theory (DFT) at B3LYP/6-31G(d) level. The most stable isomer of C84O2 was found to be 1,5,8,9-C84O2 which contains annulene-like structures. In this isomer, two oxygen atoms are added on the same hexagon, which is called a same-ring adduct. The energy gap of C84O2 is narrower than that of C84(D(2d)). The chemical shifts of the bridged carbon atoms in C84O2 are changed upfield compared with those of the same carbon atoms in C84(D(2d)). The same-ring adduct possesses the higher aromaticity than C84(D(2d)). The area within the range of 0.2 nm from the cage center of C84(D(2d)) or C84O2 is the most suitable area for calculating NICS values.