Variations of human body skeletons may be considered as dynamic graphs, which are generic data representation for numerous real-world applications. In this paper, we propose a spatio-temporal graph convolution (STGC) approach for assembling the successes of local convolutional filtering and sequence learning ability of autoregressive moving average. To encode dynamic graphs, the constructed multi-scale local graph convolution filters, consisting of matrices of local receptive fields and signal mappings, are recursively performed on structured graph data of temporal and spatial domain. The proposed model is generic and principled as it can be generalized into other dynamic models. We theoretically prove the stability of STGC and provide an upper-bound of the signal transformation to be learnt. Further, the proposed recursive model can be stacked into a multi-layer architecture. To evaluate our model, we conduct extensive experiments on four benchmark skeleton-based action datasets, including the large-scale challenging NTU RGB+D. The experimental results demonstrate the effectiveness of our proposed model and the improvement over the state-of-the-art. * Chaolong Li and Zhen Cui have equal contributions.

No abstract

Distribution network automation is considered by power supply companies as an effective investment strategy to improve reliability and service quality. Switching devices and protective devices play an important role in the distribution automation system (DAS). This paper presents a novel method to optimize placement of fault indicators and sectionalizing switches in distribution networks with branch lines. The objective function of the proposed method includes the total cost of fault indicators and sectionalizing switches as well as interruption cost. Among different automation equipment, this paper considers fault indicators and remote controlled switches. Besides, manual switches are taken into account since their number and location have a significant impact on the optimal placement problem. Mixed-integer linear programming is used to model the problem, and the proposed model can be solved by large-scale commercial solvers. The solution to the problem is composed of the optimal number and location of fault indicators and sectionalizing switches. The validity of the proposed method is demonstrated by relevant case studies and sensitivity analysis. Moreover, the proposed method is applied to a real distribution network to verify its practicability. INDEX TERMS Fault indicator (FI), manual switch (MS), remote controlled switch (RCS), mixed-integer linear programming (MILP), reliability, distribution network.

No abstract