The recognition of the importance of incorporating relevant stock data in the prediction of stock trends has been acknowledged. Nevertheless, the challenge of effectively modeling the relation between stocks and utilizing this relation to enhance the quality of forecasts remains a significant hurdle. Considering this context, we propose a deep-learning architecture designed to predict stock trends. The proposed framework involves the construction and utilization of a lead graph and lag graph. First, the lead graph and lag graph are constructed using the Dynamic Time Warping (DTW) method to reflect the interrelation between stocks. Then, we apply the Graph Convolutional Network (GCN) to extract characteristics from the prices of each stock and the lead or lag stocks. Ultimately, the stock features obtained by GCN are utilized as input for the Gated Recurrent Unit (GRU) network to predict the future movement of the stock. We conducted experiments with real stock data, and the findings demonstrate that the method proposed in this article outperforms approaches that do not account for lead and lag stocks or only consider similar stocks. These results provide empirical evidence supporting the effectiveness of incorporating lead graphs and lag graphs in the stock prediction process.

This study proposes a sensor selection approach based on maximum entropy fuzzy clustering to address the target tracking problem in large‐scale sensor networks. The authors try to deal with this problem at two levels: (i) sensor‐level tracking: data association problem and sensor‐level tracking are carried out at the local level, and only the track outputs are transmitted to the fusion centre for data fusion; (ii) global‐level fusion: two sensor selection strategies are adopted at the fusion centre, which seek to only choose a subset of reliable sensors for track‐to‐track fusion and bias registration. In addition, an improved sensor selection approach is proposed for data fusion in both sparse and dense target environments, and a new fuzzy membership reconstruction strategy is introduced for data association in dense target environments. Furthermore, the proposed sensor selection strategy is also effective in the presence of the possible changing sensor biases. Simulation results are given to evaluate the performance of the proposed approaches.