Search

Some recent evidence suggests that there is a certain correlation between parking saturation and traffic flow in a region, and the trends of the two are affected by changes in both themselves and the other. The traditional single-task prediction often neglects this point, which becomes a bottleneck for further improvement of the prediction accuracy. In this paper, we propose a multi-task spatial-temporal prediction model, which uses multi-channel graph convolutional network (GCN) to fuse the spatial features of the traffic network and the parking network, and then extracts the joint temporal features from the fused spatial features through gated recurrent unit (GRU), so as to realize the integrated and simultaneous prediction of traffic flow and parking saturation. The experiment results show that the multi-task prediction is better than the single-task prediction in terms of accuracy, especially when road traffic and parking interact with each other more closely. Through the experiment, the influence of the correlation between traffic flow and parking saturation on the prediction accuracy is observed for the first time.

During the work of sports competitions and social groups, it is necessary to evaluate and optimize their teamwork capabilities, so that they can effectively improve related capabilities. First, this paper establishes a Bayesian algorithm model, analyzes and simulates the formation of teams in different dimensions and analyzes multi-dimensional analysis of time and space to determine the effectiveness of team cooperation. Different players have their own emphasis on two-person combinations, three-person combinations and other combinations, so they should be arranged according to the actual performance of the players. But on the whole, the three-person combination is more suitable for most players. Under different time scales, their performance is also relatively a big difference. For most players, a match time of 100–1000 is reasonable. Finally, the paper makes error analysis and evaluation of the model to make it more perfect.

Recently, Ag NWs have attracted great attention as the functional layer of flexible and transparent devices. The quality of Ag NWs network is a precondition for the conductivity and transmittance in practical applications. In this paper, we demonstrate the mechanism of water bath pulling method for preparing a transparent conductive film with a two-layer vertical directional silver nanowire network on the flexible transparent PDMS substrate that was applied to resistive sensor. The resistive sensor showed a high transmittance (87.2%), a low sheet resistance (26.9 Ω/sq) and a fast response (GF=90.3) at the tensile strain of 30%. These outstanding performances demonstrate its potential for human motion monitoring.