Accurate spatiotemporal traffic flow forecasting is significant for the modern traffic management and control. In order to capture the spatiotemporal characteristics of the traffic flow simultaneously, we propose a no...
详细信息
Accurate spatiotemporal traffic flow forecasting is significant for the modern traffic management and control. In order to capture the spatiotemporal characteristics of the traffic flow simultaneously, we propose a novel spatiotemporal residual graph attention network (STRGAT). First, the network adopts a deep full residual graph attention block, which performs a dynamic aggregation of spatial features regarding the node information of the traffic network. Second, a sequence-to-sequence block is designed to capture the temporal dependence in the traffic flow. The traffic flow data with weekly periodic dependencies are also integrated and STRGAT is used for traffic forecasting of traffic road networks. The experiments are conducted on three real data sets in California, USA. Results verify that our proposed STRGAT is able to learn the spatiotemporal correlation of traffic flow well and outperforms the state-of-the-art methods.
Pedestrian trajectory prediction, which aims at predicting the future positions of all pedestrians in a crowd scene given their past trajectories, is the cornerstone of autonomous driving and intelligent transportatio...
详细信息
Pedestrian trajectory prediction, which aims at predicting the future positions of all pedestrians in a crowd scene given their past trajectories, is the cornerstone of autonomous driving and intelligent transportation systems. Accurate prediction and fast inference are both indispensable for real-world applications. In this paper, we propose a stochastic non-autoregressive Transformer-based multi-modal trajectory prediction model to address the two challenges. Specifically, a novel graph attention module dedicated to joint learning of social and temporal interaction is proposed to explore the complex interaction among pedestrians while integrating sparse attention mechanism, pedestrian identity, and temporal order contained in the trajectory data. By doing so, the interaction across temporal and social dimensions can be simultaneously processed to extract abundant context features for prediction. Besides, to accelerate inference speed, we put forward a stochastic non-autoregressive Transformer model with multi-modal prediction capability where each future trajectory can be inferred in a parallel fashion, therefore, resulting in diverse trajectory predictions and less computational cost. Extensive experiments and ablation studies are performed to evaluate our approach. The empirical results demonstrate that the proposed model not only produces high prediction accuracy but also infers with fast speed. The code of the proposed method will be publicly available at https://***/xbchen82/SNARTF.
The roller pump is a distinctive device that delivers fluid in an analogous manner to the peristaltic movement of a biological organism. The pump with the unique mechanism can isolate the liquid from the pump's me...
详细信息
The roller pump is a distinctive device that delivers fluid in an analogous manner to the peristaltic movement of a biological organism. The pump with the unique mechanism can isolate the liquid from the pump's mechanical components effectively, thereby preventing contamination of the fluid. Therefore, the pump is widely used in extracorporeal circulation machines as artificial hearts for extracorporeal circulation of blood. However, the roller pump exhibits flow pulsation, and in severe cases, that may potentially harm the human body during extracorporeal circulation surgeries. It is necessary to optimize the structure of the roller pump, reduce the degree of flow pulsation of the roller pump and improve the smoothness of the flow transmission. In order to minimize the extent of flow pulsation, the high fidelity fluid-solid interaction (FSI) model of roller pump is established, the accuracy of the model is verified by experiment. Two methods of optimizing the pump structure are proposed. First, the optimization method based on the flow compensation, a new structure model of Y- shaped is established, that reduce the degree of pulsation by superimposing the flow curves with phase difference for flow compensation. Another one is the rapid and efficient optimization method based on the surrogate model, that the surrogate model combines with the optimization algorithm to optimize the structural parameters. The surrogate model is used to replace the FSI model, and the optimal configuration of the internal structural variables is obtained through the Multi-island genetic algorithm (MIGA). And the accuracy of the surrogate model verified by FSI analysis. The results indicate that the two optimization methods have their own advantages in reducing the pump flow pulsation and the pump flow pulsation performance has been improved significantly.
Conductive carbon materials have been widely used as framework materials for electrodes. Spiral carbon nanotubes (SCNTs) with excellent physical and chemical properties can be used in lithium-sulfur (Li-S) batteries. ...
详细信息
Conductive carbon materials have been widely used as framework materials for electrodes. Spiral carbon nanotubes (SCNTs) with excellent physical and chemical properties can be used in lithium-sulfur (Li-S) batteries. Here, a novel type of planar double-layer structure cathode was designed by introducing SCNTs. Sulfur, activated carbon (AC), and SCNTs were used to fabricate the S/AC/SCNT and S/AC/SCNT-AC planar double-layer structure cathodes. The initial discharge capacity of the batteries with the S/AC/SCNT and S/AC/SCNT-AC cathodes reached 1016 mAh g(-1) and 946 mAh g(-1) at 0.2 C, respectively. This result indicates that SCNTs play a major role given their excellent conductivity and insertion throughout the cathodes, which can provide an efficient charge transfer path for active materials. Moreover, the S/AC/SCNT-AC cathode exhibits long cycle stability with a capacity decay rate of only 0.11% per cycle at 0.5 C. Therefore, the introduction of SCNTs to a planar double-layer cathode is an efficient method for increasing the conductivity and bound polysulfide amount of Li-S batteries.
暂无评论