Search

Network traffic state prediction has been constantly challenged by complex spatiotemporal features of traffic information as well as imperfection in streaming data. This paper proposes a traffic flow prediction model for spatiotemporal graph networks based on fusion of attention mechanisms (STGNN-FAM) to simultaneously tackle these challenges. This model contains a spatial feature extraction layer, a bidirectional temporal feature extraction layer, and an attention fusion layer, which not only fully considers the temporal and spatial features of the traffic flow problem but also uses the attention mechanism to enhance the critical temporal and spatial features to achieve more accurate and robust predictions. Experimental results on a network traffic speed dataset PeMSD7 show that the proposed STGNN-FAM outperforms several important benchmarks in prediction accuracy and the ability to withstand interference in the data stream, especially for mid- and long-term prediction of 30minutes and 45minutes., Author(s): Xueying Qi [1]; Weijian Hu (corresponding author) [1,2]; Baoshan Li [1]; Ke Han [2] 1. Introduction As one of the core functions of the intelligent transportation system, traffic flow [...]

Summary: In this paper, a type of high‐performance nanostructure Fe2O3 (Fe2O3‐arc) is synthesized via a novel direct current electric arc method and employed as a sulfur‐wrapping matrix for lithium‐sulfur batteries. Scanning electron microscopy reveals Fe2O3‐arc has a granular morphology and the crystal size can be controlled below 100 nm. X‐ray diffraction patterns and Raman spectrums show that Fe2O3‐arc displays obvious confusion, but continues to have a typical Fe2O3 crystal structure with preferentially growing on the (110) crystal plane. After sulfur loading, stable physical entrapment and chemical interaction can be established between sulfur and Fe2O3‐arc matrix. The electrochemical test indicates the sulfur composite cathode with Fe2O3‐arc as matrix at the loading mass ratio to 1:3 has a stable and conventional sulfur electrochemical process. The initial discharge specific capacities can achieve 720.59, 653.79 and 540.32 mAh.g−1 at 0.1, 0.2 and 0.5 C current rates, respectively. And after 200 cycles, the capacity retention rate can be at 62.23%. [ABSTRACT FROM AUTHOR]

Summary: An ideal catalyst material in the air electrode can reduce the over‐potentials and obtain an excellent electrochemical performance for lithium‐oxygen batteries. In this paper, Ag modified NixAlyMnzO2 polynary metal oxides (Ag@NAM) is synthesized by a facile precipitation method and as a bifunctional catalyst for high performance air electrode of lithium‐oxygen batteries. X‐ray diffraction and Raman spectrum test results show that the Ag@NAM catalyst has high crystallinity, which can prevent the lattice distortion caused by manganese dissolution and Ag staying on the surface can change the bond energy in order to supply some special catalytic effects. Through scanning electron microscope observation, Ag@NAM with the proportion of Ag and NixAlyMnzO2 polynary metal oxides to 8.5:1.5 has regular block morphology and uniform grain size. When an air electrode catalyst for lithium‐oxygen batteries, Ag@NAM can provide a large electrochemical reaction space along with enough oxygen atoms and lithium ions for electrocatalytic and electrochemical reactions. Specific discharge capacities can achieve to 6834.83, 6477.07, and 4357.14 mAh g−1 at 0.1, 0.2, and 0.3 mA cm−2 current densities, respectively. In addition, this air electrode can carry out stable 28‐time charge and discharge cycles. Hence, we feel that Ag@NAM catalyst can play an ideal bifunctional catalytic role and effectively reduce the polarization resistance. [ABSTRACT FROM AUTHOR]