A multi-modal attention neural network for traffic flow prediction by capturing long-short term sequence correlation.

Accurate traffic flow prediction information can help traffic managers and drivers make more rational decisions and choices. To make an effective and accurate traffic flow prediction, we need to consider not only the spatio-temporal dependencies between data, but also the temporal correlation between data. However, most existing methods only consider temporal continuity and ignore temporal correlation. In this paper, we propose a multi-modal attention neural network for traffic flow prediction by capturing long-short term sequence correlation (LSTSC). In the model, we employed attention mechanisms to capture the spatio-temporal correlations of the sequences, and the model based on multiple decision forms demonstrated higher accuracy and reliability. The superiority of the model is demonstrated on two datasets, PeMS08 and PeMSD7(M), particularly for long-term predictions.

Weighted correlation network analysis of the genes in the eyes of juvenile Plectropomus leopardus provide novel insights into the molecular mechanisms of the adaptation to the background color.

Plectropomus leopardus is a valuable marine fish whose skin color is strongly affected by the background color. However, the influence of the visual sense on the skin color variation of P. leopardus remains unknown. In the present study, transcriptome analysis was used to examine the visual response mechanism under different background colors. Paraffin sections of the eyes showed that the background color caused morphological changes in the pigment cells (PCs) and outer nuclear layer (ONL) and the darkening of the iris color. The transcriptome analysis results indicated that the gene expressions in the eyes of P. leopardus were significantly different for different background colors. We identified 4845, 3069, 5874, and 6309 differentially expressed genes (DEGs) in the pairwise comparisons of white vs. initial, blue vs. initial, red vs. initial, and black vs. initial groups, respectively. Some hub genes and key pathways regulating the adaptive mechanism of P. leopardus's eyes to the background color were identified, i.e., the JAK-STAT, mTOR, and Ras signaling pathways, and the ndufb7, slc6a13, and novel.3553 gene. This adaptation was achieved through the synthesis of stress proteins and energy balance supply mediated by hub genes and key pathways. In addition, the phenylalanine metabolism, tyrosine metabolism, and actin cytoskeleton-related processes or pathways and genes were responsible for iris and skin color adaptation. In summary, we inferred that stress protein synthesis, phenylalanine metabolism, and energy homeostasis were critical stress pathways for P. leopardus to adapt its skin color to the environment. These new findings indicate that the P. leopardus skin color variation may have been caused by the environmental adaption of the eyes. The results provide new insights into the molecular mechanisms underlying the skin color adaptation of P. leopardus.

Seismic Response of Star-Type Grid Concrete Wall Structure by Numerical Modeling.

Cement polystyrene shell mold (CPSM) grid concrete walls have been widely applied in the construction of low and mid-rise buildings with higher load-bearing and insulation properties. A star-type grid concrete wall was constructed based on the infill wall simplified to an equivalent diagonal bracing model. To investigate the seismic responses and behavior of a star-type grid concrete wall structure, an overall time-history numerical simulation was carried out in this paper. Typical results, including acceleration, deformation, hysteresis curve and failure pattern of this novel construction system, were interpreted. Results indicate that the star-type grid concrete wall structure has satisfactory seismic performance, including energy dissipation capacity. The structure has higher lateral stiffness and can work in an elastic state under major earthquakes. Accordingly, it is more sensitive to near-fault ground motion with higher frequency components. Meanwhile, the structural inter-story drift angle is less than the limit value of lighter damage when subjected to a super-major earthquake, and the structure presents shear deformation. The openings significantly affect the failure mode, the star-type grid concrete wall with a window (a small aspect ratio less than 1.11) conforms to shear failure, and the wall with a door (aspect ratio of 2.5) conforms to bending-shear failure. The diagonal bracing can distribute the stress in the wall, especially the concrete lattice beam, and effectively resist the lateral forces via the concrete lattice column, improving the ductility and integrity of the structural system.

Analyzed and Simulated Prediction of Emission Characteristics of Construction Dust Particles under Multiple Pollution Sources.

Dust pollution in construction sites is an invisible hazard that is often ignored as a nuisance. Regulatory and engineering control methods are predominantly used for its mitigation. To control dust, dust-generating activities and their magnitudes need to be established. While researchers have comprehensively studied dust emissions of construction work, prediction of dust concentrations based on work phases and climatic conditions is still lacking. To overcome the above knowledge gap, this article selected two construction stages of a project to monitor dust generation using the HXF-35 dust sampler. Based on the collected data, dust emission characteristics of these two stages are studied, and dust emission characteristics under multiple pollution sources are analyzed. Based on the results, a BP neural network model is built to perform simulations of dust emission concentrations in different work areas and predict construction dust concentrations under different conditions. Except few, the majority of the work areas monitored have exceeded the allowable upper limit of TSP concentration stipulated by relevant standards. In addition, dust emission differences of work areas are pronounced. The results verified that the BP neural network dust concentration prediction model is feasible to be used to predict dust concentration changes in different work faces under different climate conditions and to provide a scientific base for pollution control. This study provides several practical solutions where the prediction of dust concentrations at designated work areas will allow construction companies early warning to implement mitigation measures before it becomes a serious health hazard. In addition, it provides an opportunity to re-evaluate those hazardous work in the light of these revelations. The outcome of this study is both original and useful for both construction companies and regulatory agencies. It can better predict the concentration of construction dust in different operating areas and different weather conditions and provide a guide for the prevention and control of construction dust.