Search

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. [ABSTRACT FROM AUTHOR]

This paper presents an experimental and numerical investigation on the buckling behaviour of corroded cold-formed steel (CFS) channel section columns under axial compression. 7 stub columns and 7 medium long columns were accelerated corrosion by the outdoor periodic spray test. Prior to compression tests, the mass, residual thickness, surface morphology and initial geometric imperfection of the corroded CFS columns were measured. The failure modes, load–strain curves and load–axial displacement curves obtained from axial compression tests were discussed. Based on the corrosion morphology, the non-linear finite element (FE) model for the corroded CFS columns was then developed. Finally, the calculation method for corroded CFS channel section columns was proposed. The results indicated that with the increasing mass loss rate, the irregularity of residual thickness increased rapidly at first, and then increased slowly due to uniform corrosion. The failure mode of the corroded specimens may change from distortional buckling to local buckling as the mass loss rate increased. With the increase in mass loss rate, the buckling critical load, ultimate load, post-buckling strength and axial displacement corresponding to ultimate load decreased. The failure positions of distortional buckling and local buckling were mainly related to the corrosion degree of the flange and web, respectively. The FE results were compared against the experiment results showing a good match in terms of both the ultimate strength and failure modes. [ABSTRACT FROM AUTHOR]

In British Columbia, large-scale salvage harvesting has been underway to recover timber value from forest stands infested by mountain pine beetle during the current outbreak. Understanding the response of beetles to clearcut edges particularly at the landscape scale is crucial to understanding the impacts of increased habitat fragmentation due to salvage harvesting on the spread of the beetle infestations. A novel proximity analysis approach based on null models of complete spatial randomness with three different spatial extents was developed to examine the spatial patterns of infestations in relation to cutblocks. Inhomogeneous Poisson point process models were fitted to predict how intensities of infestations varied with distances to the nearest cutblocks. Marked Poisson point process models were also fitted to evaluate the effects of the variables associated with the nearest cutblocks and adjacent infested pine stands on the edge response of beetles. The results clearly illustrated a significant positive edge response of beetles at the landscape scale. The intensities of infestations decreased non-linearly with distances to the nearest cutblocks. The results also suggested that the quality and distribution of key habitat resources could not fully explain the fundamental mechanisms underlying the edge response. The behavioural change of beetle dispersal at edges may also be an important factor contributing to a positive edge response. The results from this study may be useful in improving the efficacy of mountain pine beetle management efforts. [ABSTRACT FROM AUTHOR]

This paper presents an effective approach for updating finite element dynamic model from incomplete modal data identified from ambient vibration measurements. The proposed method is based on the relationship between the perturbation of structural parameters such as stiffness and mass changes and the modal data measurements of the tested structure such as measured mode shape readings. Structural updating parameters including both stiffness and mass parameters are employed to represent the differences in structural parameters between the finite element model and the associated tested structure. These updating parameters are then evaluated by an iterative solution procedure, giving optimised solutions in the least squares sense without requiring an optimisation technique. In order to reduce the influence of modal measurement uncertainty, the truncated singular value decomposition regularization method incorporating the quasi-optimality criterion is employed to produce reliable solutions for the structural updating parameters. Finally, the numerical investigations of a space frame structure and the practical applications to the Canton Tower benchmark problem demonstrate that the proposed method can correctly update the given finite element model using the incomplete modal data identified from the recorded ambient vibration measurements. [ABSTRACT FROM AUTHOR]