Blind Attention Geometric Restraint Neural Network for Single Image Dynamic/Defocus Deblurring.

Based on the information loss analysis of the blur accumulation model, a novel single-image deblurring method is proposed. We apply the recurrent neural network architecture to capture the attention perception map and the generative adversarial network (GAN) architecture to yield the deblurring image. Considering that the attention mechanism has to make hard decisions about specific parts of the input image to be focused on since blurry regions are not given, we propose a new adaptive attention disentanglement model based on the variation blind source separation, which provides the global geometric restraint to reduce the large solution space, so that the generator can realistically restore details on blurry regions, and the discriminator can accurately assess the content consistency of the restored regions.

Characteristic and mechanism of structural acoustic radiation for box girder bridge in urban rail transit.

Noise caused by urban rail transit (URT) has been a hot concerned issue for a long time, and the secondary noise caused by viaduct bridges even make the problem more serious. As well known, structural acoustic radiation (SAR) induced by vibrations of concrete bridges is usually in low frequency. By now, the existing studies mainly focused on the noise above 20Hz, while the infrasonic wave below 20Hz attracts few investigations.

Prediction and mitigation of train-induced vibrations of large-scale building constructed on subway tunnel.

Among all the recent improvements in the railway industry, ground vibration remains an important showstopper in metropolitan cities. In some particular cases, significant levels of vibration are felt by residents. The role of engineers is to propose mitigation solutions and to ensure that they are efficient in the long-term.