The Discontinuous Galerkin Finite-Element TimeDomain method is presented. The method is based on a highorder finite element discretization of Maxwell's time-dependent curl equations. The mesh is decomposed into contiguous subdomains of finite-elements with independent function expansions. The fields are coupled across the sub-domain boundaries by enforcing the tangential field continuity. This leads to a locally implicit, globally explicit difference operator that provides an efficient high-order accurate time-dependent solution.An efficient implementation of the perfectly matched layer media boundary truncation is also presented that allows general tetrahedral meshing through the PML region.

No abstract

Named entity recognition (NER) is an essential part of natural language processing tasks. Chinese NER task is different from the many European languages due to the lack of natural delimiters. Therefore, Chinese Word Segmentation (CWS) is usually regarded as the first step of processing Chinese NER. However, the word-based NER models relying on CWS are more vulnerable to incorrectly segmented entity boundaries and the presence of out-of-vocabulary (OOV) words. In this paper, we propose a novel character-based Gated Convolutional Recurrent neural network with Attention called GCRA for Chinese NER task. In particular, we introduce a hybrid convolutional neural network with gating filter mechanism to capture local context information and a highway neural network after LSTM to select characters of interest. The additional gated self-attention mechanism is used to capture the global dependencies from different multiple subspaces and arbitrary adjacent characters. We evaluate the performance of our proposed model on three datasets, including SIGHAN bakeoff 2006 MSRA, Chinese Resume, and Literature NER dataset. The experiment results show that our model outperforms other state-of-the-art models without relying on any external resources like lexicons and multi-task joint training. INDEX TERMS Chinese NER, gating mechanism, highway neural network, self-attention.

No abstract

The Johnson–Holmquist-II(JH-2) model is introduced as the constitutive model for rock materials in tunnel smooth blasting. However, complicated and/or high-cost experiments need to be carried out to obtain the parameters of the JH-2 constitutive model. This study chooses Barre granite as an example to propose a quick and convenient determination method for the parameters of the JH-2 model using a series of computational and extrapolated methods. The validity of the parameters is verified via comparing the results of 3D numerical simulations with laboratory blast-loading experiments. Subsequently, the verified parameter determination method, together with the JH-2 damage constitutive model, is applied in the numerical simulation of smooth blasting in Zigaojian tunnel, Hangzhou–Huangshan high-speed railway. The overbreak/underbreak induced by rock blasting and joints/discontinuities is well estimated through comparing the damage contours resulting from the numerical study with the tunnel profiles measured from the tunnel site. The peak particle velocities (PPVs) of the near field are extracted to estimate the damage scope and damage degree for the surrounding rock mass of the tunnel on the basis of PPV damage criteria. This method can be used in the excavation of rock tunnels subjected to large strains, high strain rates, and high pressures, thereby reducing safety risk and economic losses.

No abstract

Visual appearance is an important cue to judge similarity. We readily classify objects that share a visual appearance as similar, and reject those that do not. The hypothesis is that, image intensity surface features can be used to compute appearance similarity. In the first part of this paper a technique to compute global appearance similarity is described. Images are filtered with Gaussian derivatives to compute two features, namely, local curvatures and orientation. Global image similarity is deduced by comparing distributions of these features. This technique is evaluated on a heterogeneous collection 1600 images.The results support the hypothesis in that images similar in appearance are ranked close together. In the second part of this paper appearance-based retrieval is applied to trademarks. Trademarks are generally binary images containing a single mark against a texture-less background. While moments have been argued as a representation, however, we find that appearance-based retrieval yields better results. Two small databases containing a set of 2,345 parametrically generated shapes, and 10,745 trademarks from the US Patent and Trademark office are used for evaluation. Then a system to retrieve a US Patent and Trademark Office(PTO) trademark database containing 68,000 binary images with textual information is discussed. Text and appearance features are jointly (or independently) queried to retrieve images. Text retrieval is performed using INQUERY and image retrieval using global appearance similarity.

Abstract:The reliability of locomotives plays a central role for the smooth operation of railway systems. Hot-axle failures are one of the most commonly found problems leading to locomotive accidents. Since the operating status of the locomotive axle bearings can be distinctly reflected by the axle temperatures, online temperature monitoring has become an essential way to detect hot-axle failures. In this work, we explore the feasibility of predict the hot-axle failures by identifying the temperature from predicted nominal values. We propose a data-driven approach based on the Long Short-Term Memory (LSTM) network to predict the sensor temperature for axle bearings. The effectiveness of the prediction model was validated with operation data collected from commercial locomotives. With a prediction accuracy is within a few percent, the proposed techniques can be used as a dynamic reference for hot-axle monitoring.