Neural Machine Translation by Fusing Key Information of Text

When the Transformer proposed by Google in 2017, it was first used for machine translation tasks and achieved the state of the art at that time. Although the current neural machine translation model can generate high quality translation results, there are still mistranslations and omissions in the translation of key information of long sentences. On the other hand, the most important part in traditional translation tasks is the translation of key information. In the translation results, as long as the key information is translated accurately and completely, even if other parts of the results are translated incorrect, the final translation results’ quality can still be guaranteed. In order to solve the problem of mistranslation and missed translation effectively, and improve the accuracy and completeness of long sentence translation in machine translation, this paper proposes a key information fused neural machine translation model based on Transformer. The model proposed in this paper extracts the keywords of the source language text separately as the input of the encoder. After the same encoding as the source language text, it is fused with the output of the source language text encoded by the encoder, then the key information is processed and input into the decoder. With incorporating keyword information from the source language sentence, the model’s performance in the task of translating long sentences is very reliable. In order to verify the effectiveness of the method of fusion of key information proposed in this paper, a series of experiments were carried out on the verification set. The experimental results show that the Bilingual Evaluation Understudy (BLEU) score of the model proposed in this paper on the Workshop on Machine Translation (WMT) 2017 test dataset is higher than the BLEU score of Transformer proposed by Google on the WMT2017 test dataset. The experimental results show the advantages of the model proposed in this paper.     

Residual Feature Attentional Fusion Network for Lightweight Chest CT Image Super-Resolution

The diagnosis of COVID-19 requires chest computed tomography (CT). High-resolution CT images can provide more diagnostic information to help doctors better diagnose the disease, so it is of clinical importance to study super-resolution (SR) algorithms applied to CT images to improve the resolution of CT images. However, most of the existing SR algorithms are studied based on natural images, which are not suitable for medical images; and most of these algorithms improve the reconstruction quality by increasing the network depth, which is not suitable for machines with limited resources. To alleviate these issues, we propose a residual feature attentional fusion network for lightweight chest CT image super-resolution (RFAFN). Specifically, we design a contextual feature extraction block (CFEB) that can extract CT image features more efficiently and accurately than ordinary residual blocks. In addition, we propose a feature-weighted cascading strategy (FWCS) based on attentional feature fusion blocks (AFFB) to utilize the high-frequency detail information extracted by CFEB as much as possible via selectively fusing adjacent level feature information. Finally, we suggest a global hierarchical feature fusion strategy (GHFFS), which can utilize the hierarchical features more effectively than dense concatenation by progressively aggregating the feature information at various levels. Numerous experiments show that our method performs better than most of the state-of-the-art (SOTA) methods on the COVID-19 chest CT dataset. In detail, the peak signal-to-noise ratio (PSNR) is 0.11 dB and 0.47 dB higher on CTtest1 and CTtest2 at SR compared to the suboptimal method, but the number of parameters and multi-adds are reduced by 22K and 0.43G, respectively. Our method can better recover chest CT image quality with fewer computational resources and effectively assist in COVID-19.     

Container-Based Internet of Vehicles Edge Application Migration Mechanism

Internet of Vehicles (IoV) applications integrating with edge computing will significantly drive the growth of IoV. However, the contradiction between the high-speed mobility of vehicles, the delay sensitivity of corresponding IoV applications and the limited coverage and resource capacity of distributed edge servers will pose challenges to the service continuity and stability of IoV applications. IoV application migration is a promising solution that can be supported by application containerization, a technology forseamless cross-edge-server application migration without user perception. Therefore, this paper proposes the container-based IoV edge application migration mechanism, consisting of three parts. The first is the migration trigger determination algorithm for cross-border migration and service degradation migration, respectively, based on trajectory prediction and traffic awareness to improve the determination accuracy. The second is the migration target decision calculation model for minimizing the average migration time and maximizing the average service time to reduce migration times and improve the stability and adaptability of migration decisions. The third is the migration decision algorithm based on the improved artificial bee colony algorithm to avoid local optimal migration decisions. Simulation results show that the proposed migration mechanism can reduce migration times, reduce average migration time, improve average service time and enhance the stability and adaptability of IoV application services.     

基于MP算法的快速地震信号谱分析

MP(Matching Pursuits)算法以其灵活的自适应性,取得了广泛的应用,但依然存在计算量大的应用瓶颈问题.为了解决传统MP算法运算量大的问题,首先对MP算法的原理进行了介绍,然后针对其计算量大的问题提出了一种基于遗传算法的快速算法,有效地降低了MP算法的运算量,较好地解决了运算量大的问题.最后利用MP算法对地震信号进行了谱分析,消除了Wigner算法中的交叉项,从而有效地揭示了地震信号的时频信息.结果表明,改进后的MP算法可以作为地震信号谱分析的有效算法,为烃类检测和储层描述等提供有地效的手段.     

PCI总线在双谱段探测系统中的应用*

PCI是DSP应用系统与通用计算机高速通信的理想接口。介绍了一种双谱段探测系统的PCI接口方案,该方案采用TI公司的TMS320F2812 DSP作为控制单元主控芯片,采用Cypress公司PCIDP系列的CY7C09449PV作为PCI接口芯片,具有接口简单方便易于实现的优点。详细讨论了CY7C09449PV与TMS320F2812的硬件连接、参数配置与时序分析。     

用多媒体软件模拟匀加速直线运动

用多媒体软件Ｄｉｒｅｃｔｏｒ６．０来模拟物理教学中的匀加速直线运动。     

Hybrid Well-balanced WENO Schemes with Different Indicators for Shallow Water Equations

In (J. Comput. Phys. 229: 8105–8129, 2010), Li and Qiu investigated the hybrid weighted essentially non-oscillatory (WENO) schemes with different indicators for Euler equations of gas dynamics. In this continuation paper, we extend the method to solve the one- and two-dimensional shallow water equations with source term due to the non-flat bottom topography, with a goal of obtaining the same advantages of the schemes for the Euler equations, such as the saving computational cost, essentially non-oscillatory property for general solution with discontinuities, and the sharp shock transition. Extensive simulations in one- and two-dimensions are provided to illustrate the behavior of this procedure.     

Blockwise conjugate gradient methods for image reconstruction in volumetric CT

Cone beam computed tomography (CBCT) enables volumetric image reconstruction from 2D projection data and plays an important role in image guided radiation therapy (IGRT). Filtered back projection is still the most frequently used algorithm in applications. The algorithm discretizes the scanning process (forward projection) into a system of linear equations, which must then be solved to recover images from measured projection data. The conjugate gradients (CG) algorithm and its variants can be used to solve (possibly regularized) linear systems of equations Ax=b and linear least squares problems minx∥b-Ax∥(2), especially when the matrix A is very large and sparse. Their applications can be found in a general CT context, but in tomography problems (e.g. CBCT reconstruction) they have not widely been used. Hence, CBCT reconstruction using the CG-type algorithm LSQR was implemented and studied in this paper. In CBCT reconstruction, the main computational challenge is that the matrix A usually is very large, and storing it in full requires an amount of memory well beyond the reach of commodity computers. Because of these memory capacity constraints, only a small fraction of the weighting matrix A is typically used, leading to a poor reconstruction. In this paper, to overcome this difficulty, the matrix A is partitioned and stored blockwise, and blockwise matrix-vector multiplications are implemented within LSQR. This implementation allows us to use the full weighting matrix A for CBCT reconstruction without further enhancing computer standards. Tikhonov regularization can also be implemented in this fashion, and can produce significant improvement in the reconstructed images.     

Phase formation and modification of corrosion property of nitrogen implanted Ti-Al-V alloy

In the present investigation, polished samples were implanted with nitrogen ion at an energy of 60 keV and implantation doses were 1×10¹⁶, 5×10¹⁶, 1×10¹⁷ and 6×10¹⁷ ions/cm². Glancing incidence X-ray diffraction was employed on the implanted specimens to understand the phases formed with increasing dose. The valence states of nitrogen, titanium and carbon on the sample surfaces were analyzed by X-ray photoemission spectroscopy. The corrosion resistance was examined by the electrochemical methods in a solution with pH=10 at room temperature in order to determine the optimum dose that can give good corrosion resistance in a simulated nuclear reactor condition. Scanning electron microscopy was used to observe the topographies of nitrogen-implanted Ti-Al-Zr after potentiodynamic measurement. It was found that implanted nitrogen dissolved in titanium matrix with increasing dose and the resultant nitrides such as TiN and Ti₂N precipitated. Implantation of nitrogen ions into the surface of Ti-Al-V alloy improves its corrosion resistance, and the increase of the corrosion resistance depends on the nitrogen dose employed; the maximum improvement of the corrosion resistance was observed at a dose of 1×10¹⁷ N⁺/cm².