计算机辅助汉字书写教学技术研究综述

传统的汉字书写教学方法具有一定的局限性，为此人们开始关注计算机辅助的汉字书写教学技术。它主要研究汉字书写规范的智能化、自动化评判方法以及可视化的反馈形式。对近20年来计算机辅助汉字书写教学技术的发展情况进行了综述；详细介绍了数字化展示、书写评判、水平评测等几个研究分支的特点、关键问题以及主要成果；结合相关技术的发展和需求的变化，提出了汉字书写数字化教学技术在未来的发展方向。     

Low-light image enhancement via deep Retinex decomposition and bilateral learning

Low-light images enhancement is a challenging task because enhancing image brightness and reducing image degradation should be considered simultaneously. Although existing deep learning-based methods improve the visibility of low-light images, many of them tend to lose details or sacrifice naturalness. To address these issues, we present a multi-stage network for low-light image enhancement, which consists of three sub-networks. More specifically, inspired by the Retinex theory and the bilateral grid technique, we first design a reflectance and illumination decomposition network to decompose an image into reflectance and illumination maps efficiently. To increase the brightness while preserving edge information, we then devise an attention-guided illumination adjustment network. The reflectance and the adjusted illumination maps are fused and refined by adversarial learning to reduce image degradation and improve image naturalness. Experiments are conducted on our rebuilt SICE low-light image dataset, which consists of 1380 real paired images and a public dataset LOL, which has 500 real paired images and 1000 synthetic paired images. Experimental results show that the proposed method outperforms state-of-the-art methods quantitatively and qualitatively.     

Learn from the past – sequentially one-to-one video deblurring network

With the growing availability of hand-held cameras in recent years, more and more images and videos are taken at any time and any place. However, they usually suffer from undesirable blur due to camera shake or object motion in the scene. In recent years, a few modern video deblurring methods are proposed and achieve impressive performance. However, they are still not suitable for practical applications as high computational cost or using future information as input. To address the issues, we propose a sequentially one-to-one video deblurring network (SOON) which can deblur effectively without any future information. It transfers both spatial and temporal information to the next frame by utilizing the recurrent architecture. In addition, we design a novel Spatio-Temporal Attention module to nudge the network to focus on the meaningful and essential features in the past. Extensive experiments demonstrate that the proposed method outperforms the state-of-the-art deblurring methods, both quantitatively and qualitatively, on various challenging real-world deblurring datasets. Moreover, as our method deblurs in an online manner and is potentially real-time, it is more suitable for practical applications.     

Heat capacities and standard entropies and enthalpies of some compounds essential for steelmaking and refractory design approximated by Debye-Einstein integrals

Heat capacity data for compounds located in the binary CaO–SiO₂, CaO–Al₂O₃ and MgO–Al₂O₃ systems are fitted by Debye-Einstein integrals. Starting from the fitted heat capacities, the standard values of the thermodynamic functions of these compounds are calculated. In almost all cases investigated, the derived standard entropies are within the uncertainties of the values provided in literature. The Debye-Einstein coefficients obtained in this thermodynamic assessment can be used to approximate the heat capacities, enthalpies and entropies of these compounds in the temperature range from 0 to 298.15 K.     

基于GA-BP的汽车风振噪声声品质预测模型

目前对于汽车风振噪声的优化研究主要以声压级（Sound pressure level，SPL）作为单一评价指标，既不能全面反映噪声的物理属性，也无法考虑人耳对噪声的主观认知过程。为准确评价风振噪声，引入声品质，运用大涡模拟（Large eddy simulation，LES）对风振噪声进行数值仿真，根据实车道路试验判断仿真的准确性；对仿真结果进行声品质客观评价与主观评价，综合声品质客观评价参数与声品质主观评价试验结果建立BP神经网络预测模型；利用遗传算法（Genetic algorithm，GA），进一步对BP神经网络的结构参数进行优化，建立GA-BP声品质预测模型。研究结果表明，GA-BP声品质预测模型在训练速度和预测精度上都优于BP神经网络预测模型。预测模型基于声品质主客观评价结果，其预测值可以代替传统的声压级评价指标，为风振噪声提供更为准确合理的评价。     

Flow conditioning system for tri-sonic high pressure aerothermal testing

Blowdown testing offers a cost-effective experimental tool to replicate the aerothermal conditions in numerous high speed systems. The wind tunnel must replicate the inlet operating conditions, while the spatial and time dependent inlet flow conditions should be assessed carefully. This paper provides a design methodology and rules that ensure adequate flow conditioning in high inlet pressure wind tunnels suitable for subsonic and supersonic operation with mass-flow limits ranging from 1 kg/s to 25 kg/s, Reynolds numbers from 10³ (1/m) to 4x10⁷ (1/m), and Mach numbers from 0.01 up to 6. The quality of the proposed flow conditioning system was evaluated using stereo PIV measurements combined with hotwire, Pitot probe, and total flow temperature traverses.