Image inpainting algorithm based on TV model and evolutionary algorithm

With the development of modern image processing techniques, the numbers of images increase at a high speed in network. As a new form of visual communication, image is widely used in network transmission. However, the image information would be lost after transmission. In view of this, we are motivated to restore the image to make it complete in an effective and efficient way in order to save the network bandwidth. At present, there are two main methods for digital image restoration, texture-based method and non-textured-based method. In the texture-based method, Criminisi algorithm is a widely used algorithm. However, the inaccurate completion order and the inefficiency in searching matching patches are two main limitations of Criminisi algorithm. To overcome these shortcomings, in this paper, an exemplar image completion based on evolutionary algorithm is proposed. In the non-textured-based method, total variation method is a typical algorithm. An improved total variation algorithm is proposed in this paper. In the improved algorithm, the diffusion coefficients are defined according to the distance and direction between the damaged pixel and its neighborhood pixel. Experimental results show that the proposed algorithms have better general performance in image completion. And these two new algorithms could improve the experience of network surfing and reduce the network communication cost.     

基因表达式编程的一种新遗传算子

遗传算子在演化算法中发挥重要的作用。设计了基因表达式编程中的一种新遗传算子（TIS）,它在基因尾部随机选择一个小片段,然后复制该片段（或该片段的倒置）并插入到基因尾部的任意位置,插入点后的符号依次向后挪动,超过尾部长度的编码被丢弃。实验表明,该算子在挖掘多元函数时能提高算法的成功率和收敛速度。     

太赫兹信号在老化硅橡胶中的传播特性仿真研究

绝缘是影响电力系统稳定运行的重要因素,但大多数情况下电气设备很难拆卸,对其绝缘老化程度的检测较为困难.太赫兹波具有可以轻易穿透绝缘材料等非金属材料的特性,这对于硅橡胶复合绝缘子的无损检测具有重要意义.分析了太赫兹信号在理想介质与有损介质中传播的特性,从理论上阐述了其在非理想材料中可能发生的损耗,进而指出可以通过检测太赫...     

圆锥滚子球基面磨削力模型及实验研究

为实现圆锥滚子球基面优质高效的磨削加工,以滚子球基面磨削原理为基础,建立圆锥滚子球基面磨削力的数学模型,提出了基于静刚度和功率来验证法向和切向磨削力的方法,系统地分析了夹持圆锥滚子的导轮盘转速差、圆锥滚子自转线速度和砂轮线速度对磨削力的影响,同时基于球基面磨削力数学模型优化磨削工艺参数。研究结果表明：所提出的磨削力模型的计算值与实验结果一致;导轮盘转速差降低、圆锥滚子自转线速度降低和砂轮线速度升高都会减小磨削力;优化后的磨削工艺参数可有效降低圆锥滚子球基面半径散差,从而再次验证了球基面磨削力模型的正确性。     

门静脉高压症小鼠模型构建

【摘要】 目的 构建小鼠胆总管结扎（BDL）及四氯化碳（CCl4）诱导的两种门静脉高压症（PHT）模型。方法 24只C57BL/6小鼠，随机分成4组（BDL组及相应对照组，CCl4诱导组及相应对照组），每组6只。BDL及CCl4诱导法构建PHT小鼠模型后，经门静脉主干穿刺测取门静脉压，并通过血清谷氨酸转氨酶（ALT）及天冬氨酸转氨酶（AST）水平检测，肝脏切片苏木精-伊红（HE）及天狼星红染色，α- 平滑肌肌动蛋白（SMA）免疫组化检查分别对模型肝功能、肝纤维化及肝星状细胞激活情况进行评价。结果 两种建模方法均使小鼠门静脉压上升，CCl4诱导组上升更为显著。两模型组小鼠与相应对照组相比，均呈现严重肝功能损伤、肝纤维化及肝星状细胞激活。结论 BDL及CCl4诱导方法均能成功构建PHT小鼠模型，其门静脉压、血清学生化指标及肝脏病理学改变均符合PHT特点。

     

基于深度学习模型LeNet-5-L的车牌识别算法

针对车牌中汉字识别率低和识别速度慢问题,提出一种基于深度学习的车牌识别网络LeNet-5-L,该网络把车牌识别分为两个阶段,运用OpenCV库函数对车牌图像预处理,结合垂直投影分割方法将车牌分割为7个独立字符图像,降低了图像特征提取难度,从而提高车牌中各个的字符识别率和整个车牌识别速度;运用卷积神经网络解决车牌字符识别问题,基于LeNet-L设计一种车牌字符识别网络LeNet-5-L,有效提高车牌中首字符汉字识别率;实验结果表明,该网络对车牌中各个字符的识别准确率均高于99.97％,单个车牌识别时间仅需0.83 ms,该方法有效的提高车牌识别的正确率和识别速度.     

使用演化计算求解生成循环码的合法码字

编码纠错、检错是计算机应用中最重要的操作手段之一,也是软件、硬件设计中必不可少的一个重要环节。目前,求解域GF(q)中多项式g(x)的生成多项式(g(x))的合法码字的方法有多种,文章认为比较好的一种方法就是利用求解高阶多项式g(x)的根来求出它的生成多项式(g(x))的合法码字。求解域GF(q)中高阶多项式的根通常非常困难,该文介绍一种使用演化计算来求解生成循环码的合法码字的方法。     

基于单形正交实验设计的差分演化算法

为了克服传统差分演化(DE)算法在求解约束优化问题时出现的收敛性慢和容易陷入早熟等缺陷,提出一种新的基于单形正交实验设计的差分演化(SO-DE)算法。该算法设计了一种结合单形交叉和正交实验设计的混合交叉算子来提高差分演化算法的搜索能力;同时采用了一种改进的个体优劣比较准则对种群个体进行比较和选择。这种新的混合交叉算子利用多个父代个体进行单形交叉产生多个子代个体,从两者中选择优秀个体进行正交实验设计得到下一代种群个体。改进的个体优劣比较准则对不同状态下的种群采用不同的处理方案,其目的在于能够有效地权衡目标函数值和约束违反量之间的关系,从而选择优秀个体进入下一代种群。通过对13个标准测试函数和2个工程设计问题进行仿真实验,实验结果表明SO-DE算法求解的精度和标准方差都要优于HEAA算法和COEA/OED算法。SO-DE算法具有更高的精度以及更好的稳定性。     

数据库系统双语教学的探索与实践

双语教学改革是高等教育改革的重要内容之一。本文阐述计算机专业数据库系统开展双语教学的必要性,并从教学准备、课堂教学方法到实验和课程设计的具体实施做了详细叙述,最后总结了该课程改革的收获与不足。     

Nanomedicine-Boosting Tumor Immunogenicity for Enhanced Immunotherapy

Immunotherapy has revolutionized oncology remarkably and gained great improvements in cancer therapy. However, tumor immunotherapy still encounters serious challenges, especially certain tumors barely respond to immunotherapy. The lack of immunogenicity and subsequent insufficient antitumor immune activation is a pivotal reason. Here, a general introduction and the strengthening strategies of immunogenicity of a tumor for enhanced immunotherapy are reviewed. Specifically, nanotechnology nowadays is playing important roles in increasing the antitumor efficacy of various treatments, including immunotherapy. This review highlights how nanomedicines integrating one or more anticancer therapeutic methods (e.g., cancer vaccines, chemotherapy, phototherapy, and radiotherapy) to increase the tumor immunogenicity for rousing T cell related immune responses and achieving inspiring antitumor efficacy. Given the sophisticated immune evasion mechanisms, rational designed nanodrugs with combinational formulations are summarized to improve therapeutic efficacy in synergistic ways. Nanoplatforms taking advantage of the distinct features of tumor tissue or tumor cell with stimuli-responsiveness and targeting functions are introduced to accelerate tumor accumulation of drugs successfully and greatly promote therapeutic efficacy with low-dose administration and programmed drug release. Finally, the related challenges and personal perspectives of nanomedicines for tumor immunotherapy are concluded.