基于改进型批决策与调度建模的生产计划调度系统的研究

热轧型钢生产工艺复杂,其生产中极易出现由于计划调度安排不当而产生的交货期延误、库存超负荷等问题。针对以上问题研究设计了MES生产计划调度系统,改进了批决策调度策略用于数学建模,利用自适应遗传算法求解生产调度计划。以此为基础,为某热轧企业设计实现了生产计划调度系统,并通过真实的热轧型钢订单、原料、设备等数据,对模型改进前后的计划编制方法进行模拟与比较,验证了利用该改进型批决策与调度模型编制的热轧型钢生产调度计划可节省生产时间、降低设备调度时间,以此来指导热轧型钢的生产可切实减少交货延误和减少库存占用率,并提高企业利润率。     

基于Dragon描述符与改进的决策树-遗传算法的反应溶剂设计方法

反应溶剂被广泛应用于液-液均相有机合成中，能够大幅度提高反应速率与选择性，有助于绿色合成新工艺路线的开发。提出了一种基于Dragon描述符与SMILES (simplified molecular-input line-entry system)编码的计算机辅助(computer-aided molecular design, CAMD)反应溶剂设计方法。首先，利用决策树-遗传算法构建可定量预测反应速率常数k的反应动力学模型；基于构建的反应动力学模型，提出了集成决策树-遗传算法与CAMD设计方法，通过SMILES分子编码算法生成同分异构体，并利用Dragon软件计算描述符大小，建立由目标函数与约束方程组成的混合整数非线性规划(mixed integer nonlinear programming, MINLP)模型，进一步采用分解算法对模型进行优化求解，从而实现反应溶剂设计目标；最后，以Diels-Alder反应为例，验证了该方法的可行性与有效性。     

改进教与学优化算法的LQR控制器优化设计

为了快速有效地确定线性二次最优控制(linear quadratic regulator,LQR)问题中的加权矩阵Q和R,针对主动悬架LQR控制器权系数设计问题,提出一种改进的教与学优化算法进行LQR优化设计。算法对基本教与学优化算法中的"教"与"学"阶段进行了进一步的改进,同时提出一种"自我学习"策略。通过仿真实验表明,和基本教与学算法、粒子群算法、遗传算法相比,本文算法在对主动悬架LQR控制器优化时,具有收敛速度快,求解精度高和稳定性强等优势。     

结合图论的JSEG彩色图像分割算法

静态图像压缩标准（ JSEG）分割算法是一种经典的图像分割方法,它充分考虑到了图像的局部信息,可以获得比较精确的分割边界。但JSEG算法在分割过程中计算量相当大并且分割结果容易出现过分割现象。由此,文中提出一种结合图论的JSEG图像分割算法。首先去除JSEG算法中在多个尺度上反复计算J值的过程,改为仅在一个小尺度上进行计算。其次,在得到的J图上使用K-means方法进行聚类,分割得到过分割区域。最后,将分割后的小区域对应为图中的点,进而利用图理论的方法进行区域合并。实验结果表明新算法具有高精度和低复杂度的优势。     

基于数据同化的图像融合方法研究

数据同化凭借其在数值预报中将观测数据与理论模型相结合的特点,目前广泛应用于遥感图像处理及图像融合领域。文中介绍了数据同化的含义和数据同化系统的构成,并分析了其应用于图像融合的原理;结合现有的研究成果着重分析了数据同化框架下结合不同优化算法的图像融合方法,并对其进行分类比较,给出了各方法的优缺点和研究成果及应用;最后在总结了各种基于数据同化的图像融合方法普遍存在的问题的基础上,探讨了进一步发展与研究的方向。     

Research on technology of desktop virtualization based on SPICE protocol and its improvement solutions

Increasingly mature cloud computing technology promotes virtual desktop technology, which can solve many problems existing in traditional computing models. However, virtual desktop solutions introduce the thorny problem of how to deliver a real desktop experience to users, as if they are using it locally, especially when playing video. The SPICE （simple protocol for independent computing environments） virtual desktop solution provides several image compression algorithms to address this problem with the purpose of making virtual desktops as real as possible. Although different compression algorithms can contribute their own abilities to different images to a large extent, switching between them is a big problem that consumes a large amount of resources to detect the different type of image and also causes jitter of the virtual desktop. This paper proposes a new solution, called SPICEx, using the JPEG2000 compression algorithm with dynamic compression ratios to solve the problem and finally validates that the performance is better than that of SPICE. With better quality of user experience and also reducing bandwidth consumption, SPICEx solution is meaningful in virtual desktop fields and can be widely used.     

应用于临床生存时间预测的二次学习算法研究

生存时间预测在医学、经济和工程等领域有着广泛的应用。随着机器学习技术和数据挖掘技术的发展和广泛应用,研究人员提出了很多基于机器学习技术的生存时间预测算法。这些算法虽然都取得了良好的效果,但预测精度均有提升的空间。因此,提出了一种基于二次学习风范的生存时间预测算法,并结合最近邻算法在截尾样本估计上的应用以及支持向量机在泛化性能上的优势,实现了对临床生存时间的建模。实验结果表明,该算法能够获取精确的生存时间,且具有预测精度上的性能优势。     

基于语言结构和情感极性的虚假评论识别

随着电子商务的发展,识别网络中的虚假评论意义重大。传统的启发式策略或全监督学习算法不能有效地解决该问题。虚假评论与真实评论在语言结构和情感极性上存在差异,提出基于遗传算法对语言结构及情感极性特征进行优化选择,并利用选取的特征结合无监督硬、软聚类算法对虚假评论进行识别。实验结果验证了所提算法的有效性。     

Local adaptive segmentation algorithm for 3-D medical image based on robust feature statistics

Medical image segmentation is of pivotal importance in computer-aided clinical diagnosis. Many factors, including noises, bias field effect, local volume effect, as well as tissue movement may affect the med- ical image, thus causing blurring or uneven characteristics when forming a picture. Such quality defects will inevitably impair the gray-scale difference between adjacent tissues and lead to insufficient segmentation or even leakage during tissue or organ segmentation. In the present investigation, a local adaptive segmentation algorithm for 3-D medical image based on robust feature statistics （LARFS） was proposed. By combining segmentation algorithm principles for traditional region growing （RG） and robust feature statistics （RFS）, the location and neighborhood image information of input seed point can be comprehensively analyzed by LARFS. Results show that, for different segmentation objects, under controlling the input parameter of growing factor within certain range, LARFS segmentation algorithm can adapt well to the regional geometric shape. And be- cause the robust feature statistics is applied in the contour evolution process, LARFS algorithm is not sensitive to noises and not easily influenced by image contrast and object topology. Hence, the leakage and excessive segmentation effects are ameliorated with a smooth edge, and the accuracy can be controlled within the effective error range.     

Implementing optimized pairings with elliptic nets

In this paper,we use elliptic nets to implement the optimized Ate pairings and optimal pairings on the Barreto-Naehrig curves with embedding degree 12.In order to do the arithmetic of elliptic curves over finite fields with elliptic nets,we first give some basic properties of elliptic nets associated to elliptic curves over finite fields and the expression of Miller function in terms of elliptic nets.Then we give formulae to compute some optimized pairings with elliptic nets,which is a new method to implement pairings.This method with elliptic nets has time complexity comparable to Miller’s algorithm and it can be optimized.