Bayesian estimation of Dirichlet mixture model with variational inference

In statistical modeling, parameter estimation is an essential and challengeable task. Estimation of the parameters in the Dirichlet mixture model (DMM) is analytically intractable, due to the integral expressions of the gamma function and its corresponding derivatives. We introduce a Bayesian estimation strategy to estimate the posterior distribution of the parameters in DMM. By assuming the gamma distribution as the prior to each parameter, we approximate both the prior and the posterior distribution of the parameters with a product of several mutually independent gamma distributions. The extended factorized approximation method is applied to introduce a single lower-bound to the variational objective function and an analytically tractable estimation solution is derived. Moreover, there is only one function that is maximized during iterations and, therefore, the convergence of the proposed algorithm is theoretically guaranteed. With synthesized data, the proposed method shows the advantages over the EM-based method and the previously proposed Bayesian estimation method. With two important multimedia signal processing applications, the good performance of the proposed Bayesian estimation method is demonstrated.     

Bezier三角曲面凸性的证明

Bezier曲面造型是计算机图形学的重要研究方向,在实际工作中有着非常广泛的应用.讨论了二次及三次Bezier三角曲面凸性的充分必要条件,这些条件对于控制曲面造型中的保凸性有重要意义.     

On the Range of the Common Cycle Time in a Road Network

In a coordinated road network, the optimal common cycle time is determined by evaluating the performance of the network in the given range of cycles. Normally, this range is determined by users’ experience. And a large range of common cycle time, e.g. \[0,0\] is chosen, which requires long computation time. This study considers that the optimal common cycle time ranges between the minimal and maximal value of intersections’ individual optimal cycle time. It is proved mathematically from the convexity condition, that the delay of the network and each individual intersection are convex functions of the cycle time according to Webster delay model. Finally, 2 000 random cases for the network composed of two intersections and of eight intersections are created to underline the proposed conclusions. The results of all cases confirm the validity, and show up to 90% improvement in computation time to compare with experience range. The signal optimization tool, Synchro, is also used to validate the conclusion by 50 random cases. The results confirm reliability further.     

铁路车辆铆钉拉伸断口不平整原因分析

采用光学显微镜、扫描电镜对失效铁路车辆铆钉的微观组织与断口进行分析.结果表明,铆钉拉伸断口上产生凸台阶的主要原因是在槽口边缘形成的裂纹扩展到心部之前,又在中心形成新的裂纹,且在这些中心裂纹处发生塑性变形.通过调整热处理工艺与控制材料中夹杂物级别可以解决断口不平问题.     

一种新的基于弧段提取的椭圆检测方法

为了克服椭圆检测过程中对椭圆完整性和边缘梯度信息依赖性较强的缺点,提高椭圆目标的检测速度,提出了一种新的基于弧段提取的椭圆拟合方法;首先将梯度方向符号相同的相邻边缘点连接成弧段,然后根据弧段的凸性和象限分类定义新的弧选择策略,利用位置约束和弧对的椭圆中心估计提取候选椭圆,最后采用改进的拟合算法拟合椭圆;实验结果表明,基于弧段提取的椭圆拟合方法相对于LMEDS算法和RHT3具有更好的准确性、鲁棒性和稳定性,实时性也有一定的提高。     

基于法向量的非线性逼近型细分格式

提出一种二进制的几何非线性逼近型细分格式。在该格式中,新点不全是旧点的线性组合,其中一个新点是通过在法向量方向偏移所产生,且法向量在每次细分中能自适应计算。引入一些参数来控制细分过程,且参数对曲线形状的影响是局部的。实例证明,通过选择适当的参数值,产生的细分曲线具有保凸性和 连续性。     

Bernstein-type operators which preserve polynomials

In this paper we present the sequence of linear Bernstein-type operators defined for f∈C[0,1] by B_n(f°τ⁻¹)°τ, B_n being the classical Bernstein operators and τ being any function that is continuously differentiable ∞ times on [0,1], such that τ(0)=0, τ(1)=1 and τ^′(x)>0 for x∈[0,1]. We investigate its shape preserving and convergence properties, as well as its asymptotic behavior and saturation. Moreover, these operators and others of King type are compared with each other and with B_n. We present as an interesting byproduct sequences of positive linear operators of polynomial type with nice geometric shape preserving properties, which converge to the identity, which in a certain sense improve B_n in approximating a number of increasing functions, and which, apart from the constant functions, fix suitable polynomials of a prescribed degree. The notion of convexity with respect to τ plays an important role.     

热轧带钢中板形的计算和控制

热轧带钢中保持良好的板形是生产过程中极其重要的问题。首先,介绍了板形的基础知识包括板形的概念和计算,以及目前生产中板形控制方面实际存在的问题。在此基础上,讨论了影响板形的因素和控制策略,并对由带钢温度引起的缺陷,经过层流冷却获得良好板形的策略做了重点的讨论。从预防的角度阐明了板形的控制方法,并且介绍了一种实际生产中热轧带钢中浪板形控制方法,即PC设定控制方法的具体流程和实际应用效果。     

改善辊型降低弯辊力提高工作辊轴承及轧辊使用寿命

论述了四辊可逆板带冷轧机较大的弯辊力对昂贵的轧辊及轧辊轴承使用寿命的影响,通过研究辊系的弹性变形曲线,找出合理辊系凸度曲线来降低弯辊力.