Weight measurement using image-based pose analysis

Image-based gait analysis as a means of biometric identification has attracted much research attention. Most of the existing methods focus on human identification, posture analysis and movement tracking. There have been few investigations on measuring the carried load based on the carrier＇s gait characteristics by automatic image processing. Nevertheless, this measurement is very useful in a number of applications, such as the study of the carried load on the postural development of children and adolescence. In this paper, we investigate how to automatically estimate the carried weight from a sequence of images. We present a method to extract human gait silhouette based on an observation that humans tend to minimize the energy during motion. We compute several angles of body leaning and determine the relationship of the carried weight, the leaning angles and the centroid location according to a human kinetic study. Our weight determination method has been verified successfully by experiments.     

优势区相图的计算机软件开发及应用

根据国内外的优势区相图计算机研究状况，作者采用化学势最小约束原理开发了一种新算法，并给出了新算法的程序框图和应用实例．新算法通用性强，效率高，便于计算机处理，能自动回收数据．     

可分离凸规划问题的交替邻近梯度法的次线性收敛率

给出了目标函数为3个凸函数的和且具有线性约束的可分离凸规划问题的交替邻近梯度法在遍历意义下的次线性收敛率为■的一个充分条件.     

Image separation using wavelet-complex shearlet dictionary

This paper presents a new method for image separation through employing a combined dictionary consisting of wavelets and complex shearlets. Because the combined dictionary sparsely represents points and curvilinear singularities respectively, the image can be decomposed into pointlike and curvelike parts as accurate as possible. The proposed method based on the geo- metric separation theory introduced by Donoho in 2005 shows that accurate geometric separation of the morphologically distinct fea- tures of points and curves can be achieved by l1 minimization. The experimental results show that the proposed method can not only be effective but also greatly reduce the computing time.     

A comparison of optimization theories for energy conservation in heat exchanger groups

In general,thermal processes can be classified into two categories: heat-work conversion processes and heat transfer processes. Correspondingly,the optimization of thermal processes has to have two different criteria:the well known entropy generation minimization method and the recently proposed entransy dissipation maximization method. This study analyzes the thermal issues in a heat exchanger group,and optimizes the unit arrangements under different constraints based on a suitable optimization crite-rion. The result indicates that the principle of minimum entropy generation rate is valid for optimizing heat exchangers in a ther-modynamic cycle with given boundary temperatures. In contrast,the entransy dissipation maximization is more suitable in heat exchanger optimizations involving only heat transfer processes. Furthermore,the entropy generation rate induced by dumping used streams into ambient surroundings has to be taken into account,except for that originating from the hot and cold-ends of heat exchangers,when using the entropy generation minimization to optimize heat exchangers undergoing a thermodynamic cycle.     

分离错误最小化的极大熵方法

分离错误最小化是支持向量机的基本问题之一．一种形式是最小化分离错误点的偏离和,这是一个不可傲优化问题,笔者提出用极大熵函数将其转化成可微凸规划问题来处理,得到原问题的近似最优解。     

解一类复合非光滑极小化问题的拟牛顿型算法

本文讨论极小化由凸泛函和光滑算子复合而成的目标函数的数值方法,给出了旨在求上述问题的一个平稳点的拟牛顿型算法,它将原问题转化为求解一系列约束凸极小化问题的近似解.在适当的条件下算法具有全局收敛性,当目标函数满足增长条件时算法有超线性的敛速.     

指数自回归模型的辨识的研究

本文讨论了指数自回归模型的辨识问题，证明了该模型的最小二乘问题的非凸性，并给出其保证凸性的条件，最后运用混合算法，辨识了该模型，并用数值算例加以说明。     

求解等式约束的二次规划问题

我们在此文中利用一类解决亚定相容线性等式与不等式组的直接方法，提出了一求解等式约束的二次规划问题的算法，讨论了算法的良好性质，实现步骤及收敛性，数值结果表明了算法的有效性。     

基于模糊遗传优化支持向量机的系统辨识研究

在实际应用中支持向量机的参数选取问题一直没有得到很好地解决,限制了其应用。为了能够自动获取最优的支持向量机参数,提出了基于模糊遗传算法的SVM参数选择方法,用模糊逻辑在线调整遗传算法的交叉概率pc和变异概率pm,并采用基于模糊遗传优化的支持向量机回归和BP神经网络对非线性系统辨识问题进行了研究。仿真结果表明,在小样本情况下,支持向量机比神经网络具有更高的系统辨识精度和更好的泛化能力。