基于支持向量回归的图像复原方法研究

针对退化图像复原问题,提出了一种基于支持向量回归的退化图像复原方法.该方法利用支持向量机回归算法非线性映射能力,通过训练样本对的学习训练,在退化图像与原始清晰图像之间建立映射关系,然后对测试样本进行复原.实际图像复原实验表明,得到的复原图像在视觉上和定量分析上都获得了比较好的效果.与神经网络方法相比,支持向量机回归算法克服了神经网络的模型选择与过学习问题、局部极小问题等.     

Spatter rate estimation of GMAW-S based on partial least square regression

This paper analyzes the drop transfer process in gas metal arc welding in short-circuit transfer mode （GMAW-S） in order to develop an optimized spatter rate model that can be used on line. According to thermodynamic characters and practical behavior, a complete arcing process is divided into three sub-processes： arc re-ignition, energy output and shorting preparation. Shorting process is then divided as drop spread, bridge sustention and bridge destabilization. Nine process variables and their distribution are analyzed based on welding experiments with high-speed photos and synchronous current and voltage signals. Method of variation coefficient is used to reflect process consistency and to design characteristic parameters. Partial least square regression （PLSR） is utilized to set up spatter rate model because of severe correlativity among the above characteristic parameters. PLSR is a new multivariate statistical analysis method, in which regression modeling, data simplification and relativity analysis are included in a single algorithm. Experiment results show that the regression equation based on PLSR is effective for on-line predicting spatter rate of its corresponding welding condition.     

Relationships between characteristics of motorcycles and hydrocarbon emissions in Taiwan: A note

Taiwan’s inspection and maintenance (I/M) programs identifies high-emission motorcycles but, although these help reduce air pollution, they have been criticized for being cost-ineffective. This study examines the relationship between characteristics of motorcycles and hydrocarbon emissions in the Central Air Quality Basin of Taiwan. It is shown that engine size and type, age and manufacturer of a motorcycle significantly affect HC emissions. Larger-size engines emit smaller amounts of HCs; whereas older motorcycles emitted greater amounts. In addition, two-stroke-engine machines produced significantly higher HC emission levels than four-strokes. Variations in HC emissions testing are a result of various I/M testing locations and efficiency may be improved by modifying these.     

寒冷地区隧道温度场的变化规律

为了揭示隧道温度场的变化规律,以某寒冷地区公路隧道为依托,选择11个测试断面,对隧道拱顶、拱腰、边墙和路面四个部位的温度进行1.5a的长期测试,采用正弦函数回归法,对测试数据进行分析。结果表明:隧道洞内的年气温变化具有周期性,随时间大致呈正弦曲线变化;隧道内纵向气温随着进入隧道距离的增大,年平均温度逐渐下降,年温度振幅也下降,其变化规律呈指数函数曲线变化关系;隧道围岩温度在径向一定范围内,随着径向深度的增加,年平均温度上升,年温度振幅衰减,并且呈指数函数曲线变化关系;防水夹层对隧道保温隔热是有利的。     

基于非参数回归的短时交通流预测研究综述

短时交通流预测是实现交通控制和诱导的关键问题之一。综述了基于非参数回归的短时交通流预测方法,指出了状态向量的选取没有考虑天气环境等存在的问题,提出了改进思路和方法,即基于动态聚类和决策树的历史数据组织方式、时空一天气环境相结合的状态向量选取方法以及基于密集度和状态向量的自适应变K机制等,期望通过这些改进能提高基于非参数回归短时交通流的预测精度,为交通控制和交通诱导建立基础。     

Hierarchical optimisation on scissor seat suspension characteristic and structure

Scissor seat suspension has been applied widely to attenuate the cab vibrations of commercial vehicles, while its design generally needs a trade-off between the seat acceleration and suspension travel, which creates a typical optimisation issue. A complexity for this issue is that the optimal dynamics parameters are not easy to approach solutions fast and unequivocally. Hence, the hierarchical optimisation on scissor seat suspension characteristic and structure is proposed, providing a top-down methodology with the globally optimal and fast convergent solutions to compromise these design contradictions. In details, a characteristic-oriented non-parametric dynamics model of the scissor seat suspension is formulated firstly via databases, describing its vertical dynamics accurately. Then, the ideal vertical stiffness-damping characteristic is cascaded via the characteristic-oriented model, and the structure parameters are optimised in accordance with a structure-oriented multi-body dynamics model of the scissor seat suspension. Eventually, the seat effective amplitude transmissibility factor, suspension travel and the CPU time for solving are evaluated. The results show the seat suspension performance and convergent speed of the globally optimal solutions are improved well. Hence, the proposed hierarchical optimisation methodology regarding characteristic and structure of the scissor seat suspension is promising for its virtual development.     

回归分析中模型的选择问题

本文从一种新的角度讨论了回归分析中回归函数的选择问题,提出了一个一般性准 则,并对几种常见的情况给出了具体的结论。      

大型运输船舶快速性能回归分析研究

基于450条大型运输船舶的船型子样及其快速性能试验数据,应用多元统计回归分析方法,分段研究了大型运输船舶的阻力系数与自航因子的快速估算策略。通过不同船型自变量方案组合的对比分析,得出了影响大型运输船舶快速性的主要船型参数,进而得出了两套阻力系数与自航因子的统计回归表达式,并通过实例验证其正确性。研究成果可用于大型运输船舶的航速快速预报,也为大型运输船舶的快速性能优化指明了方向。     

三体船阻力回归分析及预报方法研究

基于三体船船模系列阻力试验结果,以非均匀B样条拟合船模阻力试验数据随航速变化关系曲线,采用模长界限控制的Gram-Schmidt正交化方法建立给定排水量和航速三体船阻力与侧体位置关系的回归模型,该方法能够快速而有效地获取有效范围内任意给定航速下三体船阻力随侧体位置的变化关系,具有一定的理论意义和较高的工程实用价值.     

A Comparative Study of Three Machine Learning Methods for Software Fault Prediction

The contribution of this paper is comparing three popular machine learning methods for software fault prediction. They are classification tree, neural network and case-based reasoning. First, three different classifiers are built based on these three different approaches. Second, the three different classifiers utilize the same product metrics as predictor variables to identify the fault-prone components. Third, the predicting results are compared on two aspects, how good prediction capabilities these models are, and how the models support understanding a process represented by the data.