共查询到20条相似文献，搜索用时 46 毫秒
1.
RAHMAN M.M ARIFFIN A.K. JAMALUDIN N HARON C.H.C. 《浙江大学学报(A卷英文版)》2006,7(11):1819-1830
INTRODUCTION Fatigue durability has long been important issues in the design of a two-stroke free piston linear engine structure (Torres and Voorwald, 2002; Rahman et al., 2005a; 2005b). Durability assessment is traditionally done in the later part of the product development stage when prototypes are available, and heavily re- lied on in confirming ground durability tests. This process is very time consuming and often results in over-design with weight penalties, which is the major obsta… 相似文献
2.
Analysis of keystroke logging data is of increasing interest, as evident from a substantial amount of recent research on the topic. Some of the research on keystroke logging data has focused on the prediction of essay scores from keystroke logging features, but linear regression is the only prediction method that has been used in this research. Data mining methods such as boosting and random forests have been found to improve over traditional prediction methods such as linear regression in various scientific fields, but have not been used in the prediction of essay scores from keystroke logging features. This article first provides a review of boosting, which is a popular data mining method. The article then applies boosting to predict essay scores from a large number of keystroke logging features and other predictor variables from two real data sets. 相似文献
3.
利用分子力学和量子化学方法计算出烷基硫醇类化合物的分子结构描述参数,用多元线性回归法建立化合物在不同极性色谱柱上的QSRR模型。烷基硫醇类化合物在不同极性色谱柱上的气相色谱保留指数与其拓扑指数之间具有较好的线性关系。建立的不同极性色谱柱上的烷基硫醇类化合物的色谱保留QSRR模型预测此类化合物的色谱保留值,具有较好的稳定性和准确性。 相似文献
4.
高友福 《长江工程职业技术学院学报》2006,23(4):54-57
介绍语音信号的线性预测分析原理,并详细分析用来求解线性预测正则方程的自相关法、Burg法、协方差法的原理和计算方法,并对算法进行了比较. 相似文献
5.
混沌时间序列单变量和多变量重构的预测比较 总被引：2，自引：0，他引：2
提出了多变量混沌时间序列相空间延迟重构中延迟时间间隔和嵌入维数的选取方法，给出了多变量混沌时间序列的局部平均预测法，局部线性预测法和BP神经网络预测法等3种非线性预测方法．通过Lorenz系统的仿真计算表明，无论用3种非线性预测方法中的哪一种，多变量混沌时间序列要比单变量混沌时间序列的预测误差小得多，即使前的数据长度只有后的一半，前的预测误差也要小很多．另外从预测误差最小的角度验证了多变量混沌时间序列相空间延迟重构中延迟时间间隔和嵌入维数选取方法的有效性． 相似文献
6.
《市场调查和预测》是市场营销专业和工商管理专业的一门必修课程,市场预测的时间序列法和因果分析法中经常会提到直线方程,关于直线方程的系数求解,不同情况下可以用不同的方法解决,为了帮助学生理解记忆、提高教学效果,现专门针对直线方程的系数求解及应用范围进行例题讲解并归纳总结． 相似文献
7.
提出了一种在离散变换域中合成语音信号的方法,建立语音线性预测模型,对语音信号分帧、加窗,然后进行线性预测和基音周期的提取,进而模拟重构语音信号。实验表明,该方法易于实现,可操作性强,重建的语音信号还原的声音精度高,并能节省信号传输的带宽,相比以往的方法更能方便、准确的重构合成语音信号。 相似文献
8.
为解决污水处理过程出水氨氮难以精确测量问题,提出一种基于自适应核函数RBF神经网络的出水氨氮软测量方法。由于隐层激活函数对神经网络性能影响较大,AK-RBF 神经网络将基于欧几里得的高斯核与余弦核通过线性组合形成新的隐层神经元激活函数。网络参数学习采用梯度下降算法推导的迭代公式更新以提高网络预测精度。仿真实验表明,基于AK-RBF神经网络的出水氨氮软测量方法能够在线预测出水氨氮,比RBF神经网络具有更高的预测精度和更好的自适应能力。 相似文献
9.
The theory of flows in networks began to evolve in the early 1950’s.The various linear optimisation questions that could be asked of flows in conserving networks turned out to be neat combinatorial specialisations of linear programming. The simplex method (and its variants) turned out to have very pretty combinatorial interpretations on networks. The algebraic dexterity of linear programming duality led to a unified treatment of many deep theorems in graph theory and combinatorics. In this part, the last of the series on linear programming, we will see glimpses of the theory of network flows through a specific flow optimisation problem — the maximum flow problem. 相似文献
10.
Reliability is a very important target of linear induction motors. In this paper, the reliability model of the motor is established, the reliability indexes are defined, the faults’ modes are analyzed and classified according to their effect and damage, the sequential sampling plan is discussed and its acceptable fault rate (ACFR) and refusable fault rate (REFR) are presented, and then, the detailed reliability compliance field test method is introduced with one case. With the method, engineers can verify the reliability of linear induction motors expediently. 相似文献
11.
代金辉 《安阳师范学院学报》2007,(5):24-26
本文基于NPME模型提出一个核线性混合效应模型(KLME)估计量。该方法是结合核方法与线性混合效应模型方法得到的。此方法中,组内相关被融合成一种"权",此估计量能够达到很好的渐进有效性,并且在有限样本时更加实用。 相似文献
12.
13.
由于Euler方法的收敛性较差，研究步长很小时Euler方法的稳定性有着重要的意义。文章证明了应用于一类特殊线性延迟随机微分方程的Euler方法对于很小的步长是T-稳定的。 相似文献
14.
MIXED LINEAR MODEL APPROACHES FOR ANALYZING GENETIC MODELS OF COMPLEX QUANTITATIVE TRAITS 总被引：2，自引：0，他引：2
ＩＮＴＲＯＤＵＣＴＩＯＮＭａｎｙｇｅｎｅｔｉｃｍｏｄｅｌｓｂａｓｅｄｏｎｔｈｅａｐｐｒｏａｃｈｏｆＡＮＯＶＡ (ａｎａｌｙｓｉｓｏｆｖａｒｉａｎｃｅ)ｗｅｒｅｄｅｖｅｌ ｏｐｅｄｂｙＦｉｓｈｅｒ(1 92 5) .Ｓｏｍｅｏｆｔｈｅｓｅｍｏｄｅｌｓ,ｅ.ｇ .ＮＣｄｅｓｉｇｎＩａｎｄＩＩ(Ｃｏｍｓｔｏｃｋｅｔａｌ.,1 952 ;Ｈａｌｌａｕｅｒｅｔａｌ.,1 981 ) ,ｄｉａｌｌｅｌｍｏｄｅｌｓ(Ｙａｔｅｓ,1 94 7;Ｇｒｉｆｆｉｎｇ,1 956;ＧａｒｄｎｅｒａｎｄＥ ｂｅｒｈａｒｔ,1 966) ,ａｒｅｓｔｉｌｌｗｉｄｅｌｙｕｓｅｄｂｙｐｌａ… 相似文献
15.
The geometries of azobenzene compounds are optimized with B3LYP/6-311 G* method, and analyzed with nature bond orbital, then their visible absorption maxima are calculated with TD-DFT method and ZINDO/S method respectively. The results agree well with the observed values. It was found that for the calculation of visible absorption using ZINDO/S method could rapidly yield better results by adjusting OWFπ-π (the relationship between π-π overlap weighting factor) value than by the TD-DFT method. The method of regression showing the linear relationship between OWFπ-π and BLN-N (nitrogen-nitrogen bond lengths) as OWFπ-π=-8.1537 6.5638BLN-N, can be explained in terms of quantum theory, and also be used for prediction of visible absorption maxima of other azobenzne dyes in the same series. This study on molecules' orbital geometry indicates that their visible absorption maxima correspond to the electron transition from HOMO (the highest occupied molecular orbital) to LUMO (the lowest unoccupied molecular orbital). 相似文献
16.
魏明彬 《四川教育学院学报》2014,(7):122-124
常数变易法是求解线性微分方程的重要方法。数学家是如何想到的,是一个值得探讨的问题。讨论了得到常数变易法的思路。在求解一阶线性微分方程的过程中,根据“任何一个未知函数总可以表示为一个已知的恒不为零的函数和一个待定函数之积”,自然地得到了常数变易法。 相似文献
17.
利用MATLAB编程软件,分别建立BP神经网络和AR模型,采用全国出生率,死亡率,老年抚养率等9个指标作为样本,分别对BP网络和AR模型进行训练,预测5年后的人口数量.结果表明这两种方法预测人口均是可行的,效果较好,误差很小,但是AR模型较适合线性预测,而BP网络适合较非线性预测. 相似文献
18.
人口问题是制约中国经济发展的重大问题之一,实行计划生育以来,我国的人口增长水平虽然放缓,但由于人口基数庞大,人口的增长数量仍然相当的可观,因此,准确的预测未来总人口数量对于制定相应的政策法规以保证经济的快速发展具有重大意义。基于过去年份的人口数据,利用ARIMA模型和回归模型来预测未来中国的人口数量,并利用联合预测将两种预测结果进行加权平均,以达到更高的预测精度,为人口预测提供了一种简单高效的预测模型。 相似文献
19.
Kernel Model Applied in Kernel Direct Discriminant Analysis for the Recognition of Face with Nonlinear Variations 总被引：1，自引：0，他引：1
A kernel-based discriminant analysis method called kernel direct discriminant analysis is employed, which combines the merit of direct linear discriminant analysis with that of kernel trick. In order to demonstrate its better robustness to the complex and nonlinear variations of real face images , such as illumination, facial expression, scale and pose variations, experiments are carried out on the Olivetti Research Laboratory, Yale and self-built face databases. The results indicate that in contrast to kernel principal component analysis and kernel linear discriminant analysis, the method can achieve lower (7%) error rate using only a very small set of features. Furthermore, a new corrected kernel model is proposed to improve the recognition performance. Experimental results confirm its superiority (1% in terms of recognition rate) to other polynomial kernel models. 相似文献
20.
Zhu Jun 《浙江大学学报(A卷英文版)》2000,1(1):78-90
New approaches based on general mixed linear models were presented for analyzing complex quantitative traits in animal models,
seed models and QTL (quantitative trait locus) mapping models. Variances and covariances can be appropriately estimated by
MINQUE (minimum norm quadratic unbiased estimation) approaches. Random genetic effects can be predicted without bias by LUP
(linear unbiased prediction) or AUP (adjusted unbiased prediction) methods. Mixed-model based composite interval mapping (MCIM)
methods are suitable for efficiently searching QTLs along the whole genome. Bayesian methods and Markov Chain Monte Carlo
(MCMC) methods can be applied in analyzing parameters of random effects as well as their variances.
Projects supported by NSFC (39670390, 39893350) and the NIH Grant GM32518 相似文献