Oracle数据库中Java执行的安全性研究

Java是一种比较安全的编程语言,而且功能强大、应用广泛;Oracle数据库提供了极其强大的安全特性.两者的结合,可以为当前比较复杂的应用程序提供更强的安全性.主要研究了基于Oracle Java虚拟机的诸多安全途径.     

基于支持向量机的人脸识别算法

特征提取是人脸识别问题中的一个普遍问题,主要是指通过变换将图像空间中的人脸转化到人脸特征空间中,其目的是用最少的数据量表示原始图像的最多的信息.其中Fisher脸法是常用的特征提取方法,本文采用Fisher脸法和支持向量机的方法,构造了一个能够将图像数据空间的人脸映射到人脸特征空间中,并实施识别的实验系统.分析了该系统的构成与特点,并给出了实验测试结果.     

用VxD实现并行数据通讯

通过开发实例介绍了在Delphi5 .0中利用虚拟设备驱动程序进行动态加载 ,实现与并行采集卡通讯的技术方法 .     

Dual decomposition of a single-machine scheduling problem

We design a fast ascent direction algorithm for the Lagrangian dual problem of the single-machine scheduling problem of minimizing total weighted completion time subject to precedence constraints. We show that designing such an algorithm is relatively simple if a scheduling problem is formulated in terms of the job completion times rather than as an 0–1 linear program. Also, we show that upon termination of such an ascent direction algorithm we get a dual decomposition of the original problem, which can be exploited to develop approximative and enumerative approaches for it. Computational results exhibit that in our application the ascent direction leads to good Lagrangian lower and upper bounds.     

Modeling and optimizing a vendor managed replenishment system using machine learning and genetic algorithms

Using a supply chain network, we demonstrate the feasibility, viability, and robustness of applying machine learning and genetic algorithms to respectively model, understand, and optimize such data intensive environments. Deployment of these algorithms, which learn from and optimize data, can obviate the need to perform more complex, expensive, and time consuming design of experiments (DOE), which usually disrupt system operations. We apply and compare the behavior and performance of the proposed machine learning algorithms to that obtained via DOE in a simulated Vendor Managed Replenishment system, developed for an actual firm. The results show that the models resulting from the proposed algorithms had strong explanatory and predictive power, comparable to that of DOE. The optimal system settings and profit were also similar to that obtained from DOE. The virtues of using machine learning and evolutionary algorithms to model and optimize data rich environments thus seem promising because they are automatic, involving little human intervention and expertise. We believe and are exploring how they can be made adaptive to improve parameter estimates with increasing data, as well as seamlessly detecting system (and therefore model) changes, thus being capable of recursively updating and reoptimizing a modified or new model.     

An unfeasibility view of neural network learning

We define the notion of a continuously differentiable perfect learning algorithm for multilayer neural network architectures and show that such algorithms do not exist provided that the length of the data set exceeds the number of involved parameters and the activation functions are logistic, tanh or sin.     

基于连续小波变换下的土壤有害元素砷含量估测

与传统检测方法相比,利用高光谱技术进行土壤有害元素砷含量的估算,具有快速、准确,成本低的特点,可对干旱区绿洲土壤有害元素砷污染进行动态监测。基于新疆渭干河-库车河三角洲绿洲耕层土壤样品的采集,获取土壤光谱数据和有害元素砷含量。通过bior1.3,db4,gaus4和mexh这4种小波基函数对土壤原始光谱反射率进行连续小波变换,并将变换后光谱数据与有害元素砷进行相关分析,以筛选出的敏感小波系数为自变量,采用偏最小二乘回归、支持向量机回归、BP神经网络和随机森林回归方法对有害元素砷含量进行高光谱反演。研究结果显示：（1）4种小波基函数在3~8尺度的光谱分解效果明显优于其他尺度,特别是4~6尺度的连续小波变换有效提升了光谱反射率与土壤有害元素砷之间的相关性,通过显著性检验的小波系数数量有了明显增多（p<0.01）,在可见光的400~700 nm以及近红外的1 100~1 700和2 200~2 400 nm附近具有较强的相关性;（2）通过比较4种小波基函数对光谱数据中有效信息的辨识能力,认为小波基函数bior1.3和mexh要优于db4和gaus4,其中bior1.3的光谱分解效果最好,gaus4相对最弱;通过bior1.3第5尺度的光谱变换,与土壤有害元素砷显著相关的波段数量最多,为507个（p<0.01）;（3）比较4种建模方法的反演结果发现,SVMR,BPNN和RFR模型相较于PLSR模型具有更强的估测能力,模型的估测精度更高。综合分析各模型的稳定性及估测精度后,认为bior1.3-25-RFR模型可作为研究区土壤有害元素砷的最佳估测模型。该模型的训练集和验证集的R2分别为0.893和0.639,RMSE为1.075和1.651 mg·kg-1,RPD分别为2.89和1.64,表明模型估测效果较好,稳定性较强。采用合适的小波基函数进行连续小波变换可减少土壤高光谱数据中的白噪声,挖掘出土壤光谱数据中的有效信息,对土壤有害元素砷含量的准确估测提供有力的技术保障。     

Optimal deteriorating items production inventory models with random machine breakdown and stochastic repair time

This study develops deteriorating items production inventory models with random machine breakdown and stochastic repair time. The model assumes the machine repair time is independent of the machine breakdown rate. The classical optimization technique is used to derive an optimal solution. A numerical example and sensitivity analysis are shown to illustrate the models. The stochastic repair models with uniformly distributed repair time tends to have a larger optimal total cost than the fixed repair time model, however the production up time is less than the fixed repair time model. Production and demand rate are the most sensitive parameters for the optimal production up time, and demand rate is the most sensitive parameter to the optimal total cost for the stochastic model with exponential distribution repair time.     

Single machine scheduling with semi-resumable machine availability constraints

This paper considers the semi-resumable model of single machine scheduling with a non-availability period. The machine is not available for processing during a given time interval. A job cannot be completed before the non-availability period will have to partially restart after the machine has become available again. For the problem with objective of minimizing makespan, the tight worst-case ratio of algorithm LPT is given, and an FPTAS is also proposed. For the problem with objective of minimizing total weighted completion time, an approximation algorithm with worst-case ratio smaller than 2 is presented. Two special cases of the latter problem are also considered, and improved algorithms are given.     

高光谱的刺五加黑斑病的早期检测研究

对感染黑斑病的刺五加叶片进行光谱特性研究,能为药用植物病害的早期筛选与精准治疗提供重要研究资料。实验目的,运用高光谱成像技术实现植物病害的自动监督分类与识别。实验过程,首先使用高光谱成像系统在可见光波段（380～960 nm）内采集刺五加黑斑病的叶片样本,光谱数据经过去除亮暗噪声和平滑预处理后,再经过主成分分析实现数据降维,继而运用基于不同核函数的支持向量机法建立分类模型,最后利用总体分类精度、Kappa系数等因子评价不同核函数对分类器性能的影响。根据叶片表面的特征将其分为四类样本：健康亮部、健康暗部、轻度病害和重度病害等。对比各类样本的光谱可知,刺五加的健康样本在540 nm波长存在一个明显峰值,在620～680 nm光谱曲线急剧上升;而病害样本的光谱反射率呈现缓慢且平稳的上升趋势,上述特征能够将图像空间上反射强度接近的健康亮部和严重病害完全区分开。经对比发现前四个主成分（PC1,PC2,PC3,PC4）在分类表达上存在差异,主要表现为PC1含有的信息多,能够较好地区分各类样本;PC2则出现健康亮部和严重病害的交叉混淆;PC3是对于PC2的补充,能基本完整地表达轻微病害;PC4的贡献率仅有0.19%,依然能够准确地识别严重病害。不同主成分分量在表达各类样本特征中存在的差异能够作为复杂样本分类的参考依据。对比四种核函数对支持向量机分类器性能的影响,结果显示线性核函数的识别过程受光强反射的影响较大,Sigmoid核函数的训练精度易受数据集大小的影响,在识别健康亮或暗,以及轻微病害上均存在一定的误差,多项式核函数与径向基核函数的效果较好,其中,多项式核函数的精度更高,为92.77%。研究表明,利用高光谱成像技术能够准确地识别刺五加的健康叶片和患病叶片,为实现自动诊断药用植物叶片病害提供新方法。