一种新的改进AdaBoost弱分类器训练算法

AdaBoost是机器学习中比较流行的分类算法.通过研究弱分类器的特性,提出了两种新的弱分类器的阈值和偏置计算方法,二者可以使弱分类器识别率大于50%,从而保证在弱分类器达到一定数目的情况下,AdaBoost训练收敛.对两种阈值和偏置计算方法的仿真实验结果表明,在错分率降可接受的范围内,二者均使用较少的弱分类器便可获得高识别率的强分类器.     

多标签代价敏感分类集成学习算法

尽管多标签分类问题可以转换成一般多分类问题解决,但多标签代价敏感分类问题却很难转换成多类代价敏感分类问题.通过对多分类代价敏感学习算法扩展为多标签代价敏感学习算法时遇到的一些问题进行分析,提出了一种多标签代价敏感分类集成学习算法.算法的平均错分代价为误检标签代价和漏检标签代价之和,算法的流程类似于自适应提升（Adaptive boosting,AdaBoost）算法,其可以自动学习多个弱分类器来组合成强分类器,强分类器的平均错分代价将随着弱分类器增加而逐渐降低.详细分析了多标签代价敏感分类集成学习算法和多类代价敏感AdaBoost算法的区别,包括输出标签的依据和错分代价的含义.不同于通常的多类代价敏感分类问题,多标签代价敏感分类问题的错分代价要受到一定的限制,详细分析并给出了具体的限制条件.简化该算法得到了一种多标签AdaBoost算法和一种多类代价敏感AdaBoost算法.理论分析和实验结果均表明提出的多标签代价敏感分类集成学习算法是有效的,该算法能实现平均错分代价的最小化.特别地,对于不同类错分代价相差较大的多分类问题,该算法的效果明显好于已有的多类代价敏感AdaBoost算法.     

一种限制输出模型规模的集成进化分类算法

AdaBoost算法是一种典型的集成学习框架,通过线性组合若干个弱分类器来构造成强学习器,其分类精度远高于单个弱分类器,具有很好的泛化误差和训练误差。然而AdaBoost 算法不能精简输出模型的弱分类器,因而不具备良好的可解释性。本文将遗传算法引入AdaBoost算法模型,提出了一种限制输出模型规模的集成进化分类算法(Ensemble evolve classification algorithm for controlling the size of final model,ECSM)。通过基因操作和评价函数能够在AdaBoost迭代框架下强制保留物种样本的多样性,并留下更好的分类器。实验结果表明,本文提出的算法与经典的AdaBoost算法相比,在基本保持分类精度的前提下,大大减少了分类器数量。     

基于EREF的PSO-AdaBoost训练算法*

针对基于PSO的AdaBoost算法(PSO-AdaBoost)的不足,分析了传统目标函数不能适应多个弱分类器拥有相同最小错误率时弱分类器的选择问题,提出了解决这一问题的有效方法。新方法使用特征值和阈值的绝对值差衡量错分样本的错误程度,结合相对熵理论形成PSO算法的适应度函数,使其根据错分样本的错误程度挑选最佳弱分类器。实验结果表明,所提算法具有较高的检测率和较小的泛化错误。     

标记错分样本的AdaBoost算法

提出一种新的标记迭代过程中错分样本的AdaBoost算法(MWBoost),该算法通过在提升过程中,把上一个分类器错分的样本全部参入到下一个分类器的训练中,并在分类正确的样本中进行重采样,从而使得后一轮提升中分类器能够更快速地关注那些难以分类的样本.该算法在UCI的多个数据集上进行了测试,并且与传统的AdaBoost算法进行了比较,实验结果表明,新的算法具有更好的分类精度.     

基于信息熵的RVM-AdaBoost组合分类器

针对AdaBoost算法不能有效提高RVM分类性能的问题,提出一种基于信息熵的RVM与AdaBoost组合分类器。依据RVM输出的后验概率来定义样本的信息熵,信息熵越高的样本越容易错分。提出使用自适应信息熵阈值对数据进行筛选,筛选出的数据使用基于AdaBoost算法的集成分类器进行分类,样本的分类结果由RVM与集成分类器组合给出。把未筛选出且分类错误的极少样本作为噪声对待,增强了组合分类器的稳定性,避免了随着AdaBoost算法迭代次数增加集成分类器出现退化的现象。使用UCI数据集从分类正确率、分类效率和稳定性三方面对提出的组合分类器进行验证,实验结果表明了此分类器的有效性。     

一种改进的AdaBoost算法在人脸检测系统中的应用

针对复杂背景条件下人脸检测的检测率低、速度慢的问题,提出了一种改进的AdaBoost算法,与遗传算法相结合,产生了一种识别率高、泛化能力好的强分类器,文中称之为GA-AdaBoost算法。该算法首先训练多个支持向量机作为弱分类器,然后用AdaBoost算法将多个弱分类器组合成一个强分类器,在组合的同时采用遗传算法对各弱分类器的权值进行全局寻优。最后,通过试验与传统AdaBoost进行对比,表明了该算法具有识别率高和速度快的优越性。     

快速多分类器集成算法研究

研究快速多分类器集成算法。对多分类器集成需选定一定数量的弱分类器,再为每个弱分类器分配一定权重。在选择弱分类器时,通过计算每个弱分类器在全部训练样本集上的分类错误率,对其进行排序,挑选出分类效果最好的若干弱分类器。在多分类器权重分配策略上,提出2种权重分配方法：Biased AdaBoost算法与基于差分演化的多分类器集成算法。在人脸数据库上的实验结果表明,与经典AdaBoost算法相比,该算法能有效降低训练时间,提高识别准确率。     

基于改进AdaBoost算法的人脸检测

研究人脸识别实现自动化检测,针对实时定位准确识别人脸,采用传统AdaBoost算法构建人脸检测器时存在的过拟合现象和特征冗余缺欠,提出一种自适应样本权重更新规则和遗传算法的改进AdaBoost人脸检测方法.可把正负样本错分率引入样本权重更新过程,将分类效果反馈给分类器,实现对分类器结构的有效控制.用遗传算法进一步优化所选特征及其参数,达到使用较少的弱分类器实现高检出率和低误判率的双重要求.仿真结果表明,与传统AdaBoost算法相比,采用文中算法训练人脸检测器可有效避免样本权重扭曲现象,消除分类器冗余,在保证较高检出率的同时降低误检率,使人脸检测更加快速和精确.     

基于相关性的AdaBoost人脸检测算法

为提高传统AdaBoost算法的集成性能,降低算法复杂度,提出2种基于分类器相关性的AdaBoost算法。在弱分类器的训练过程中,加入Q统计量进行判定。每个弱分类器的权重更新不仅与当前分类器有关,而且需要考虑到前面的若干分类器,以有效降低弱分类器间的相似性,剔除相似特征。仿真结果表明,该算法具有更好的检测率,同时可降低误检率,改进分类器的整体性能。     

Structural consistency: enabling XML keyword search to eliminate spurious results consistently

XML keyword search is a user-friendly way to query XML data using only keywords. In XML keyword search, to achieve high precision without sacrificing recall, it is important to remove spurious results not intended by the user. Efforts to eliminate spurious results have enjoyed some success using the concepts of LCA or its variants, SLCA and MLCA. However, existing methods still could find many spurious results. The fundamental cause for the occurrence of spurious results is that the existing methods try to eliminate spurious results locally without global examination of all the query results and, accordingly, some spurious results are not consistently eliminated. In this paper, we propose a novel keyword search method that removes spurious results consistently by exploiting the new concept of structural consistency. We define structural consistency as a property that is preserved if there is no query result having an ancestor-descendant relationship at the schema level with any other query results. A naive solution to obtain structural consistency would be to compute all the LCAs (or variants) and then to remove spurious results according to structural consistency. Obviously, this approach would always be slower than existing LCA-based ones. To speed up structural consistency checking, we must be able to examine the query results at the schema level without generating all the LCAs. However, this is a challenging problem since the schema-level query results do not homomorphically map to the instance-level query results, causing serious false dismissal. We present a comprehensive and practical solution to this problem and formally prove that this solution preserves structural consistency at the schema level without incurring false dismissal. We also propose a relevance-feedback-based solution for the problem where our method has low recall, which occurs when it is not the user’s intention to find more specific results. This solution has been prototyped in a full-fledged object-relational DBMS Odysseus developed at KAIST. Experimental results using real and synthetic data sets show that, compared with the state-of-the-art methods, our solution significantly (1) improves precision while providing comparable recall for most queries and (2) enhances the query performance by removing spurious results early.     

What users see - Structures in search engine results pages

This paper investigates the composition of search engine results pages. We define what elements the most popular web search engines use on their results pages (e.g., organic results, advertisements, shortcuts) and to which degree they are used for popular vs. rare queries. Therefore, we send 500 queries of both types to the major search engines Google, Yahoo, Live.com and Ask. We count how often the different elements are used by the individual engines. In total, our study is based on 42,758 elements. Findings include that search engines use quite different approaches to results pages composition and therefore, the user gets to see quite different results sets depending on the search engine and search query used. Organic results still play the major role in the results pages, but different shortcuts are of some importance, too. Regarding the frequency of certain host within the results sets, we find that all search engines show Wikipedia results quite often, while other hosts shown depend on the search engine used. Both Google and Yahoo prefer results from their own offerings (such as YouTube or Yahoo Answers). Since we used the .com interfaces of the search engines, results may not be valid for other country-specific interfaces.     

On decidability and closure properties of language classes with respect to bio-operations

We present general results that are useful in showing closure and decidable properties of large classes of languages with respect to biologically-inspired operations. We use these results to prove new decidability results and closure properties of some classes of languages under bio-operations such hairpin-inversion, the recently studied operation of pseudo-inversion, and other bio-operations. We also provide techniques for proving undecidability results. In particular, we give a new approach for proving the undecidability of problems for which the usual method of reduction to the undecidability of the Post Correspondence Problem seems hard to apply. Our closure and decidability results strengthen or generalize previous results.     

基于数据库二进制日志的竞赛式仲裁优化方案

在拟态防御理论中,仲裁模型在一定程度上决定了拟态系统的整体安全性和执行效率,而仲裁策略作为仲裁模型中的关键环节,会对裁决结果的正确性产生直接影响.针对竞赛式仲裁模型中由差模逃逸造成的裁决结果异常问题,提出一种竞赛式仲裁优化方案,采用异构数据库执行体的二进制日志匹配结果对仲裁结果进行校验,保证裁决结果的正确性.实验结果表...     

元搜索引擎结果集成算法

对于元搜索引擎的集成方法有很多,但是多数只考虑到客观因素,而没有考虑到用户因素。不管生成的结果在数据上有多么好,只有用户在最靠前的位置找到自己需要结果的集成方法,才是好的算法。本篇文章介绍了一种新算法,该算法在考虑到用户所查询条目同独立搜索引擎返回结果的相关性和搜索引擎数据库的影响因子的情况下,加入了用户反馈因素。用户反馈因素的加入使得该算法产生的结果更贴近用户的需要,可以根据用户对所搜索出来的结果的关注程度来调整结果的排序,使排序的结果更加优化。     

DynaForm在汽车顶盖重力变形评估中的应用

针对大型面板的重力变形在整车车型设计和生产过程中易被忽略的问题,用DynaForm对某车型的顶盖进行重力变形评估,并验证软件评估结果与实验结果的一致性.结果表明:DynaForm的模拟结果与实验结果基本符合,零件的重力变形评估意义重大.研究结果对于DynaForm在零件重力变形方面的应用和实际生产具有参考和指导意义.     

含零漂的遥测加速度振动信号时域积分方法研究

提出通过遥测加速度振动信号时域数值积分和最小二乘相结合的方法消除零漂对积分结果精度的影响,即采用最小二乘原则对加速度振动信号时域数值积分结果根据其包含的趋势项形式进行多项式拟合,获得修正参数,进一步对积分结果进行修正,获取遥测速度和位移振动信号的修正值。方法在仿真信号上进行了应用,修正结果和真实结果的误差较小,结果精度较高,说明方法的有效性,在此基础上将方法在遥测加速度振动信号的处理上进行了应用,鉴于方法模型的在仿真信号上的有效性,可以推断获取的遥测速度和位移振动信号的修正结果具有较高的置信度。     

数字图像净化在乐谱识别中的应用研究

本文针对电子音乐制作中扫描结果不理想而影响识别效果的问题，提出了对乐谱的初始扫描结果进行预处理的构思，借助专业知识分析了预处理．的工作原理。给出了具体的实现过程。实验结果表明。对乐谱的扫描结果进行必要的预处理能提高乐谱识别的准确率，并取得满意的演奏效果，从技术上对常用音乐制作软件的功能起到很好的补充、辅助作用。     

Keyword advertising is not what you think: Clicking and eye movement behaviors on keyword advertising

This study examined the behavior of online searchers in relation to keyword advertising according to the theory of advertising avoidance. A total of 451 volunteers were recruited for an experiment. A computer program and an eye-tracking device were used to measure the number of clicks and eye movements. The findings show that the number of clicks for to obtain organic search results is higher than that for keyword advertising. There is no difference in observation count between the area of keyword advertising placed above the organic search results and the area of the organic search results themselves. However, observation counts for the organic search results and keyword advertising placed above the organic search results are higher than for the keyword advertising placed at the right-hand side of the page. Searchers seem to spend the longest observation time on the organic search results, then on the keyword advertising placed above the organic search results, and finally on the keyword advertising placed at the right-hand side of the page.