Second Order Training of a Smoothed Piecewise Linear Network

In this paper, we introduce a smoothed piecewise linear network (SPLN) and develop second order training algorithms for it. An embedded feature selection algorithm is developed which minimizes training error with respect to distance measure weights. Then a method is presented which adjusts center vector locations in the SPLN. We also present a gradient method for optimizing the SPLN output weights. Results with several data sets show that the distance measure optimization, center vector optimization, and output weight optimization, individually and together, reduce testing errors in the final network.     

基于选择性集成策略的嵌入式网络流特征选择

机器学习在网络流量分类中存在特征选择度量指标单一、类别不平衡和概念漂移等问题,使得模型复杂度提高、泛化能力下降.该文提出基于选择性集成策略的嵌入式特征选择方法,根据选择性集成策略选取部分特征选择器集成,再改进序列前向搜索和封装器组合方法二次搜索最优特征子集.实验结果表明该算法在保证分类效果的同时有效降低了特征子集复杂度,从而达到了分类效果、效率和稳定性的最优平衡.     

基于分段线性插值的过程神经网络训练

过程神经元网络的输入为时变连续函数,不能直接输入离散样本。针对该问题,提出一种基于分段线性插值函数的过程神经网络训练方法。将样本函数、过程神经元权函数的离散化数据插值为分段表示的线性函数,计算样本函数与权值函数乘积在给定采样区间上的积分,将此积分值提交给网络的隐层过程神经元,并计算网络输出。实验结果证明了该方法的有效性。     

模糊粗糙神经网络特征选择方法研究

实际采集的数据中往往存在模糊不确定性和粗糙不确定性,为全面度量数据的不确定性,引入了模糊粗糙集中的模糊粗糙隶属函数概念,并结合容错能力较强的神经网络设计了一种新的模糊粗糙神经网络.该网络不仅训练速度快,且具有较好的分类效果.利用该网络设计了一种新的特征选择算法,根据精度下降指标对输入节点进行结构修剪,实现最优特征子集的搜索.通过UCI数据集实验,并与RBF网络选择结果进行比较,表明该算法具有精度高、速度快、泛化性能好等优点,是有效的.     

A Quick Search Method for Audio Signals Based on a Piecewise Linear Representation of Feature Trajectories

This paper presents a new method for a quick similarity-based search through long unlabeled audio streams to detect and locate audio clips provided by users. The method involves feature-dimension reduction based on a piecewise linear representation of a sequential feature trajectory extracted from a long audio stream. Two techniques enable us to obtain a piecewise linear representation: the dynamic segmentation of feature trajectories and the segment-based Karhunen-Loeve (KL) transform. The proposed search method guarantees the same search results as the search method without the proposed feature-dimension reduction method in principle. Experimental results indicate significant improvements in search speed. For example, the proposed method reduced the total search time to approximately 1/12 that of previous methods and detected queries in approximately 0.3 s from a 200-h audio database.     

基于SAC的特征选择算法

特征选择通过移除不相关和冗余的特征来提高学习算法的性能。基于进化算法在求解优化问题时表现出的优越性能,提出FSSAC特征选择方法。新的初始化策略和评估函数使得SAC能将特征选择作为离散空间搜索问题来解决,利用特征子集的准确率指导SAC的采样阶段。在实验阶段,FSSAC结合SVM,J48和KNN分类器,通过UCI数据集完成验证,并与FSFOA,HGAFS,PSO等算法进行了比较。实验结果表明,FSSAC可以提高分类器的分类准确率,且具有良好的泛化性能。除此之外,对FSSAC和其他算法在特征空间维度缩减情况方面做了对比。     

Approximating Points by a Piecewise Linear Function

Approximating points by piecewise linear functions is an intensively researched topic in computational geometry. In this paper, we study, based on the uniform error metric, an array of variations of this problem in 2-D and 3-D, including points with weights, approximation with violations, using step functions or more generally piecewise linear functions. We consider both the min-# (i.e., given an error tolerance ?, minimizing the size k of the approximating function) and min-? (i.e., given a size k of the approximating function, minimizing the error tolerance ?) versions of the problems. Our algorithms either improve on the previously best-known solutions or are the first known results for the respective problems. Our approaches are based on interesting geometric observations and algorithmic techniques. Some data structures we develop are of independent interest and may find other applications.     

Feature Selection Using Probabilistic Neural Networks

Selection of input variables (features) is a key stage in building predictive models. As exhaustive evaluation of potential feature sets using full non-linear models is impractical, it is common practice to use simple fast-evaluating models and heuristic selection strategies. This paper discusses a fast, efficient, and powerful non-linear input selection procedure using a combination of probabilistic neural networks and repeated bitwise gradient descent with resampling. The algorithm is compared with forward selection, backward selection and genetic algorithms using a selection of real-world data sets. The algorithm has comparative performance and greatly reduced execution time with respect to these alternative approaches.     

神经网络分类器的特征提取和优选

结合木质胶合体缺疵质检过程,论述了用类内方差、类间方差,特征相关度三个目标函数综合测度图像特征差异的技术方法,从而实现了对神经网络输入层神经元的优选,降低了网络规模,提高了分类性能.     

Wrapper–Filter Feature Selection Algorithm Using a Memetic Framework

This correspondence presents a novel hybrid wrapper and filter feature selection algorithm for a classification problem using a memetic framework. It incorporates a filter ranking method in the traditional genetic algorithm to improve classification performance and accelerate the search in identifying the core feature subsets. Particularly, the method adds or deletes a feature from a candidate feature subset based on the univariate feature ranking information. This empirical study on commonly used data sets from the University of California, Irvine repository and microarray data sets shows that the proposed method outperforms existing methods in terms of classification accuracy, number of selected features, and computational efficiency. Furthermore, we investigate several major issues of memetic algorithm (MA) to identify a good balance between local search and genetic search so as to maximize search quality and efficiency in the hybrid filter and wrapper MA     

无监督环境下基于聚类集成的特征选择

无监督学习环境下的特征选择往往无法取得像有监督学习环境下那样令人满意的效果.文章提出了一种无监督环境下特征选择的方法,能够根据特征之间的相关性对特征进行聚类,通过选择聚类中那些与该类内其他特征相关性最大的特征作为精简特征集,因此不需要进行特征空间的搜索,同时可以获得更有意义的分类信息.     

基于遗传算法的特征选择方法

特征提取广泛应用于模式识别、知识发现、机器学习等诸多领域,并受到了越来越多的关注犤1犦。对于一个给定的待分类模式,特征提取要求人们从大量的特征中选取一个最优特征子集,以代表被分类的模式。该文对特征提取这一组合优化及多目标优化问题提出了基于遗传算法的解决方法,把遗传算法作为识别或分类系统的“前端”,找出代表问题空间的最优特征子集,以大大降低分类系统的搜索空间,从而提高搜索效率。     

DEA-Based Piecewise Linear Discriminant Analysis

Nonlinear classification models have better classification performance than the linear classifiers. However, for many nonlinear classification problems, piecewise-linear discriminant functions can approximate nonlinear discriminant functions. In this study, we combine the algorithm of data envelopment analysis (DEA) with classification information, and propose a novel DEA-based classifier to construct a piecewise-linear discriminant function, in this classifier, the nonnegative conditions of DEA model are loosed and class information is added; Finally, experiments are performed using a UCI data set to demonstrate the accuracy and efficiency of the proposed model.     

最小二乘法分段直线拟合

曲线拟合是图像分析中非常重要的描述符号。最常用的曲线拟合方法是最小二乘法,然而一般的最小二乘法有一定的局限性,已经有不少学者对其进行了一些改进。进一步对最小二乘法进行改进,提出一种新的分段直线拟合算法来代替多项式曲线拟合,以达到简化数学模型的建立和减少计算的目的,使其能够更好地对点序列进行拟合。     

卷积神经网络特征重要性分析及增强特征选择模型

卷积神经网络等深度神经网络凭借着其强大的表达能力、突出的分类性能,已在不同领域内得到了广泛应用.当面对高维特征时,深度神经网络通常被认为具有较好的鲁棒性,能够隐含地对特征进行选择,但由于网络参数巨大,如果数据量达不到足够的规模,则会导致学习不充分,因而可能无法达到最优的特征选择.而神经网络的黑箱特性使得无法观测神经网络选择了哪些特征,也无法评估其特征选择的能力.为此,以卷积神经网络为例,首先研究如何显式地表达神经网络中的特征重要性,提出了基于感受野的特征贡献度分析方法;其次,将神经网络特征选择与传统特征评价方法进行对比分析发现,在非海量样本的情况下,传统特征评价方法对高重要性特征和噪声特征的识别能力反而能够超过神经网络.因此,进一步地提出了卷积神经网络增强特征选择模型,将传统特征评价方法对特征重要性的理解结合到神经网络的学习过程中,以辅助深度神经网络进行特征选择.在基于文本的社交媒体用户属性建模任务下进行了对比实验,结果验证了该模型的有效性.     

基于复杂网络的情感分类特征选择

首先针对公共情感词典对专业领域适用性较低问题,以公共情感词典作为种子情感词典,以评论语料库中未出现在公共情感词典中的形容词作为候选情感词,在此基础之上利用点互信息理论构建专业领域的情感词典。其次针对在线评论情感分类问题,利用复杂网络理论提出了一种新的情感分类特征选择算法,改进了传统特征选择算法忽略特征语义相关信息,遗漏评论情感资源的问题。通过构建候选特征词关系网络,利用复杂网络节点重要性理论,考虑节点的局部和全局重要性,提出了利用网络节点的度中心性、介数中心性和接近中心性综合衡量节点重要性来选择情感分类特征的算法NTFS(Complex network feature selection)。最后以iPhone手机的在线评论为实验数据,利用SVM、NNET、NB分类器对比了NTFS、GI、CHI传统特征选择方法,实验证明NTFS在分类性能上优于GI,CHI算法。     

基于特征选择的网络入侵检测模型研究

为了有效从收集的恶意数据中选择特征去分析,保障网络系统的安全与稳定,需要进行网络入侵检测模型研究;但目前方法是采用遗传算法找出网络入侵的特征子集,再利用粒子群算法进行进一步选择,找出最优的特征子集,最后利用极限学习机对网络入侵进行分类,但该方法准确性较低;为此,提出一种基于特征选择的网络入侵检测模型研究方法;该方法首先以增强寻优性能为目标对网络入侵检测进行特征选择,结合分析出的特征选择利用特征属性的Fisher比构造出特征子集的评价函数,然后结合计算出的特征子集评价函数进行支持向量机完成对基于特征选择的网络入侵检测模型研究方法;仿真实验表明,利用支持向量机对网络入侵进行检测能有效地提高入侵检测的速度以及入侵检测的准确性。     

基于特征选择的网络入侵检测模型

研究网络安全问题,网络入侵手段多样,特征多,存在大量不利的冗余特征,传统网络入侵检测不考虑特征冗余,检测效率和正确论低。为更一步提高了网络安全,提出一种特征选择的网络入侵检测模模型。采用粒子群算法对网络系统状态特征和支持向量机参数进行同步选择,找到最优网络入侵检测模型特征和模型参数,降低了模型的输入样本维数。仿真结果表明,改进算法可降低特征维数,消除了不利于提高检测结果的冗余特征,并提高了网络入侵检测正确率,适合于小样本、实时要求高的网络入侵检测。     

一种面向网络入侵检测的特征选择方法

在网络入侵检测中,不相关或冗余的特征使得检测变得越来越困难,为了提高检测的精度和效率,提出了一种新的网络入侵检测的特征选择方法.该方法首先利用粗糙集理论的特性对特征进行筛选;然后利用遗传算法在解决NP问题上的并行性、鲁棒性和全局优化搜索等特点,在剩余的特征子集中寻找最优子集.考虑到早熟问题会使遗传算法陷入局部最优,采用对种群聚类的方式建立自适应的交叉、变异率,种群个体交叉时在不同的类内随机选择从而保证群体多样性,每次迭代均保留父代的最优个体.在入侵检测的经典数据集KDD CUP 99上检验了算法的有效性,使用SVM分类器对选出的特征子集进行性能评估.实验结果表明,该方法与相关研究对比提高了入侵检测系统的精度和效率.