Hadamard 纠错码结合支持向量机在多分类问题中的应用

多分类问题一直是模式识别领域的一个热点,本文提出了将Hadamard纠错码同二元分类器相结合的方法来解决此问题,相对于其它类型的纠错码多分类器法,该方法的实现简单快捷,且更容易构造出性能优越的纠错码本.本文将Hadamard纠错码和支持向量机相结合,应用于说话人辨认这样一个多分类问题中,并同传统的"1对余"的多类推广方式进行了比较.实验结果表明在多分类任务中,Hadamard纠错码对于不同的类别都表现出了很强的分类能力,且性能优于"1对余"法,对于类间码字的不同分配方式也具有良好的鲁棒性.     

基于ROC的三元再编码研究

针对三元编码矩阵中基分类器不包含被忽略样本类别先验知识的问题,该文提出一种基于接收机工作特性(ROC)曲线的矩阵再编码方法。首先基于ROC曲线寻找构造拒绝域的阈值对,从而获得最优分类器;然后利用最优分类器对训练样本中被忽略的类别进行分类,将经典的二值输出变为三值输出,从而对初始编码矩阵的码元0进行重新编码。在解码阶段,采用经典的汉明距离解码方法对未知样本进行决策。该方法能够避免基分类器的二次训练,适用于任意的三元纠错输出编码,具有良好的普适性和实用性。基于人工和UCI公共数据集的实验结果表明该方法简单高效,在不增加训练时间的基础上,能够提高解码的速度和精度,促进分类效果的提升。     

基于神经网络的纠错输出编码方法研究

构造基于数据编码矩阵是目前利用纠错输出编码解决多类分类问题的研究重点.为此提出利用单层感知器作为学习框架,结合解码策略把输出编码矩阵各码元值映射为感知器网络中的权值,同时引入含权值取值约束的目标函数作为该网络代价函数,并对其进行学习,最终得到基于子类划分的数据编码矩阵.实验中利用人工数据集和UCI数据集并选择线性逻辑分类器作为基分类器分别进行测试,通过与几种经典编码方法比较,结果表明该编码方法能在编码长度较小情况下得到更好的分类效果.     

Image classification for content-based indexing

Grouping images into (semantically) meaningful categories using low-level visual features is a challenging and important problem in content-based image retrieval. Using binary Bayesian classifiers, we attempt to capture high-level concepts from low-level image features under the constraint that the test image does belong to one of the classes. Specifically, we consider the hierarchical classification of vacation images; at the highest level, images are classified as indoor or outdoor; outdoor images are further classified as city or landscape; finally, a subset of landscape images is classified into sunset, forest, and mountain classes. We demonstrate that a small vector quantizer (whose optimal size is selected using a modified MDL criterion) can be used to model the class-conditional densities of the features, required by the Bayesian methodology. The classifiers have been designed and evaluated on a database of 6931 vacation photographs. Our system achieved a classification accuracy of 90.5% for indoor/outdoor, 95.3% for city/landscape, 96.6% for sunset/forest and mountain, and 96% for forest/mountain classification problems. We further develop a learning method to incrementally train the classifiers as additional data become available. We also show preliminary results for feature reduction using clustering techniques. Our goal is to combine multiple two-class classifiers into a single hierarchical classifier.     

一种基于证据理论的多类半监督分类算法

为了提高多类半监督分类的性能,提出了一种基于证据理论的多类协同森林算法（DSM-Co-Forest）.首先,通过"多对多"模式将有标记的多类数据随机拆分为多个二类数据集,并以此训练二类基分类器;然后,利用多个基分类器同时对未标记样本进行预测,并利用证据组合算法挑选出可信度较高的未标记样本;最后,将高可信度的未标记样本加入到原训练样本中,以迭代更新其他的基分类器,从而提高分类器的整体性能.通过在一些公共数据集上进行实验,并与其他半监督分类算法进行对比,验证了所提算法的可行性和有效性.     

ECOC多类分类研究综述

纠错输出编码能有效地将多类问题转化为二类问题进行求解,已受到国内外从事机器学习的研究者们的重视,并使其成为多类分类领域的研究热点.本文首先分析了ECOC多类分类的原理和框架,指出解决ECOC多类分类问题的关键在于解码策略和编码策略的确定;然后从这两个关键点出发综述了ECOC多类分类的最新进展和应用领域;最后指出了目前存在的问题以及下一步研究方向.论文研究成果将为基于ECOC多类分类方法在实际应用过程中起借鉴和参考作用.     

基于修正核函数SVM的一维距离像识别

支持向量机的识别性能很大程度上依赖于核函数的使用。根据黎曼几何理论,提出了一种新的保角变换,对核函数进行数据依赖性改进。该方法通过扩大分类边界处的黎曼张量,使得分类间隔扩大,从而提高支持向量机的分类能力。针对多类舰船目标的识别,利用聚类分析中的均值距离来生成二叉树,将分类器分布在各个节点上,构成多分类支持向量机。对四类舰船目标仿真实验的结果表明,该分类方法无论识别率还是识别速度都具有优势。     

Study on the classification of multi-spectral images based on a FSVM multi-class classifier with the binary tree

Due to the features of the multi-spectral images, the result with the usual methods based on the support vector machine (SVM) and binary tree is not satisfactory. In this paper, a fuzzy SVM multi-class classifier with the binary tree is proposed for the classification of multi-spectral images. The experiment is conducted on a multi-spectral image with 6 bands which contains three classes of terrains. The experimental results show that this method can improve the segmentation accuracy. 更多还原     

Important citation identification using sentiment analysis of in-text citations

Citation represents the relationship between the cited and the citing document and vice versa. Citations are widely used to measure the different aspects of knowledge-based achievements such as institutional ranking, author ranking, the impact factor of the journal, research grants, and peer judgments. A fair evaluation of research required a quantitative and qualitative assessment of citations. To perform the qualitative analysis of citations, researchers tried to classify the citations into binary classes (i.e., important and non-important). To perform this task, researchers used metadata, content, citations count, cue words or phrases, sentiment analysis, keywords, and machine learning approaches for citation classification. However, the state-of-the-art results of binary classification are inadequate for the calculation of different aspects of the researcher and their work. Therefore, this research proposed an in-text citation sentiment analysis-based approach for binary classification which effectively enhanced the results of the state-of-the-art. In this research, different machine learning-based models are evaluated to determine the in-text citations sentiments. These sentiment results are further used for positive-negative, and neutral citation counts. Furthermore, the scores of cosine similarity between paper citation pairs are also calculated and used as a feature. This sentiment and cosine similarity scores are further used as features in binary classification. The classification is performed through SVM, KLR, and Random Forest. The proposed approach is evaluated and compared with two state-of-the-art approaches on the benchmark dataset. The proposed approach can achieve 0.83 f-measure with the improvement of 13.6% for dataset 1 and 0.67 with an improvement of 8% for dataset two with a random forest classification model.     

基于复合核支持向量回归机的多类分类算法

针对传统支持向量机(SVM)在解决多类分类问题时需要训练多个分类器、存在不可分区域等问题,研究了基于支持向量回归机的多类分类算法。利用回归思想求解多类分类问题,将分类样本作为回归输入,样本的类别标识作为回归输出,通过支持向量回归机训练拟合出各样本与其类别标识之间的函数关系。将待分类样本代入回归函数,对其输出取整后即可得到样本类别。该算法仅使用1个分类器,明显简化了分类过程。另外,引入复合核函数来提高支持向量回归机的性能。采用加州大学欧文分校(UCI)例题库中的多类分类问题进行仿真验证,并将改进算法与传统算法作对比,结果表明改进算法在分类速度和准确率上都有显著提高。     

基于二叉树的SVM多类分类算法

在介绍了几种常用的支持向量机的多类分类方法及分析其存在的问题和缺点的基础上利用类均值距离思想提出了一种新的基于二叉树的多类SVM分类方法.     

基于特征值分解的中心支持向量机算法

针对广义特征值中心支持向量机(GEPSVM)训练和决策过程不一致问题,该文提出一类改进的基于特征值分解的中心支持向量机,简称为IGEPSVM。首先针对二分类问题提出了基于特征值分解的中心支持向量机,然后基于一类对余类策略将其推广到多类分类问题。将GEPSVM求解广义特征值问题转化为求解标准特征值问题,降低了计算复杂度。引入了一个新的参数,可以调节模型的性能,提高了GEPSVM的分类精度。提出了基于IGEPSVM的多类分类算法。实验结果表明,与GEPSVM算法相比较,IGEPSVM不仅提高了分类精度,而且缩短了训练时间。     

Novel speech signal processing algorithms for high-accuracy classification of Parkinson's disease

There has been considerable recent research into the connection between Parkinson's disease (PD) and speech impairment. Recently, a wide range of speech signal processing algorithms (dysphonia measures) aiming to predict PD symptom severity using speech signals have been introduced. In this paper, we test how accurately these novel algorithms can be used to discriminate PD subjects from healthy controls. In total, we compute 132 dysphonia measures from sustained vowels. Then, we select four parsimonious subsets of these dysphonia measures using four feature selection algorithms, and map these feature subsets to a binary classification response using two statistical classifiers: random forests and support vector machines. We use an existing database consisting of 263 samples from 43 subjects, and demonstrate that these new dysphonia measures can outperform state-of-the-art results, reaching almost 99% overall classification accuracy using only ten dysphonia features. We find that some of the recently proposed dysphonia measures complement existing algorithms in maximizing the ability of the classifiers to discriminate healthy controls from PD subjects. We see these results as an important step toward noninvasive diagnostic decision support in PD.     

Automatic bifurcation detection in coronary IVUS sequences

In this paper, we present a fully automatic method which identifies every bifurcation in an intravascular ultrasound (IVUS) sequence, the corresponding frames, the angular orientation with respect to the IVUS acquisition, and the extension. This goal is reached using a two-level classification scheme: first, a classifier is applied to a set of textural features extracted from each image of a sequence. A comparison among three state-of-the-art discriminative classifiers (AdaBoost, random forest, and support vector machine) is performed to identify the most suitable method for the branching detection task. Second, the results are improved by exploiting contextual information using a multiscale stacked sequential learning scheme. The results are then successively refined using a-priori information about branching dimensions and geometry. The proposed approach provides a robust tool for the quick review of pullback sequences, facilitating the evaluation of the lesion at bifurcation sites. The proposed method reaches an F-Measure score of 86.35%, while the F-Measure scores for inter- and intraobserver variability are 71.63% and 76.18%, respectively. The obtained results are positive. Especially, considering the branching detection task is very challenging, due to high variability in bifurcation dimensions and appearance.     

Information–Theoretic Multiclass Classification Based on Binary Classifiers

In this paper, we consider the multiclass classification problem based on sets of independent binary classifiers. Each binary classifier represents the output of a quantized projection of training data onto a randomly generated orthonormal basis vector thus producing a binary label. The ensemble of all binary labels forms an analogue of a coding matrix. The properties of such kind of matrices and their impact on the maximum number of uniquely distinguishable classes are analyzed in this paper from an information-theoretic point of view. We also consider a concept of reliability for such kind of coding matrix generation that can be an alternative to other adaptive training techniques and investigate the impact on the bit error probability. We demonstrate that it is equivalent to the considered random coding matrix without any bit reliability information in terms of recognition rate.     

Application of kernel methods in signals modulation classification

A new approach to common signals classification of relevance vector machine(RVM) was presented and two signal classifiers based on kernel methods of support vector machine(SVM) and RVM were compared and analyzed.First several robust features of signals were extracted as the input of classifiers,then the kernel thought was used to map feature vectors impliedly to the high dimensional feature space,and multi-class RVM and SVM classifiers were designed to complete AM,CW,SSB,MFSK and MPSK signals recognition.Simulation result showed that when chose proper parameter,RVM and SVM had comparable accuracy but RVM had less learning time and basis functions.The classification speed of RVM is much faster than SVM.     

Co-Occurrence Histogram Based Ensemble of Classifiers for Classification of Cervical Cancer Cells

To explore the potential of conventional image processing techniques in the classification of cervical cancer cells, in this work, a co-occurrence histogram method was employed for image feature extraction and an ensemble classifier was developed by combining the base classifiers, namely, the artificial neural network (ANN), random forest (RF), and support vector machine (SVM), for image classification. The segmented pap-smear cell image dataset was constructed by the k-means clustering technique and used to evaluate the performance of the ensemble classifier which was formed by the combination of above considered base classifiers. The result was also compared with that achieved by the individual base classifiers as well as that trained with color, texture, and shape features. The maximum average classification accuracy of 93.44% was obtained when the ensemble classifier was applied and trained with co-occurrence histogram features, which indicates that the ensemble classifier trained with co-occurrence histogram features is more suitable and advantageous for the classification of cervical cancer cells.     

Investigation of the random forest framework for classification of hyperspectral data

Statistical classification of byperspectral data is challenging because the inputs are high in dimension and represent multiple classes that are sometimes quite mixed, while the amount and quality of ground truth in the form of labeled data is typically limited. The resulting classifiers are often unstable and have poor generalization. This work investigates two approaches based on the concept of random forests of classifiers implemented within a binary hierarchical multiclassifier system, with the goal of achieving improved generalization of the classifier in analysis of hyperspectral data, particularly when the quantity of training data is limited. A new classifier is proposed that incorporates bagging of training samples and adaptive random subspace feature selection within a binary hierarchical classifier (BHC), such that the number of features that is selected at each node of the tree is dependent on the quantity of associated training data. Results are compared to a random forest implementation based on the framework of classification and regression trees. For both methods, classification results obtained from experiments on data acquired by the National Aeronautics and Space Administration (NASA) Airborne Visible/Infrared Imaging Spectrometer instrument over the Kennedy Space Center, Florida, and by Hyperion on the NASA Earth Observing 1 satellite over the Okavango Delta of Botswana are superior to those from the original best basis BHC algorithm and a random subspace extension of the BHC.     

基于聚类识别的极化SAR图像分类

This paper presents a novel unsupervised image classification method for Polarimetric Synthetic Aperture Radar (PolSAR) data. The proposed method is based on a discriminative clustering framework that explicitly relies on a discriminative supervised classification technique to perform unsupervised clustering. To implement this idea, an energy function is designed for unsupervised PolSAR image classification by combining a supervised Softmax Regression (SR) model with a Markov Random Field (MRF) smoothness constraint. In this model, both the pixelwise class labels and classifiers are taken as unknown variables to be optimized. Starting from the initialized class labels generated by Cloude-Pottier decomposition and K-Wishart distribution hypothesis, the classifiers and class labels are iteratively optimized by alternately minimizing the energy function with respect to them. Finally, the optimized class labels are taken as the classification result, and the classifiers for different classes are also derived as a side effect. This approach is applied to real PolSAR benchmark data. Extensive experiments justify that the proposed approach can effectively classify the PolSAR image in an unsupervised way and produce higher accuracies than the compared state-of-the-art methods.     

Training Classifiers for Tree-structured Categories with Partially Labeled Data

In this paper we propose a new method for training classifiers for multi-class problems when classes are not (necessarily) mutually exclusive and may be related by means of a probabilistic tree structure. It is based on the definition of a Bayesian model relating network parameters, feature vectors and categories. Learning is stated as a maximum likelihood estimation problem of the classifier parameters. The proposed algorithm is specially suited to situations where each training sample is labeled with respect to only one or part of the categories in the tree. Our experiments on information retrieval scenarios show the advantages of the proposed method.