基于RoughSet的特征集融合PET/CT肺部肿瘤CAD模型

针对肺部肿瘤PET/CT感兴趣区域(ROI)在高维特征表示下存在着特征相关和维数灾难问题,提出了一种基于粗糙集特征集融合的PET/CT肺部肿瘤CAD模型。首先提取肺部肿瘤ROI的8维形状特征、7维灰度特征、3维Tamura纹理特征、56维GLCM特征和24维频域特征,得到98维特征矢量;然后基于遗传算法的知识约简方法和基于属性重要度的启发式算法对提取的特征集合分别进行特征级融合得到特征子集G1、G2、G3,A1、A2、A3,降低特征矢量的维数;再次利用网格寻优算法优化核函数的SVM作为分类器分别进行融合前和融合后的分类识别比较,基于遗传算法的特征集融合和基于属性重要度的特征集融合的分类识别比较2组实验;最后以2 000幅肺部肿瘤的PET/CT图像为原始数据,采用基于粗糙集特征集融合的肺部肿瘤PET/CT计算机辅助诊断模型对肺部肿瘤进行辅助诊断。实验结果表明,经过粗糙集特征集融合的肺部肿瘤诊断识别方法能有效提高肺部肿瘤的诊断正确率,一定程度上降低了特征之间的相关性。     

基于二次互信息特征选择的人脸表情识别研究

针对主动表观模型(AAM)在表情识别中特征点定位不够精确以及特征数据存在冗余性的问题,本文通过对AAM拟合时初始模型的自动调整,提高了定位准确度,使获取的特征更能有效的反映表情的变化;用二次互信息解决特征矢量选择问题,减少了特征维数,再构造支持向量机(SVM)分类器进行表情识别.实验于CAS-PEAL人脸表情库的结果显示本文采用的方法能有效地提高人脸表情识别性能,最高识别率为83.33%.     

基于多特征信息及Ma-Ada多分类器融合的蛋白质结构类预测

蛋白质序列特征表示和机器学习算法是影响蛋白质结构类预测效果好坏的两个重要方面.本研究基于k-字统计频率和k-片段位置分布两种特征提取方法,将分别提取到的氨基酸序列信息和物理化学性质信息同蛋白质二级结构信息进行融合,建立17维和57维的特征信息集,并尝试在Adaboost.M1算法中引入Multi-Agent多智能体融合的思想,提出了一种Ma-Ada多分类器融合算法.该算法作为蛋白质结构类的预测工具,充分挖掘了单分类器度量层信息以及各个单分类器之间的交互融合信息.实验结果表明,Ma-Ada算法在Z277、Z498、1189和D640四个蛋白质数据集的57维特征信息集上的分类率分别达到了91.3％、96.8％、85.3％和87.2％,在17维特征信息集上的分类率也分别达到了90.6％、95.8％、84.8％和88.3％.与其它蛋白质结构类预测方法的结果相比,本方法能够获得较好的分类率.     

基于PCA和LDA方法的肿瘤基因表达谱数据分类

目的基因芯片技术对医学临床诊断、治疗、药物开发和筛选等技术的发展具有革命性的影响。针对高维医学数据降维困难及基因表达谱样本数据少、维度高、噪声大的特点,维数约减十分必要。基于主成分分析（principalcomponentanalysis,PCA）和线性判别分析（1ineardiscriminantanalysis,LDA）方法,有效解决了基因表达谱数据分类问题,并提高了识别率。方法分别引人PCA和LDA方法对基因表达谱数据进行降维,然后用K近邻（K—nearestneighbor,KNN）作为分类器对数据进行分类,并分别在乳腺癌和卵巢癌质谱数据上。结果在两类癌症质谱数据上应用PCA和LDA方法能够有效提取分类特征信息,并在保持较高分类正确率的前提下大幅度降低医学数据的维数。结论利用维数约减的方法对癌症基因表达谱数据进行分类,可辅助临床医生发现新的疾病特征,提高疾病诊断的正确率。     

基于蚁群算法的表面肌电信号特征选择

目的为提高假肢系统对动作信号的识别速度,设计了基于优化蚁群算法（ant colonyoptimization,ACO）的特征选择法,对表面肌电信号（surface electromyography,sEMG）高维特征向量降维以减少计算负担。方法以特征与目标类型之间互信息关系作为启发函数,通过蚁群算法选出最佳特征子集,最后用已训练好的人工神经网络检验其分类性能。结果对10名健康受试者进行了手腕部动作的肌电信号模式分类实验。与传统主成分分析法（principle component analysis,PCA）相比,该算法选出的特征子集提高了识别准确率,并显著降低了原始特征集的特征维数,进而简化分类器的结构,减少计算开销。结论本方法在实时性要求高的肌电控制假肢等系统中具有良好的应用前景。     

基于互信息与主成分分析的运动想象脑电特征选择算法

针对脑机接口中运动想象任务的特征选择问题,提出一种基于互信息与主成分分析的脑电特征选择算法。该算法融入类别信息,用不同运动想象类别条件下特征间的互信息矩阵之和取代传统主成分分析算法中的协方差矩阵,其特征向量表示新的主成分空间内各主成分的方向,特征值则作为评价准则判断主成分维数。对2005年国际BCI竞赛数据集,联合功率谱估计、连续小波变换、小波包分解、Hjorth参数四种方法进行特征提取,采用所提出的算法进行特征选择并与主成分分析算法对比,实验结果表明,所提出算法的降维效果更好,以支持向量机为分类器,相同维数的主成分,所得分类正确率更高。     

脑电信号的小波特征提取及半监督识别方法的研究

特征提取和特征分类是脑机接口中模式识别过程中两个关键的环节。首先,针对脑电信号的非平稳特性,提出基于小波变换系数、系数均值及小波熵相结合的特征提取方法,该方法在特征中加入了脑电信号的能量信息。实验证明,通过该方法获取的P300信号特征量能够更好地表达脑电信号中的瞬变成分,进一步提高了识别率;其次,在模式识别方面,改进了基于自训练半监督的支持向量机算法和基于自训练半监督的K均值聚类算法。在BCI2003竞赛数据集上的实验表明,相比于传统的BP神经网络,两种改进的分类算法在获得了更高的识别率的同时,能够将特征量维数降低一个数量级,明显提高了训练收敛速度,有效增加了基于脑电信号的实时BCI系统的可实现性。     

Feature selection for surface electromyography signal based on ant colony optimization

目的为提高假肢系统对动作信号的识别速度,设计了基于优化蚁群算法(ant colony optimization,ACO)的特征选择法,对表面肌电信号(surface electromyography,sEMG)高维特征向量降维以减少计算负担.方法 以特征与目标类型之间互信息关系作为启发函数,通过蚁群算法选出最佳特征子集,最后用已训练好的人工神经网络检验其分类性能.结果 对10名健康受试者进行了手腕部动作的肌电信号模式分类实验.与传统主成分分析法(principle component analysis,PCA)相比,该算法选出的特征子集提高了识别准确率,并显著降低了原始特征集的特征维数,进而简化分类器的结构,减少计算开销.结论 本方法在实时性要求高的肌电控制假肢等系统中具有良好的应用前景.     

基于随机森林算法的高维脑电特征优选

在基于脑电的脑-机接口研究中,脑电信号的分类是较为重要的部分.从多导脑电中得到大量可用于分类的特征,并对这些特征进行优选是研究热点.本文应用多分类器组合的分类树方法和自助法重采样技术,结合随机特征选择,使用随机森林组合分类器方法对想象运动实验中的高维脑电特征进行分析.根据不同特征在生成森林过程中被选用于分枝次数的不同,提出了一种有效的特征优选方法,并在特征优选的基础上可以进行导联的筛选.     

基于次生特征提取方法预测蛋白质同源寡聚体

寡聚蛋白质相对于单体蛋白质具有许多优势,广泛地参与多种生命活动。本文提出次生特征提取方法,使用支持向量机作为分类器,采用"一对一"的多类分类策略,基于蛋白质一级序列提取特征方法,对四类同源寡聚体进行分类研究。结果表明,在Jackknife检验下,基于次生特征和氨基酸组成成分特征构成的特征集,加权情况下,其总分类精度最高达到了78.41%,比氨基酸组成成分特征提高13.09%,比参考文献最好特征集BG提高了6.86%,比最好原生特征集CM1提高了5.53%。此结果说明次生特征提取方法对于蛋白质同源寡聚体分类是一种非常有效的特征提取方法。     

基于F-score特征选择和支持向量机的P300识别算法

如何从脑电信号中快速准确地识别出P300成分是脑-机接口研究中的一个热点问题.针对P300的识别问题,我们提出了一种将F-score特征选择与支持向量机相结合的判别方法,该方法采用F-score特征选择减少输入特征的维数,以克服支持向量机算法判别速度慢的缺点;然后借助支持向量机算法良好的分类性能实现P300的识别.本文在BCI Competition 2003的P300实验数据集上对该方法进行了验证,结果表明,在5次重复实验中该方法的识别准确率达到了100%,且判别速度与未经特征选择的传统支持向量机算法相比提高了近2倍.     

Feature dimensionality reduction for myoelectric pattern recognition: A comparison study of feature selection and feature projection methods

This study investigates the effect of the feature dimensionality reduction strategies on the classification of surface electromyography (EMG) signals toward developing a practical myoelectric control system. Two dimensionality reduction strategies, feature selection and feature projection, were tested on both EMG feature sets, respectively. A feature selection based myoelectric pattern recognition system was introduced to select the features by eliminating the redundant features of EMG recordings instead of directly choosing a subset of EMG channels. The Markov random field (MRF) method and a forward orthogonal search algorithm were employed to evaluate the contribution of each individual feature to the classification, respectively. Our results from 15 healthy subjects indicate that, with a feature selection analysis, independent of the type of feature set, across all subjects high overall accuracies can be achieved in classification of seven different forearm motions with a small number of top ranked original EMG features obtained from the forearm muscles (average overall classification accuracy >95% with 12 selected EMG features). Compared to various feature dimensionality reduction techniques in myoelectric pattern recognition, the proposed filter-based feature selection approach is independent of the type of classification algorithms and features, which can effectively reduce the redundant information not only across different channels, but also cross different features in the same channel. This may enable robust EMG feature dimensionality reduction without needing to change ongoing, practical use of classification algorithms, an important step toward clinical utility.     

Evolutionary weighting of image features for diagnosing of CNS tumors

This paper concerns an application of evolutionary feature weighting for diagnosis support in neuropathology. The original data in the classification task are the microscopic images of ten classes of central nervous system (CNS) neuroepithelial tumors. These images are segmented and described by the features characterizing regions resulting from the segmentation process. The final features are in part irrelevant. Thus, we employ an evolutionary algorithm to reduce the number of irrelevant attributes, using the predictive accuracy of a classifier ('wrapper' approach) as an individual's fitness measure. The novelty of our approach consists in the application of evolutionary algorithm for feature weighting, not only for feature selection. The weights obtained give quantitative information about the relative importance of the features. The results of computational experiments show a significant improvement of predictive accuracy of the evolutionarily found feature sets with respect to the original feature set.     

Application of the mutual information criterion for feature selection in computer-aided diagnosis.

The purpose of this study was to investigate an information theoretic approach to feature selection for computer-aided diagnosis (CAD). The approach is based on the mutual information (MI) concept. MI measures the general dependence of random variables without making any assumptions about the nature of their underlying relationships. Consequently, MI can potentially offer some advantages over feature selection techniques that focus only on the linear relationships of variables. This study was based on a database of statistical texture features extracted from perfusion lung scans. The ultimate goal was to select the optimal subset of features for the computer-aided diagnosis of acute pulmonary embolism (PE). Initially, the study addressed issues regarding the approximation of MI in a limited dataset as it is often the case in CAD applications. The MI selected features were compared to those features selected using stepwise linear discriminant analysis and genetic algorithms for the same PE database. Linear and nonlinear decision models were implemented to merge the selected features into a final diagnosis. Results showed that the MI is an effective feature selection criterion for nonlinear CAD models overcoming some of the well-known limitations and computational complexities of other popular feature selection techniques in the field.     

基于变尺度符号化补偿传递熵的EEG压力情感分析

基于脑电信号的情感识别,对于相关情感疾病的诊断与治疗有着重要的临床和科研意义。如何有效地提取特征,提高识别率,减少计算时间是研究的重点。从研究脑通道间定向信息交互的角度出发,结合对瞬时因果效应的补偿算法,提出以变尺度符号化补偿传递熵(VSSCTE)为特征的情感分析方法,并以此构建情感因效性脑网络,使用网络测度与ReliefF特征优化选择算法进行通道选择。结果显示,在使用DAEP数据集中处理后的127个压力状态和125个平静状态的数据时,较传统的二元传递熵方法,VSSCTE的特征提取方法在压力和平静情感二分类上的准确率提升约15%,达到96.74%;进行脑电通道优化后,当通道数由32个降至15个时,分类准确率仅下降约2%(分类准确率为94.36%),计算时间从51.27 s降至23.84 s。所提出的VSSCTE脑电特征提取方法可以有效分析情感变化时脑区之间的信息交互,为情感分析和计算提供新的思路。     

Bispectral analysis and genetic algorithm for congestive heart failure recognition based on heart rate variability

This paper proposes a congestive heart failure (CHF) recognition method that includes features calculated from the bispectrum of heart rate variability (HRV) diagrams and a genetic algorithm (GA) for feature selection. The roles of the bispectrum-related features and the GA feature selector are investigated. Features calculated from the subband regions of the HRV bispectrum are added into a feature set containing only regular time-domain and frequency-domain features. A support vector machine (SVM) is employed as the classifier. A feature selector based on genetic algorithm proceeds to select the most effective features for the classifier. The results confirm the effectiveness of including bispectrum-related features for promoting the discrimination power of the classifier. When compared with the other two methods in the literature, the proposed method (without GA) outperforms both of them with a high accuracy of 96.38%. More than 3.14% surpluses in accuracies are observed. The application of GA as a feature selector further elevates the recognition accuracy from 96.38% to 98.79%. When compared to the Isler and Kuntalp's impressive results recently published in the literature that also uses GA for feature selection, the proposed method (with GA) outperforms them with more than 2.4% surpass in the recognition accuracy. These results confirm the significance of recruiting bispectrum-related features in a CHF classification system. Moreover, the application of GA as feature selector can further improve the performance of the classifier.     

Ant colony optimization-based feature selection method for surface electromyography signals classification

This paper presented a new ant colony optimization (ACO) feature selection method to classify hand motion surface electromyography (sEMG) signals. The multiple channels of sEMG recordings make the dimensionality of sEMG feature grow dramatically. It is known that the informative feature subset with small size is a precondition for the accurate and computationally efficient classification strategy. Therefore, this study proposed an ACO based feature selection scheme using the heuristic information measured by the minimum redundancy maximum relevance criterion (ACO-mRMR). The experiments were conducted on ten subjects with eight upper limb motions. Two feature sets, i.e., time domain features combined with autoregressive model coefficients (TDAR) and wavelet transform (WT) features, were extracted from the recorded sEMG signals. The average classification accuracies of using ACO reduced TDAR and WT features were 95.45±2.2% and 96.08±3.3%, respectively. The principal component analysis (PCA) was also conducted on the same data sets for comparison. The average classification accuracies of using PCA reduced TDAR and WT features were 91.51±4.9% and 89.87±4.4%, respectively. The results demonstrated that the proposed ACO-mRMR based feature selection method can achieve considerably high classification rates in sEMG motion classification task and be applicable to other biomedical signals pattern analysis.     

A wavelet-based optimal texture feature set for classification of brain tumours

In this work, the classification of brain tumours in magnetic resonance images is studied by using optimal texture features. These features are used to classify three sets of brain images—normal brain, benign tumour and malignant tumour. A wavelet-based texture feature set is derived from the region of interest. Each selected brain region of interest is characterized with both its energy and texture features extracted from the selected high frequency subband. An artificial neural network classifier is employed to evaluate the performance of these features. Feature selection is performed by a genetic algorithm. Principal component analysis and classical sequential methods are compared against the genetic approach in terms of the best recognition rate achieved and the optimal number of features. A classification performance of 98% is achieved in a genetic algorithm with only four of the available 29 features. Principal component analysis and classical sequential methods require a larger feature set to attain the similar classification accuracy of 98%. The optimal texture features such as range of angular second moment, range of sum variance, range of information measure of correlation II and energy selected by the genetic algorithm provide best classification performance with lower computational effort.     

基于静电力方法的主动轮廓模型的脑部MRI图像分割

提出一种改进的使用主动轮廓线模型分割医学图像的方法.基于Greedy法和静电场模型,对Greedy算法中蛇点的邻域提出了进一步的搜索准则,并给出判定的准则.同时,在预处理后的图像中使用静电力作为图像外力,并介绍了简化计算的方法.对比实验表明了该算法的有效性.     

Identification of signatures in biomedical spectra using domain knowledge

OBJECTIVE: Demonstrate that incorporating domain knowledge into feature selection methods helps identify interpretable features with predictive capability comparable to a state-of-the-art classifier. METHODS: Two feature selection methods, one using a genetic algorithm (GA) the other a L(1)-norm support vector machine (SVM), were investigated on three real-world biomedical magnetic resonance (MR) spectral datasets of increasing difficulty. Consensus sets of the feature sets obtained by the two methods were also assessed. RESULTS AND CONCLUSIONS: Features identified independently by the two methods and by their consensus, determine class-discriminatory groups or individual features, whose predictive power compares favorably with that of a state-of-the-art classifier. Furthermore, the identified feature signatures form stable groupings at definite spectral positions, hence are readily interpretable. This is a useful and important practical result for generating hypothesis for the domain expert.