Splicing-site recognition of rice (Oryza sativa L.)DNA sequences

INTRODUCTIONCorrectlypinpointingsplicing sitesingenomicDNAsequencesisnotaneasytask ,whichisofgreatimportancetothegenomeannotationandgenefinding .Intronsaregenerallydividedinto3classes,namelycalssI,classIIandcommonnu cleuspre mRNA .IntronofclassIandIIcango…     

Splicing-site recognition of rice (<Emphasis Type="Italic">Oryza sativa</Emphasis> L.) DNA sequences by support vector machines

Motivation: It was found that high accuracy splicing-site recognition of rice (Oryza sativa L.) DNA sequence is especially difficult. We described a new method for the splicing-site recognition of rice DNA sequences. Method: Based on the intron in eukaryotic organisms conforming to the principle of GT-AG, we used support vector machines (SVM) to predict the splicing sites. By machine learning, we built a model and used it to test the effect of the test data set of true and pseudo splicing sites. Results: The prediction accuracy we obtained was 87.53% at the true 5′ end splicing site and 87.37% at the true 3′ end splicing sites. The results suggested that the SVM approach could achieve higher accuracy than the previous approaches. Project partially supported by the Start-up Funding of Zhejiang University to Chen Liang-biao     

基于SVM的智能统分自学习系统设计与实现

为了解决传统纸质试卷人工统分过程存在工作量大、错误率高、统分效率低等问题,设计开发一款基于SVM的智能统分自学习系统。该系统由前端用户界面、后台手写分数识别子系统和自学习子系统构成。系统采用C#编程语言和Microsoft Visual Studio软件设计前端用户界面;使用Matlab作为系统运算后台,并构建SVM多分类器识别手写分数;使用C#编程语言设置定时器,在系统空闲时间定时启动Matlab执行自学习程序。经过MNIST数据集的训练和测试,SVM多分类器的测试精度达到97.74%。完成系统设计开发后,使用试卷统分栏图片测试系统。测试结果表明,该系统可以有效实现智能识别、统分栏内手写分数汇总以及自学习功能,并将运行结果清晰准确地显示在前端用户界面上。     

基于改进SVM的人脸表情识别技术研究

结合Gabor小波变换的特征提取算法提出了一种基于决策模板的多分类支持向量机.该方法在对JAFFE基本表情数据库进行训练并测试时获得了较高的正确率,实验结果表明该方法是一种有效的表情识别算法.     

A novel method for detection of hard exudates from fundus images based on SVM and improved FCM

Diabetic retinopathy (DR) is one of the most important causes of visual impairment. Automatic recognition of DR lesions, like hard exudates (EXs), in retinal images can contribute to the diagnosis and screening of the disease. To achieve this goal, an automatically detecting approach based on improved FCM (IFCM) as well as support vector machines (SVM) was established and studied. Firstly, color fundus images were segmented by IFCM, and candidate regions of EXs were obtained. Then, the SVM classifier is confirmed with the optimal subset of features and judgments of these candidate regions, as a result hard exudates are detected from fundus images. Our database was composed of 126 images with variable color, brightness, and quality. 70 of them were used to train the SVM and the remaining 56 to assess the performance of the method. Using a lesion based criterion, we achieved a mean sensitivity of 94.65 and a mean positive predictive value of 97.25 . With an image-based criterion, our approach reached a 100 mean sensitivity, 96.43 mean specificity and 98.21 mean accuracy. Furthermore, the average time cost in processing an image is 4.56 s. The results suggest that the proposed method can efficiently detect EXs from color fundus images and it could be a diagnostic aid for ophthalmologists in the screening for DR.     

基于相关滤波的重检测目标跟踪算法

针对目标跟踪中因严重遮挡、变形、快速运动等因素导致的跟踪失败问题,提出一种基于相关滤波的重检测跟踪算法。首先使用相关滤波算法Staple对目标进行位置估计,然后构造一个检测滤波器对Staple算法跟踪结果进行置信度检测,将检测分数作为跟踪结果的置信度评估结果。若检测分数小于给定阈值,则激活在线SVM分类器对跟踪结果进行重检测。同时用检测滤波器对SVM分类结果进行检测,若检测分数大于Staple跟踪算法检测分数,则采用SVM的跟踪结果。在基准数据集OTB-2013上的实验结果表明,该算法精度达到80.2%,成功率达到60.6%,整体性能优于其它6种对比算法。     

基于RBF核的SVM分类应用研究

支持向量机(Support Vector Machine,SVM)在解决小样本、非线性及高维模式识别中具有优势,但核函数的选取没有定论,且其参数对SVM模型的性能起重要作用。针对这些问题,文章建立了基于SVM的分类模型,并通过UCI数据集验证了径向基核函数(Radial Basis Function,RBF)较其他核函数的有效性,其中核参数的选取采用改进的网格搜索法进行寻优。分类实验结果表明,选择RBF核函数的分类准确度较其他核函数提高了2.5%到35%。     

人脸识别中的PSVM方法

最临近支持向量机Proximal SVM(PSVM)是一种有效的、简单的和快速的近似支持向量机方法,识别效果和标准支持向量机相当,相比之下有较少处理时间．虽然有此优点,它的有效性仅仅是针对维数不高、大样本的数据集,而对于上千维甚至上万维的、小样本的人脸数据库情况没有人给出实验结果．文章把PSVM稍做改变,对四个公开的人脸库进行分类．同时采用几种典型的泛化线性鉴别分析(GLDA)方法,对人脸图像预处理．从识别率和所用的处理时间两方面以及用最近邻及最近特征线分类器进行对比,得出具有较好识别效果和处理时间的方法．     

基于PSO-SVM的电动车铅酸蓄电池SOC预测

为了提高电动车铅酸蓄电池的电池荷电状态(SOC)预测精度,将粒子优化算法(PSO)引入到支持向量机(SVM)中,建立了PSO-SVM电动车铅酸蓄电池SOC预测模型,模型输入量为电池的电压和电流,输出量为SOC。采用PSO算法对SVM的惩罚因子C和径向基函数宽度σ寻优,降低了SVM参数取值的盲目性,提高了预测精度。设计了铅酸蓄电池数据智能采集系统,并进行了实际运行车辆电池数据采集。在advisor2002软件中获取的电池数据和实际车辆电池运行数据的基础上,进行了模型训练和预测。结果表明,PSO-SVM预测模型相对传统的BP、RBF和SVM预测模型具有更好的精度和推广能力,满足了"SOC估算精度小于5%"的要求,从而表明该模型是有效的、可行的,并具有较好的工程实用价值。     

Fault diagnosis of valve clearance in diesel engine based on BP neural network and support vector machine

Based on wavelet packet transformation(WPT), genetic algorithm(GA), back propagation neural network(BPNN)and support vector machine(SVM), a fault diagnosis method of diesel engine valve clearance is presented. With power spectral density analysis, the characteristic frequency related to the engine running conditions can be extracted from vibration signals. The biggest singular values(BSV)of wavelet coefficients and root mean square (RMS)values of vibration in characteristic frequency sub-bands are extracted at the end of third level decomposition of vibration signals, and they are used as input vectors of BPNN or SVM. To avoid being trapped in local minima, GA is adopted. The normal and fault vibration signals measured in different valve clearance conditions are analyzed. BPNN, GA back propagation neural network (GA-BPNN), SVM and GA-SVM are applied to the training and testing for the extraction of different features, and the classification accuracies and training time are compared to determine the optimum fault classifier and feature selection. Experimental results demonstrate that the proposed features and classification algorithms give classification accuracy of 100%.     

一种对fMRI数据分类的加权随机SVM集群算法

如何从小样本、高维度特性的功能磁共振成像（fMRI）数据中识别出内在的脑区活动模式,对理解人脑意义重大。随着模式识别技术和机器学习算法的发展,fMRI的分类研究也引起了人们的重视。提出一种对fMRI数据分类的加权随机SVM集群（WRSVMC）算法。该算法分为两步,首先通过随机选择样本和特征建立多个SVM,以构建集成分类器;然后在投票过程中,对每个SVM赋权重,以优化模型的集成性能。结合fMRI数据和图论特征,采用WRSVMC算法对轻度认知障碍（MCI）患者数据展开分类研究。结果表明,准确率最高可达87.67%。该方法能帮助医师对MCI患者进行辅助诊断。     

基于脑电信号与集成分类器的心理负荷评估

为了精确评估个体心理负荷状态,需要获取目标脑电信号数据,脑电信号是评估脑力负荷变化的重要指标。机器学习和神经网络越来越多地用于脑力负荷分类。利用脑电信号特征可在时域和频域中提取突出信息。因此提出一个结合支持向量机（SVM）与超限学习机（ELM）的混合型脑力负荷分类框架。其中支持向量机作为成员分类器,可在高维EEG特征中查找隐藏信息|超限学习机用于融合成员分类器的输出。将ELM-SVM模型与经典脑力负荷分类器进行比较,得出该模型训练精度准确率为1,且测试精度提升0.1个百分点。     

基于音素的话者特定英语命令识别

1　Introduction　Sincethe 195 0s ,speechrecognitiontechnologies ,bothspeaker dependentandspeaker independent ,withsmallorlargevocabulary ,andusingisolatedorconnectedwords,orcontinuousspeech ,havedevel opedandbeenwidelyapplied .Recentlyithasbecomeadominanttechnologyforhuman machineinterface .Speechrecognitionisbasicallytreatedasaproblemofpatternmatching .Thegoalistotakeonepattern ,i .e .,thespeechsignal,andclassifyitasasequenceofpreviouslylearnedpatterns ,e.g .,wordsorsubwordunitssuchsphonems[1…     

基于行为特征的ATM机用户身份识别研究

传统自动柜员机（ATM）监控系统以摄像为主,不能及时检测用户身份是否异常。提出一种基于行为特征的ATM机用户身份实时识别方法,采集用户输入密码时的触屏行为特征数据,通过SVM分类算法判断该用户行为是否属于合法用户。该方法不仅要求用户输入的账户密码正确,还要求该用户的行为特征与预设定的合法用户行为特征一致。实验结果表明,通过数据预处理和SVM分类算法参数优化后的ATM机用户身份识别系统识别精确度达到97.9769%,比没通过数据预处理和SVM分类算法参数优化后的识别精确度高出4.5769%。     

Mapping paddy rice with multi-date moderate-resolution imaging spectroradiometer （MODIS） data in China

The objective of this study was to obtain spatial distribution maps of paddy rice fields using multi-date moderateresolution imaging spectroradiometer （MODIS） data in China. Paddy rice fields were extracted by identifying the unique characteristic of high soil moisture in the flooding and transplanting period with improved algorithms based on rice growth calendar regionalization. The characteristic could be reflected by the enhanced vegetation index （EVI） and the land surface water index （LSWI） derived from MODIS sensor data. Algorithms for single, early, and late rice identification were obtained from selected typical test sites. The algorithms could not only separate early rice and late rice planted in the same fields, but also reduce the uncertainties. The areal accuracy of the MODIS-derived results was validated by comparison with agricultural statistics, and the spatial matching was examined by ETM＋ （enhanced thematic mapper plus） images in a test region. Major factors that might cause errors, such as the coarse spatial resolution and noises in the MODIS data, were discussed. Although not suitable for monitoring the inter-annual variations due to some inevitable factors, the MODIS-derived results were useful for obtaining spatial distribution maps of paddy rice on a large scale, and they might provide reference for further studies.     

三种方法的NP识别比较实验研究

利用错误驱动法、支持向量机法和隐马尔可模型三种方法对汉语文本进行名词短语识别,对实验进行比较分析,结果表明SVM与HMM的识别效果总体上要好于错误驱动法,HMM法在封闭测试中优势明显.研究表明错误驱动法应用于解决从语料库中学习转换规则的传统问题;SVM方法适用于解决两类别的分类问题;而HMM方法侧重应用在与线性序列相关的现象上.     

Phonological Awareness and Naming Speed in the Prediction of Dutch Children's Word Recognition

Influences of phonological awareness and naming speed on the speed and accuracy of Dutch children's word recognition were investigated in a longitudinal study. The speed and accuracy of word recognition at the ends of Grades 1 and 2 were predicted by naming speed from both the beginning and end of Grade 1, after control for autoregressive relations, kindergarten letter knowledge, and vocabulary knowledge. Phonological awareness at the beginning of Grade 1 predicted only the accuracy of word recognition at the end of Grade 1. No evidence was found for reciprocal influences of word recognition skills on later phonological awareness or naming speed.     

基于多地震属性的储层预测新方法

目前采用地震属性预测储层参数的方法层出不穷,但是这些方法多数是基于单变量、线性的机器学习算法,在已知样本较少的情况下精度得不到保证。为了获取高精度的储层参数,指导油气的勘探开发,迫切需要寻求一种新的方法最大限度地挖掘地震地质信息。支持向量机是以结构风险最小化原则为核心的新型机器学习算法,与传统的机器学习算法相比,其具有基于多变量、小样本、非线性和预测精度高的优点。以渤海湾SZ-361油田Ⅰ油组顶部储层参数预测为例,采用支持向量机算法,得到了较高精度的储层预测结果,证实了支持向量机算法可以应用于油气勘探领域。     

Shoe Shopping and the Reliability Coefficient

Editor's Introduction. Reliability Versus Accuracy: A Critical Distinction Test reliability coefficients traditionally have been used to judge the quality of measurement. And, reliability coefficients of .90 have often been considered adequate to assure the quality for standardized testing and large-scale assessment programs. However, a test reliability of .90 (or above) does not ensure that individual test scores, such as national percentile ranks, are accurate. Consider, for example, a mathematics test with a reliability of .90 and imagine a student taking that test whose true score is at the 50th percentile; that is, we know that the student's actual capability is at that level. The probability is less than one third (.309) that when the student takes the test, he or she will obtain a score within 5 percentile points of his or her true score, the 50th percentile (Rogosa 1999a, 1999b). The following informal example attempts to explain why high test reliability does not indicate good accuracy for an individual score, without the encumbrances of percentile rank scoring, complex measurement models, and other technical detail. Dedicated to Al Bundy-A man who cares as much about good measurement as he does about his own children.