Neural specificity of acupuncture stimulation from support vector machine classification analysis

Acupoint specificity, as a crucial issue in acupuncture neuroimaging studies, is still a controversial topic. Previous studies have generally adopted a block-based general linear model (GLM) approach, which predicts the temporal changes in the blood oxygenation level-dependent signal conforming to the “on-off” specifications. However, this method might become impractical since the precise timing and duration of acupuncture actions cannot be specified a priori. In the current study, we applied a data-driven multivariate classification approach, namely, support vector machine (SVM), to explore the neural specificity of acupuncture at gall bladder 40 (GB40) using kidney 3 (KI3) as a control condition (belonging to different meridians but the same nerve segment). In addition, to verify whether the typical GLM approach is sensitive enough in exploring the neural response patterns evoked by acupuncture, we also employed the GLM method to the same data sets. The SVM analysis detected distinct neural response patterns between GB40 and KI3 — positive predominantly for the GB40, while negative following the KI3. By contrast, group analysis from the GLM showed that acupuncture at these different acupoints can both evoke similar widespread signal decreases in multiple brain regions, and most of these regions were spatially overlapped, mainly distributing in the limbic and subcortical structures. Our findings may provide additional evidence to support the specificity of acupuncture, relevant to its clinical efficacy. Moreover, we also proved that GLM analysis is prone to be susceptible to errors and is not appropriate for detecting neural response patterns evoked by acupuncture stimulation.     

Categorizing Normal and Pathological Voices: Automated and Perceptual Categorization

Objectives

The aims of the present study were to evaluate the accuracy of an elaborated automated voice categorization system that classified voice signal samples into healthy and pathological classes and to compare it with classification accuracy that was attained by human experts.

Material and Methods

We investigated the effectiveness of 10 different feature sets in the classification of voice recordings of the sustained phonation of the vowel sound /a/ into the healthy and two pathological voice classes, and proposed a new approach to building a sequential committee of support vector machines (SVMs) for the classification. By applying “genetic search” (a search technique used to find solutions to optimization problems), we determined the optimal values of hyper-parameters of the committee and the feature sets that provided the best performance. Four experienced clinical voice specialists who evaluated the same voice recordings served as experts. The “gold standard” for classification was clinically and histologically proven diagnosis.

Results

A considerable improvement in the classification accuracy was obtained from the committee when compared with the single feature type-based classifiers. In the experimental investigations that were performed using 444 voice recordings coming from 148 subjects, three recordings from each subject, we obtained the correct classification rate (CCR) of over 92% when classifying into the healthy-pathological voice classes, and over 90% when classifying into three classes (healthy voice and two nodular or diffuse lesion voice classes). The CCR obtained from human experts was about 74% and 60%, respectively.

Conclusion

When operating under the same experimental conditions, the automated voice discrimination technique based on sequential committee of SVM was considerably more effective than the human experts.     

基于Cholesky分解的增量式RELM及其在时间序列预测中的应用

针对应用于混沌时间序列预测的正则极端学习机(RELM)网络结构设计问题,提出一种基于Cholesky分解的增量式RELM训练算法.该算法通过逐次增加隐层神经元的方式自动确定最佳的RELM网络结构,并以Cholesky分解方式计算其输出权值,有效减小了隐层神经元递增过程的计算代价.混沌时间序列预测实例表明,该算法可有效实现最佳RELM网络结构的自动确定,且计算效率高.利用该算法训练后的RELM预测模型具有预测精度高的优点,适用于混沌时间序列预测. 关键词： 神经网络 极端学习机 混沌时间序列 时间序列预测     

具有选择与遗忘机制的极端学习机在时间序列预测中的应用

针对训练样本贯序输入时的极端学习机 (ELM)训练问题,提出一种具有选择与遗忘机制的极端学习机 (SF-ELM),并研究了其在混沌时间序列预测中的应用. SF-ELM以逐次增加新训练样本的方式实现在线训练,通过引入遗忘因子以减弱旧训练样本的影响,同时以泛化能力为判断依据,对其输出权值进行选择性递推更新. 混沌时间序列在线预测实例表明,SF-ELM是一种有效的ELM在线训练模式. 相比于在线贯序极端学习机,SF-ELM具有更快的在线训练速度和更高的在线预测精度,因此更适于混沌时间序列在线预测. 关键词： 混沌时间序列 时间序列预测 神经网络 极端学习机     

基于机器学习方法的丙型肝炎病毒非结构蛋白5B聚合酶抑制剂活性预测

在丙型肝炎病毒(HCV)的基因复制和蛋白质成熟的过程中, 非结构蛋白5B(NS5B)作为RNA依赖的RNA聚合酶起到了重要的作用. 抑制NS5B聚合酶可以阻止丙型肝炎病毒的RNA复制, 因此成为一种治疗丙型肝炎的有效方法. 通过计算机方法进行虚拟筛选和预测NS5B聚合酶抑制剂已经变得越来越重要. 本文主要采用机器学习方法(支持向量机(SVM)、k-最近相邻法(k-NN)和C4.5决策树(C4.5 DT))对已知的丙型肝炎病毒NS5B蛋白酶抑制剂与非抑制剂建立分类预测模型. 1248个结构多样性化合物(552个NS5B抑制剂与696个非NS5B抑制剂)被用于测试分类预测系统, 并用递归变量消除法选择与NS5B抑制剂相关的性质描述符以提高预测精度. 独立验证集的总预测精度为84.1%-85.0%, NS5B抑制剂的预测精度为81.4%-91.7%, 非NS5B抑制剂的预测精度为78.2%-87.2%. 其中支持向量机给出最好的NS5B抑制剂预测精度(91.7%); C4.5决策树给出最好的非NS5B抑制剂预测精度(87.2%); k-最近相邻法给出最好的总预测精度(85.0%). 研究表明机器学习方法可以有效预测未知数据集中潜在的NS5B抑制剂, 并有助于发现与其相关的分子描述符.     

基于紫外光谱-支持向量机对STR的基因分型

利用紫外光谱结合支持向量机(SVM)模式识别原理建立了短串联重复序列(STR)的分型方法.以D5S818基因座的10-10、11-13和13-13三个基因型为研究对象,优化了包含该多态性位点的DNA片段的聚合酶链反应(PCR)的扩增条件和紫外光谱检测条件,获得了优化条件下的待测样本紫外光谱.以该光谱为识别变量,建立了该...     

钢管直线度的机器视觉测量系统设计

针对钢管在空间方向直线度的测量,采用机器视觉方法,通过获取钢管上下边缘图像,求得钢管中心轴线坐标,评定直线度误差.在整体设计过程中,照明系统采用背光照明方式和平行光管光源,采用双高斯结构设计了光学成像系统基本结构,并用Zemax对成像系统进行了优化设计和像质分析.根据钢管边缘图像的特征,采用了一种新方法——相邻行灰度差...     

基于光谱和改进极限学习机的土壤含盐量分析

研究盐碱地的性质、组成,对于生态环境具有重要意义。传统的含盐量测定方法大多基于化学分析,因其成本高、效率低的缺点使得应用于大面积土地的可行性很低。极限学习机（ELM）作为一种基于前馈神经网络构建的机器学习系统,在许多研究中作为一种光谱处理方法被成功运用。为了改进传统的盐碱地含盐量检测方法,采用光谱学结合改进的极限学习机（ELM）模型的方法对盐碱地进行研究。根据镇赉县采集得到的62个土壤表层样本得到对应的光谱反射率和含盐量数据,提出了基于随机值改进粒子群优化算法（RVIPSO-MELM）优化的多层极限学习机模型。首先使用主成分分析提取光谱数据特征,并使用ELM算法对光谱数据建立分类模型,引入改进的粒子群优化算法以提高精度和速度。该模型结合了具有随机值的多层ELM（RV-MELM）和改进PSO算法的多层ELM（IPSO-MELM）二者的优点,在运用启发式算法搜索最优值的同时还具有随机性,提高了模型优化速度,同时以提高模型性能为目的对隐含层之间参数进行优化和选择。并且该模型可以推广到多层,对隐含层之间的参数的两种选择方法,根据经验公式计算和使用改进的启发式算法搜索,进行了提高模型性能和优化时间的讨论,实践结果表明,选择第一层参数使用改进粒子群优化算法,确定随后的隐含层之间参数选择,使用经验公式进行计算得到一种更具现实意义的方法模型。模型在进行启发式搜索最优值之前,利用蒙特卡罗方法确定一个较好的初值,使得模型能保持较高准确率的条件下,优化速度进一步提高。相比于传统方法,这种光谱分析结合ELM的模型节省时间和经济成本,有一定推广意义。     

基于可见光-近红外光谱的煤岩识别方法实验研究

以淮南矿区谢桥矿和潘二矿的煤和岩石样本为研究对象,通过地物光谱仪采集样本反射率光谱曲线,同时检测样本氧化物含量、水分、灰分及挥发分含量,将样本的反射率光谱曲线和样本成分含量分别作为自变量,样本类别“煤”和“岩石”两种矿物类型作为因变量,建立煤和岩石识别模型对煤和岩石进行二分类。该研究主要采用三种模型,分别为主成分分析结合支持向量机(PCA-SVM)、主成分分析结合BP神经网络(PCA-BP)模型和核主成分分析结合支持向量机(KPCA-SVM)模型。结果表明,基于可见光近红外光谱的三个模型中,核主成分分析结合支持向量机模型的识别精度最高,建模平均精度为95.5%,验证平均精度约为90.56%;基于样本成分的三个模型中,核主成分分析结合支持向量机模型的识别精度最高,建模平均精度为98.5%,验证平均精度约为95%。     

Dynamical learning of non-Markovian quantum dynamics

We study the non-Markovian dynamics of an open quantum system with machine learning.The observable physical quantities and their evolutions are generated by using the neural network.After the pre-training is completed,we fix the weights in the subsequent processes thus do not need the further gradient feedback.We find that the dynamical properties of physical quantities obtained by the dynamical learning are better than those obtained by the learning of Hamiltonian and time evolution operator.The dynamical learning can be applied to other quantum many-body systems,non-equilibrium statistics and random processes.