Some Group Runs Based Multivariate Control Charts for Monitoring the Process Mean Vector

In this article, we propose two control charts namely, the “Multivariate Group Runs’ (MV-GR-M)” and the “Multivariate Modified Group Runs’ (MV-MGR-M)” control charts, based on the multivariate normal processes, for monitoring the process mean vector. Methods to obtain the design parameters and operations of these control charts are discussed. Performances of the proposed charts are compared with some existing control charts. It is verified that, the proposed charts give a significant reduction in the out-of-control “Average Time to Signal” (ATS) in the zero state, as well in the steady state compared to the Hotelling’s T2 and the synthetic T2 control charts.

Photovoltaic Models Parameters Estimation Based on Weighted Mean of Vectors

Renewable energy sources are gaining popularity,particularly photovoltaic energy as a clean energy source.This is evident in the advancement of scientific research aimed at improving solar cell performance.Due to the non-linear nature of the photovoltaic cell,modeling solar cells and extracting their parameters is one of the most important challenges in this discipline.As a result,the use of optimization algorithms to solve this problem is expanding and evolving at a rapid rate.In this paper,a weIghted meaN oF vectOrs algorithm(INFO)that calculates the weighted mean for a set of vectors in the search space has been applied to estimate the parameters of solar cells in an efficient and precise way.In each generation,the INFO utilizes three operations to update the vectors’locations:updating rules,vector merging,and local search.The INFO is applied to estimate the parameters of static models such as single and double diodes,as well as dynamic models such as integral and fractional models.The outcomes of all applications are examined and compared to several recent algorithms.As well as the results are evaluated through statistical analysis.The results analyzed supported the proposed algorithm’s efficiency,accuracy,and durability when compared to recent optimization algorithms.

面向众核处理器的阴阳K-means算法优化

传统阴阳K-means算法处理大规模聚类问题时计算开销十分昂贵。针对典型众核处理器的体系结构特征,提出了一种阴阳K-means算法高效并行加速实现。该实现基于一种新内存数据布局,采用众核处理器中的向量单元来加速阴阳K-means中的距离计算,并面向非一致内存访问(non-unified memory access, NUMA)特性进行了针对性的访存优化。与阴阳K-means算法的开源多线程实现相比,该实现在ARMv8和x86众核平台上分别获得了最高约5.6与8.7的加速比。因此上述优化方法在众核处理器上成功实现了对阴阳K-means算法的加速。

基于主题词向量中心点的K-means文本聚类算法

K-means由于其时间复杂度低运行速度快一直是最为流行的聚类算法之一,但是该算法在进行聚类时需要预先给出聚类个数和初始类中心点,其选取得合适与否会直接影响最终聚类效果。该文对初始类中心和迭代类中心的选取进行大量研究,根据决策图进行初始类中心的选择,利用每个类簇的主题词向量替代均值作为迭代类中心。实验表明,该文的初始点选取方法能够准确地选取初始点,且利用主题词向量作为迭代类中心能够很好地避免噪声点和噪声特征的影响,很大程度上地提高了K-means算法的性能。

基于BERT-LDA和K-means聚类的绘画作品价值评估指标体系构建

针对目前绘画领域缺乏标准的价值评估指标体系,提出了基于BERT-LDA和K-means聚类的绘画作品价值要素挖掘方法。运用超平面法对绘画文献进行了停用词筛选,基于BERT-LDA模型构建了包含文本语义信息的融合特征向量,运用K-means算法对融合特征向量进行降维可视化,随之构建了绘画作品价值评估指标体系。结果表明,基于BERT-LDA模型和K-means算法识别的主题及主题词相比传统LDA模型的查准率、查全率和F值分别提升了28.5%、10%和21.5%。通过随机森林等算法对指标体系进行验证,验证了构建的绘画作品价值评估指标体系的科学性。

The Submanifolds with Parallel Mean Curvature Vector in a Locally Symmetric and Conformally Flat Riemannian Manifold

In the present paper we obtain the following result: Theorem Let M^R be a compact submanifold with parallel mean curvature vector in a locally symmetric and conformally flat Riemannian manifold N^(n+p)(p>1). If then M^n lies in a totally geodesic submanifold N^(n+1).

High-dimensional Tests for Mean Vector: Approaches without Estimating the Mean Vector Directly

Several tests for multivariate mean vector have been proposed in the recent literature.Generally,these tests are directly concerned with the mean vector of a high-dimensional distribution.The paper presents two new test procedures for testing mean vector in large dimension and small samples.We do not focus on the mean vector directly,which is a different framework from the existing choices.The first test procedure is based on the asymptotic distribution of the test statistic,where the dimension increases with the sample size.The second test procedure is based on the permutation distribution of the test statistic,where the sample size is fixed and the dimension grows to infinity.Simulations are carried out to examine the finite-sample performance of the tests and to compare them with some popular nonparametric tests available in the literature.

Superiority of empirical Bayes estimator of the mean vector in multivariate normal distribution

In this paper, the Bayes estimator and the parametric empirical Bayes estimator(PEBE) of mean vector in multivariate normal distribution are obtained. The superiority of the PEBE over the minimum variance unbiased estimator(MVUE) and a revised James-Stein estimators(RJSE) are investigated respectively under mean square error(MSE) criterion. Extensive simulations are conducted to show that performance of the PEBE is optimal among these three estimators under the MSE criterion.

Sign-based Test for Mean Vector in High-dimensional and Sparse Settings

In this article, we introduce a robust sparse test statistic which is based on the maximum type statistic. Both the limiting null distribution of the test statistic and the power of the test are analysed. It is shown that the test is particularly powerful against sparse alternatives. Numerical studies are carried out to examine the numerical performance of the test and to compare it with other tests available in the literature. The numerical results show that the test proposed significantly outperforms those tests in a range of settings, especially for sparse alternatives.

ON DETECTION OF CHANGE POINTS USING MEAN VECTORS

In this paper,the authors consider the problem of change points within the framework of model selection and propose a procedure for estimating the locations of change points when the number of change points is known.The strong consistency of this procedure is also established. The problem of detecting change points is discussed within the framework of the simultaneous test procedure.The case where the number of change points is unknown will be discussed in another paper.

基于K-means与SVR的致密油藏水平井压裂产能预测研究

水平井体积压裂是致密油藏高效开采的主要技术手段,准确预测产能对油田施工方案编制具有重要的指导意义,开采效果受地层因素、原油物性因素、压裂施工因素等影响,基于机理计算公式的传统预测方法存在一定局限性,提出一种基于K-means聚类与支持向量回归的产能预测组合模型,采用主成分分析算法解决K-means中欧氏距离对所有特征贡献程度一致性问题,K-means聚类结果与压裂施工参数结合作为SVR预测样本,有效解决不同区域间差异较大等问题。通过实验对比SVR、BP神经网络,预测准确性和稳定性优于单一模型,具有较高的合理性,可为致密油田高效开发提供指导性建议。

Use of Support Vector Regression Based on Mean Impact Value Model to Identify Active Compounds in a Combination of Curcuma longa L.and Glycyrrhiza extracts

A support vector regression based on the mean impact value (MIV) model was constructed to identify the bioactive compounds inhibiting proliferation of HeLa cells in a combination of turmeric (Curcuma longa L.) and liquorice (Glycyrrhiza) extracts. The quantitative chemical fingerprint from 50 batches of turmeric and liquorice extracts was established using high performance liquid chromatography hyphenated to an ultraviolet visible detector. Qualitative results were obtained using ultra performance liquid chromatography coupled with electrospray ionization quadrupole time-of-flight tandem mass spectrometry. A total of 46 peaks (peaks 1–15 from turmeric and 16–46 from liquorice) were selected as “common peaks” for analysis. The inhibitory effect of the combined extracts on HeLa cells was measured by MTT (3-(4,5-dimethylthiazol-2-yl)-2,5-diphenyltetrazolium bromide) assay. It was found that 15 compounds (peaks: 8, 12, 30, 24, 46, 11, 14, 9, 3, 1, 44, 18, 7, 45 and 43) possessing high absolute MIV exhibited a significant correlation with the cytotoxicity against HeLa cells; most of these have already been confirmed with potential cytotoxicity in previous research. The important potential application of the present model can be extended to help discover active compounds from complex herbal medicine prior to traditional bioassay-guided separation. It is considered that this could be a useful tool for re-developing herbal medicine based on the use of these active compounds. © 2017, Tianjin University and Springer-Verlag Berlin Heidelberg.

FAST IMAGE ENCODING ALGORITHM BASED ON MEAN-MATCH CORRELATION VECTOR QUANTIZATION

A mean-match correlation vector quantizer (MMCVQ) was presented for fast image encoding. In this algorithm, a sorted codebook is generated regarding the mean values of all codewords. During the encoding stage, high correlation of the adjacent image blocks is utilized, and a searching range is obtained in the sorted codebook according to the mean value of the current processing vector. In order to gain good performance, proper THd and NS are predefined on the basis of experimental experiences and additional distortion limitation. The expermental results show that the MMCVQ algorithm is much faster than the full-search VQ algorithm, and the encoding quality degradation of the proposed algorithm is only 0.3～0.4 dB compared to the full-search VQ.

基于CSI和K-means-SVR的多指纹库室内定位方法

传统的Wi-Fi室内定位方法需要与所有指纹数据库中的指纹数据进行匹配后才能定位,导致人群聚集区域定位效率不高,体验较差。提出一种基于信道状态信息(CSI)、K均值(K-means)聚类算法与支持向量回归(SVR)算法相结合的多指纹库室内定位方法。该方法首先根据CSI的簇分布特点,利用K-means算法对所有定位点内的CSI数据聚类后得到多个簇的CSI数据;然后,基于多个簇分别建立多个指纹库,并将CSI数据分别存入多个指纹库,进而在每个指纹库中分别训练SVR模型用于Wi-Fi定位。相较于传统的支持向量机(SVM)定位方法,所提方法在离线阶段需要的训练样本更少,定位效率更高;在线阶段,该方法既降低了匹配的复杂度,也提高了定位的精度。由于使用了多指纹库,Wi-Fi定位系统可以根据人流量实时调整资源分配策略,提高服务器运行效率和定位服务体验。

Multiple mental tasks classification based on nonlinear parameter of mean period using support vector machines

Mental task classification is one of the most important problems in Brain-computer interface.This paper studies the classification of five-class mental tasks.The nonlinear parameter of mean period obtained from frequency domain information was used as features for classification implemented by using the method of SVM(support vector machines).The averaged classification accuracy of 85.6% over 7 subjects was achieved for 2-second EEG segments.And the results for EEG segments of 0.5s and 5.0s compared favorably to those of Garrett's.The results indicate that the parameter of mean period represents mental tasks well for classification.Furthermore,the method of mean period is less computationally demanding,which indicates its potential use for online BCI systems.

MOTION VECTOR RECOVERY METHOD BASED ON MEAN SHIFT PROCEDURE

This letter presents a novel Motion Vector (MV) recovery method which is based on Mean Shift (MS) procedure. According to motion continuity, MVs in local area should be similar. If projecting MV into 2-D feature space, local MVs in the feature space tend to cluster closely. To estimate the lost MVs in local area, recovery of lost MVs is modeled as clustering operation. MS procedure is applied to enforce each lost MV in the feature space to shift to the position where dominant MVs are gathered. Meanwhile, bandwidth estimation is statistically characterized by the variation of local standard de-viations; weighted value calculation is determined by estimation of overall standard deviation. Simu-lation results demonstrate their better performance when compared with other MV recovery ap-proaches and low computation cost.

基于改进INFO-CNN-QRGRU模型的农村分布式光伏发电短期概率预测

随着“双碳”目标的推进,清洁能源所占比重大幅度增加,分布式光伏发电在我国农村地区快速发展,但其随机性、间歇性的特点给新能源消纳和电网稳定带来很大的挑战。光伏发电预测可以在一定程度上改善新能源消纳问题,减少光伏发电的不稳定性对电网的冲击。因此,为提高光伏发电功率预测精度,提出一种基于改进向量加权平均算法优化CNN-QRGRU网络的光伏发电概率预测方法。首先采用ReliefF算法对特征变量进行选择,在此基础上利用高斯混合模型(Gaussian mixture model,GMM)聚类方法将天气分为晴天、晴转多云和阴雨天3种类型,将处理好的数据输入到CNN-GRU模型中,并利用向量加权平均(weighted mean of vectors algorithm,INFO)优化算法对模型超参数进行调参,将分位数回归模型(quantile regression,QR)与INFO-CNN-GRU模型相结合得到光伏功率条件分布,结合核密度估计法从条件分布中获得概率密度函数,完成概率预测。以实际光伏电站数据作为基础,将提出的INFO优化算法与其他几种传统的优化算法进行对比,结果表明INFO的优化效果更好,在此基础上进行概率预测,得到的概率预测结果相较于点预测能提供更多有效信息,更具有应用价值。

切入场景下基于碰撞风险聚类的改进车速预测方法

切入工况的高精度车速预测是保证自动驾驶切入安全的关键依据。为提高自动驾驶汽车切入工况安全,开展了基于车车耦合风险聚类的切入场景自车速度高精度预测方法的研究。首先,依据实验所得自然驾驶数据进行车辆切入切出片段提取,使用K-means方法依据碰撞风险与加速度关联特征进行聚类分析。其次,基于支持向量机(SVM)模型,对切入切出工况车车交互状态进行在线识别,对切入危险工况进行实时预测。最后,提出基于自回归综合移动平均(ARIMA)模型的改进车速预测方法,结合在线识别结果进行车速在线优化。仿真结果表明,所提出的基于碰撞风险聚类的改进ARIMA车速预测方法对提高切入安全效果明显,较传统的预测方法车辆的碰撞风险降低了10%~20%。研究结果表明,ARIMA模型的改进车速预测方法对提高自动驾驶车切入安全具有重要的研究意义。

基于Seeded-Kmeans和SVM的分类算法

支持向量机(support vector machines,SVM)在人像识别、文本分类等模式识别问题中有广泛的应用,可以有效地解决一些实际生活中的分类问题。针对半监督两分类问题,提出了基于Seeded-Kmeans和SVM的分类算法(SK-SVM)。用SeededKmeans算法对无标签点进行处理,使其获得初始标签,再选取有效的标签点加入已有带标签点中,构成新的带标签训练集,最后结合SVM进行分类。选取UCI中的8个数据集进行数值实验,基于Seeded-Kmeans和SVM的分类算法的有效性得到了验证。

提取多场景视频关键帧的复合HOG特征聚类方法

由于直接利用帧差数据提取动态多场景视频关键帧往往会产生过多冗余帧,方向梯度直方图(HOG)特征对图像亮度、场景变化具有较好的稳定性。为此,提出了用于提取多场景视频关键帧的复合HOG特征聚类方法来提升关键帧提取效率。首先,通过提取视频帧的HOG特征引入图像信息熵构成复合特征矢量,以保持数据特征相关性。其次,根据复合特征矢量统计视频帧间差异数据确定视频分割镜头、关键帧提取个数;再次,分别考虑镜头内帧集合和完整视频帧集合,无重复地将信息熵较大的视频帧选为初始聚类中心以引导聚类算法搜索方向,并通过K均值聚类抽取视频关键帧。与传统K均值聚类方法比较后发现,所提算法冗余度降低0.003~0.015,查准率提高了0.14~0.21,聚类时间得到下降,精度和效率较优。