On the Equality of Weighted BajratarevićMeans to Quasi-Arithmetic Means

In this paper, we considered the equality problem of weighted Bajraktarević means with weighted quasi-arithmetic means. Using the method of substituting for functions, we first transform the equality problem into solving an equivalent functional equation. We obtain the necessary and sufficient conditions for the equality equation.

Median-of-Means方法在偏度系数中的应用

传统偏度系数的定义涉及样本均值和三阶矩,使其对离群值十分敏感。本文在偏度系数的估计中引入Median-of-Means方法,提出偏度系数的新估计量,并证明其相合性和渐近正态性。此外,基于经验似然方法提出一种新的偏度系数检验统计量,证明其渐近性质并进行数值模拟。结果表明,本文提出的估计量具有一定稳健性,检验统计量表现也优于传统方法。最后将所提出的估计与检验方法应用于实际数据分析发现,估计结果比较稳健,进一步表明原有的偏度系数估计方法并不适用。

加入跳跃连接的深度嵌入K-means聚类

现有的深度聚类算法大多采用对称的自编码器来提取高维数据的低维特征,但随着自编码器训练次数的不断增加,数据的低维特征空间在一定程度上发生了扭曲,这样得到的数据低维特征空间无法反映原始数据空间中潜在的聚类结构信息.为了解决上述问题,本文提出了一种新的深度嵌入K-means算法(SDEKC).首先,在低维特征提取阶段,在对称的卷积自编码器中相对应的编码器与解码器之间以一定的权重加入两个跳跃连接,以减弱解码器对编码器的编码要求同时突出卷积自编码器的编码能力,这样可以更好地保留原始数据空间中蕴含的聚类结构信息;其次,在聚类阶段,通过一个标准正交变换矩阵将低维数据空间转换为一个新的揭示聚类结构信息的空间;最后,本文以端到端的方式采用贪婪算法迭代优化数据的低维表示及其聚类,在6个真实数据集上验证了本文提出新算法的有效性.

基于K-Means聚类与熵权TOPSIS法的岩石可爆性评价研究

露天矿山的爆破块度分布,直接影响到后续的采装、运输和破碎工作。为了控制石墨矿山不同区域爆破块度分布,基于K-means无监督聚类学习法与熵权TOPSIS评价法建立了一种新的岩石可爆性评价模型,选取岩石密度、动力能量耗散率、动态抗压强度、平均应变率、脆性指数作为评价指标,通过熵权计算,发现岩石破碎程度受脆性指数影响最大,受平均应变率影响最小。将此模型应用于实际石墨矿山,可爆性分为10个等级,统计不同分级下的岩石平均破碎粒径,发现可爆性分级等级越高平均粒径越大,有明显的分级特征,验证了模型的有效性。从爆破石墨矿石岩体类型看,岩石可爆性从易到难排序为:片岩、片麻岩、变粒岩、混合岩。结合石墨矿石微观观测结果分析可知:岩性从片岩向混合岩转变,岩石内部石墨晶质呈下降趋势,石墨矿石可爆性等级也随之越来越高。岩石密度、能量耗散率、动态抗压强度之间呈线性正相关,岩石可爆性与平均应变率、脆性指数存在负相关性。研究成果为矿山矿岩可爆性评价提供了一条新思路,对露天矿山爆破块度优化具有一定的理论和实践指导意义。

基于特征分箱和K-Means算法的用户行为分析方法

针对网购用户所产生的购物行为进行分析,首先通过数据处理构建客户关系管理模型(RFM模型),在此模型的基础上采用特征分箱法和K-Means聚类两种方法对用户进行细分,并对2种模型结果进行比较分析,讨论二者的差异性和具体的应用范围和意义.其中,基于特征分箱法的RFM模型将变量转化到相似的尺度上并将变量离散化,使得用户分类标签更加清晰,也可依据各类标签分类出不同类型的用户.K-Means算法通过轮廓系数评估聚类算法质量以至于选取最优K值.本文实验分析结果可为运营商提供更加可靠直观的数据,使得运营商可以根据不同用户的不同行为进行市场细分,进而进行精准营销和服务设置.

基于改进K-means与机器视觉的档案数据分析技术

为了提升医疗信息系统对健康档案数据的分析效率,文中采用图像采集、降噪、配准与差分等技术提取医疗图像信息,进而有效提升信息系统的数据采集效率。同时还对传统的K-means算法加以改进,并提出了一种基于类间、类内距离的聚类初始化评价指标体系(BWP),将其应用于采集到的档案数据中,以实现快速的聚类分析。将所提算法在CUDA计算平台上进行了实现,测试结果表明,该方法的聚类精度和运行效率较现有算法均有显著提升。此外,改进后K-means算法的正确聚类样本数量占比提升了4.88%,高于现有的主流指标体系,且当聚类数k的取值为16或32时,运行时间大幅降低。

基于K-means聚类和特征空间增强的噪声标签深度学习算法

深度学习中神经网络的性能依赖于高质量的样本,然而噪声标签会降低网络的分类准确率。为降低噪声标签对网络性能的影响,噪声标签学习算法被提出。该算法首先将训练样本集划分成干净样本集和噪声样本集,然后使用半监督学习算法对噪声样本集赋予伪标签。然而,错误的伪标签以及训练样本数量不足的问题仍然限制着噪声标签学习算法性能的提升。为解决上述问题,提出基于K-means聚类和特征空间增强的噪声标签深度学习算法。首先,该算法利用K-means聚类算法对干净样本集进行标签聚类,并根据噪声样本集与聚类中心的距离大小筛选出难以分类的噪声样本,以提高训练样本的质量;其次,使用mixup算法扩充干净样本集和噪声样本集,以增加训练样本的数量;最后,采用特征空间增强算法抑制mixup算法新生成的噪声样本,从而提高网络的分类准确率。并在CIFAR10、CIFAR100、MNIST和ANIMAL-10共4个数据集上试验验证了该算法的有效性。

启发式k-means聚类算法的改进研究

启发式k-means聚类算法通过在k-means第一次迭代后查看附近的集群来预测每个数据点可能会被划分到的集群子集,有效地加快了算法的运行速度。但由于启发式算法存在随机选择初始聚类中心以及无法有效识别数据集中离群点的缺陷,导致聚类结果的误差平方和较大并且轮廓系数偏小。针对这一问题,提出了CHk-means算法,该算法引入仔细播种方法,克服了启发式k-means算法随机选择初始聚类中心带来的局部最优解问题;该算法引入局部异常因子LOF算法对离群点进行检测,降低了离群点数据对聚类结果的影响。在多个数据集上对3种算法进行对比试验,结果表明CHk-means算法可有效降低聚类结果的误差平方和,增强聚类的轮廓系数,使聚类质量得到明显改善。

一种融合乌鸦搜索算法的K-means聚类算法

传统的K-均值聚类算法(K-means)对初始聚类中心的选择敏感,容易陷入局部最优解,并且需要预先设定聚类数量K,这在实际操作中往往难以实现。为了解决这些问题,提出了一种融合乌鸦搜索算法的K-means聚类算法。该算法利用乌鸦搜索算法的全局搜索能力,自动确定最佳的聚类数目K,从而提高聚类的质量和效率。通过在Seeds数据集进行实验计算卡林斯基-哈拉巴斯(Calinski-Harabasz)指数等评价指标,发现该算法聚类效果明显优于传统的K-means算法。

基于K-means聚类和BP神经网络的电梯能耗实时监测方法

针对现有方法在对电梯能耗进行监测时,存在监测精度低、用时长、监测结果不理想的问题,该文提出一种基于K-means聚类算法和BP神经网络相结合的电梯能耗实时监测方法 .在经过清洗的能耗数据中提取影响建筑能耗实时监测的主要因素特征值,利用相似系数法进行相似度计算,获取相似系数.对相似电梯能耗数据进行小波分解获取高低频序列,分别采用LSSVM-GSA检测方法和均方加权处理方法对低频和高频部分进行处理,将两个结果进行重构,得到最终的实时监测结果 .仿真实验结果表明:所提方法能够获取高精度、低耗时、高稳定性的监测结果 .

光伏波动平抑下改进K-means的电池储能动态分组控制策略

针对电池储能系统(battery energy storage system,BESS)进行光伏波动平抑时寿命损耗高及荷电状态(state of charge,SOC)一致性差的问题,提出了光伏波动平抑下改进K-means的BESS动态分组控制策略。首先,采用最小最大调度方法获取光伏并网指令。其次,设计了改进侏儒猫鼬优化算法(improved dwarf mongoose optimizer,IDMO),并利用它对传统K-means聚类算法进行改进,加快了聚类速度。接着,制定了电池单元动态分组原则,并根据电池单元SOC利用改进K-means将其分为3个电池组。然后,设计了基于充放电函数的电池单元SOC一致性功率分配方法,并据此提出BESS双层功率分配策略,上层确定电池组充放电顺序及指令,下层计算电池单元充放电指令。对所提策略进行仿真验证,结果表明,所设计的IDMO具有更高的寻优精度及更快的寻优速度。所提BESS平抑光伏波动策略在有效平抑波动的同时,降低了BESS运行寿命损耗并提高了电池单元SOC的均衡性。

基于改进K-means算法的物流配送中心选址研究

针对传统K-means算法需要主观设定K值及无法处理类别型数据问题,文章运用肘部法及轮廓系数法确定合理K值,对类别型数据采取独热编码(One-Hot Encoding)转换为可以处理的连续型数据,并将其运用到在物流配送中心选址中;并综合考虑多种类别的影响因素,构建了相应的影响因素指标体系,提出的模型能够识别输入数据的数值型及类别型数据,实现样本的有效聚类。相关的案例分析结果表明,相比传统K-means聚类,文章的改进K-means算法选址结果可使物流总成本降低8.76%,运营成本降低14.85%,固定成本降低8.09%,效果显著。

Integrated classification method of tight sandstone reservoir based on principal component analysise simulated annealing genetic algorithmefuzzy cluster means

In this research,an integrated classification method based on principal component analysis-simulated annealing genetic algorithm-fuzzy cluster means(PCA-SAGA-FCM)was proposed for the unsupervised classification of tight sandstone reservoirs which lack the prior information and core experiments.A variety of evaluation parameters were selected,including lithology characteristic parameters,poro-permeability quality characteristic parameters,engineering quality characteristic parameters,and pore structure characteristic parameters.The PCA was used to reduce the dimension of the evaluation pa-rameters,and the low-dimensional data was used as input.The unsupervised reservoir classification of tight sandstone reservoir was carried out by the SAGA-FCM,the characteristics of reservoir at different categories were analyzed and compared with the lithological profiles.The analysis results of numerical simulation and actual logging data show that:1)compared with FCM algorithm,SAGA-FCM has stronger stability and higher accuracy;2)the proposed method can cluster the reservoir flexibly and effectively according to the degree of membership;3)the results of reservoir integrated classification match well with the lithologic profle,which demonstrates the reliability of the classification method.

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SVD-K-means算法的软扩频信号伪码序列盲估计

针对通信中软扩频信号伪码序列盲估计困难的问题,提出一种奇异值分解(singular value decomposition,SVD)和K-means聚类相结合的方法。该方法先对接收信号按照一倍伪码周期进行不重叠分段构造数据矩阵。其次对数据矩阵和相似性矩阵分别进行SVD完成对伪码序列集合规模数的估计、数据降噪、粗分类以及初始聚类中心的选取。最后通过K-means算法优化分类结果,得到伪码序列的估计值。该算法在聚类之前事先确定聚类数目,大大减少了迭代次数。同时实验结果表明,该算法在信息码元分组小于5 bit,信噪比大于-10 dB时可以准确估计出软扩频信号的伪码序列,性能较同类算法有所提升。

基于优化K-means算法的高校成绩聚类分析研究

针对经典K均值算法在聚类中心易受异常值影响,导致聚类结果不稳定的问题,提出基于样本分布密度的优化K-means算法,以提高聚类稳定性和准确性;聚类后通过CH指数和分类区间占比总体两种方法,客观评价3种离散化方法,结果表明,优化的K-means算法避免了区间分类不合理现象,更加准确地反映了成绩样本的分布特点。

A Novel Fractional Dengue Transmission Model in the Presence of Wolbachia Using Stochastic Based Artificial Neural Network

The purpose of this research work is to investigate the numerical solutions of the fractional dengue transmission model(FDTM)in the presence of Wolbachia using the stochastic-based Levenberg-Marquardt neural network(LM-NN)technique.The fractional dengue transmission model(FDTM)consists of 12 compartments.The human population is divided into four compartments;susceptible humans(S_(h)),exposed humans(E_(h)),infectious humans(I_(h)),and recovered humans(R_(h)).Wolbachia-infected and Wolbachia-uninfected mosquito population is also divided into four compartments:aquatic(eggs,larvae,pupae),susceptible,exposed,and infectious.We investigated three different cases of vertical transmission probability(η),namely when Wolbachia-free mosquitoes persist only(η=0.6),when both types of mosquitoes persist(η=0.8),and when Wolbachia-carrying mosquitoes persist only(η=1).The objective of this study is to investigate the effectiveness of Wolbachia in reducing dengue and presenting the numerical results by using the stochastic structure LM-NN approach with 10 hidden layers of neurons for three different cases of the fractional order derivatives(α=0.4,0.6,0.8).LM-NN approach includes a training,validation,and testing procedure to minimize the mean square error(MSE)values using the reference dataset(obtained by solving the model using the Adams-Bashforth-Moulton method(ABM).The distribution of data is 80% data for training,10% for validation,and,10% for testing purpose)results.A comprehensive investigation is accessible to observe the competence,precision,capacity,and efficiency of the suggested LM-NN approach by executing the MSE,state transitions findings,and regression analysis.The effectiveness of the LM-NN approach for solving the FDTM is demonstrated by the overlap of the findings with trustworthy measures,which achieves a precision of up to 10^(-4).

Genetics of biochemical attributes regulating morpho-physiology of upland cotton under high temperature conditions

Background Cotton is a strategically important fibre crop for global textile industry.It profoundly impacts several countries’industrial and agricultural sectors.Sustainable cotton production is continuously threatened by the unpre-dictable changes in climate,specifically high temperatures.Breeding heat-tolerant,high-yielding cotton cultivars with wide adaptability to be grown in the regions with rising temperatures is one of the primary objectives of modern cotton breeding programmes.Therefore,the main objective of the current study is to figure out the effective breed-ing approach to imparting heat tolerance as well as the judicious utilization of commercially significant and stress-tolerant attributes in cotton breeding.Initially,the two most notable heat-susceptible(FH-115 and NIAB Kiran)and tolerant(IUB-13 and GH-Mubarak)cotton cultivars were spotted to develop filial and backcross populations to accom-plish the preceding study objectives.The heat tolerant cultivars were screened on the basis of various morphological(seed cotton yield per plant,ginning turnout percentage),physiological(pollen viability,cell membrane thermostabil-ity)and biochemical(peroxidase activity,proline content,hydrogen peroxide content)parameters.Results The results clearly exhibited that heat stress consequently had a detrimental impact on every studied plant trait,as revealed by the ability of crossing and their backcross populations to tolerate high temperatures.However,when considering overall yield,biochemical,and physiological traits,the IUB-13×FH-115 cross went over particularly well at both normal and high temperature conditions.Moreover,overall seed cotton yield per plant exhibited a posi-tive correlation with both pollen viability and antioxidant levels(POD activity and proline content).Conclusions Selection from segregation population and criteria involving pollen viability and antioxidant levels concluded to be an effective strategy for the screening of heat-tolerant cotton germplasms.Therefore,understanding acquired from this study can assist breeders identifying traits that should be prioritized in order to develop climate resilient cotton cultivars.

Properties of collective flow and pion production in intermediate-energy heavy-ion collisions with a relativistic quantum molecular dynamics model

The relativistic mean-field approach was implemented in the Lanzhou quantum molecular dynamics transport model(LQMD.RMF). Using the LQMD.RMF, the properties of collective flow and pion production were investigated systematically for nuclear reactions with various isospin asymmetries. The directed and elliptic flows of the LQMD.RMF are able to describe the experimental data of STAR Collaboration. The directed flow difference between free neutrons and protons was associated with the stiffness of the symmetry energy, that is, a softer symmetry energy led to a larger flow difference. For various collision energies, the ratio between the π^(-) and π^(+) yields increased with a decrease in the slope parameter of the symmetry energy. When the collision energy was 270 MeV/nucleon, the single ratio of the pion transverse momentum spectra also increased with decreasing slope parameter of the symmetry energy in both nearly symmetric and neutron-rich systems.However, it is difficult to constrain the stiffness of the symmetry energy with the double ratio because of the lack of threshold energy correction on the pion production.

Assessing the Performance of a Dynamical Downscaling Simulation Driven by a Bias-Corrected CMIP6 Dataset for Asian Climate

In this study,we aim to assess dynamical downscaling simulations by utilizing a novel bias-corrected global climate model(GCM)data to drive a regional climate model(RCM)over the Asia-western North Pacific region.Three simulations were conducted with a 25-km grid spacing for the period 1980–2014.The first simulation(WRF_ERA5)was driven by the European Centre for Medium-Range Weather Forecasts Reanalysis 5(ERA5)dataset and served as the validation dataset.The original GCM dataset(MPI-ESM1-2-HR model)was used to drive the second simulation(WRF_GCM),while the third simulation(WRF_GCMbc)was driven by the bias-corrected GCM dataset.The bias-corrected GCM data has an ERA5-based mean and interannual variance and long-term trends derived from the ensemble mean of 18 CMIP6 models.Results demonstrate that the WRF_GCMbc significantly reduced the root-mean-square errors(RMSEs)of the climatological mean of downscaled variables,including temperature,precipitation,snow,wind,relative humidity,and planetary boundary layer height by 50%–90%compared to the WRF_GCM.Similarly,the RMSEs of interannual-tointerdecadal variances of downscaled variables were reduced by 30%–60%.Furthermore,the WRF_GCMbc better captured the annual cycle of the monsoon circulation and intraseasonal and day-to-day variabilities.The leading empirical orthogonal function(EOF)shows a monopole precipitation mode in the WRF_GCM.In contrast,the WRF_GCMbc successfully reproduced the observed tri-pole mode of summer precipitation over eastern China.This improvement could be attributed to a better-simulated location of the western North Pacific subtropical high in the WRF_GCMbc after GCM bias correction.