基于K-means聚类分析和多元线性回归的相关流量数据处理方法

相关流量计在油井产出剖面测量中得到了成功的应用。但因传感器、调理电路以及流体本身噪声的影响,相关流量计所测量的渡越时间值会出现少量异常数据,使瞬时流速的计算结果与实际值相差很大,进而平均流量计算也出现较大的测量误差。对此提出基于K-means聚类算法对渡越时间样本数据聚类分析,并根据聚类结果建立多元线性回归预测模型,合理预测渡越时间值,以修正渡越时间的异常值。对预测值与实际值进行比较,最终获得准确的相关流量数据。采用多相流装置的实验数据对所建立的方法进行验证,结果表明,该方法可有效消除渡越时间的异常,优化流量测量的数据,对两相流流量测量有一定的实践意义。

融合SOM神经网络与K-means聚类算法的用户信用画像研究

为提高现阶段基于K-Means聚类算法的用户信用画像模型的准确性和实时性,提出一种融合自组织映射(SOM,Self-Organizing Map)神经网络与K-Means聚类算法的改进方法。通过SOM对用户数据进行降维和特征提取,直接获得最优聚类数目后再用K-Means算法进行聚类分析。通过真实在线借贷平台数据对所提方法进行验证,结果表明,该方法可提升用户信用画像分析的质量,更好地满足金融数据分析中对实时管理和风险控制的要求,为金融机构提供精准的决策支持。

基于改进粒子群和K-means聚类的优化算法

为了解决粒子群优化(particle swarm optimization, PSO)收敛速度慢和迭代次数多,以及传统K-means聚类算法采取的欧氏距离划分准则会导致聚类效果不理想等问题,构建了基于改进粒子群和K-means聚类的优化算法.根据Sigmoid函数优势,对PSO算法中速度更新公式的惯性权重参数实施改进,得到新的惯性权重公式,有效提高PSO算法的收敛速度;在PSO算法的位置更新公式中引入时间权重,通过调整时间权重大小,控制粒子的空间搜索范围,增强粒子的搜索能力;在传统的欧氏距离中引入属性权值,得到新的欧氏距离计算公式,该公式在计算两个向量相似度时,同时考虑了两个向量间的累积差异以及它们之间的相似性,与改进的PSO算法相结合,设计了基于改进粒子群和K-means聚类的优化算法.在6个基准测试函数和13个UCI数据集上,将所提出的优化算法与其他算法进行对比实验分析.实验结果表明:所提算法在收敛速度和寻优稳定性方面得到了明显提升,有效地提高了聚类准确率并且降低了迭代次数.

Exact scaling for the mean first-passage time of random walks on a generalized Koch network with a trap

In this paper, we study the scaling for the mean first-passage time （MFPT） of the random walks on a generalized Koch network with a trap. Through the network construction, where the initial state is transformed from a triangle to a polygon, we obtain the exact scaling for the MFPT. We show that the MFPT grows linearly with the number of nodes and the dimensions of the polygon in the large limit of the network order. In addition, we determine the exponents of scaling efficiency characterizing the random walks. Our results are the generalizations of those derived for the Koch network, which shed light on the analysis of random walks over various fractal networks.

Mean first-passage time of an asymmetric bistable system driven by colour-correlated noise

In this paper, the effect of every parameter （including p, q, r, λ, τ） on the mean first-passage time （MFPT） is investigated in an asymmetric bistable system driven by colour-correlated noise. The expression of MFPT has been obtained by applying the steepest-descent approximation. Numerical results show that （1） the intensity of multiplicative noise p and the intensity of additive noise q play different roles in the MFPT of the system, （2） suppression appears on the curve of the MFPT with small λ （e.g. λ 〈 0.5） but there is a peak on the curve of the MFPT when λ is big （e.g. λ 〉 0.5）, and （3） with different values of r （e.g. r = 0.1, 0.5, 1.5）, the effort of τ on the MFPT is diverse.

A Novel Multiple Dependent State Sampling Plan Based on Time Truncated Life Tests Using Mean Lifetime

The design of a new adaptive version of the multiple dependent state(AMDS)sampling plan is presented based on the time truncated life test under the Weibull distribution.We achieved the proposed sampling plan by applying the concept of the double sampling plan and existing multiple dependent state sampling plans.A warning sign for acceptance number was proposed to increase the probability of current lot acceptance.The optimal plan parameters were determined simultaneously with nonlinear optimization problems under the producer’s risk and consumer’s risk.A simulation study was presented to support the proposed sampling plan.A comparison between the proposed and existing sampling plans,namely multiple dependent state(MDS)sampling plans and a modified multiple dependent state(MMDS)sampling plan,was considered under the average sampling number and operating characteristic curve values.In addition,the use of two real datasets demonstrated the practicality and usefulness of the proposed sampling plan.The results indicated that the proposed plan is more flexible and efficient in terms of the average sample number compared to the existing MDS and MMDS sampling plans.

Alpha-reliable combined mean traffic equilibrium model with stochastic travel times

Based on the reliability budget and percentile travel time(PTT) concept, a new travel time index named combined mean travel time(CMTT) under stochastic traffic network was proposed. CMTT here was defined as the convex combination of the conditional expectations of PTT-below and PTT-excess travel times. The former was designed as a risk-optimistic travel time index, and the latter was a risk-pessimistic one. Hence, CMTT was able to describe various routing risk-attitudes. The central idea of CMTT was comprehensively illustrated and the difference among the existing travel time indices was analyzed. The Wardropian combined mean traffic equilibrium(CMTE) model was formulated as a variational inequality and solved via an alternating direction algorithm nesting extra-gradient projection process. Some mathematical properties of CMTT and CMTE model were rigorously proved. Finally, a numerical example was performed to characterize the CMTE network. It is founded that that risk-pessimism is of more benefit to a modest(or low) congestion and risk network, however, it changes to be risk-optimism for a high congestion and risk network.

Moments and Mean First—Passage Time of Parabolic—Bistable Potential System Driven by Colored Noise

A parabolic-bistable potential system driven by colored noise is studied. The exact analytical expressionsof the stationary probability distribution (SPD) and the moments of the system are derived. Furthermore, the meanfirst-passage time is calculated by the use of two approximate methods, respectively. It is found that (i) the double peaksof SPD are rubbed-down into a flat single peak with the increasing of noise intensity; (ii) a minimum occurs on the curve of the second-order moment of the system vs.noise intensity at the point DΓ=0.025;(iii)the results obtained by our approximate approach are in good agreement with the numerical calculations for either small or large correlation time Γ，while the conventional steepest descent apprximation leads to poor results.

Transient Properties of a Bistable System with Delay Time Driven by Non-Gaussian and Gaussian Noises:Mean First-Passage Time

The mean first-passage time of a bistable system with time-delayed feedback driven by multiplicativenon-Gaussian noise and additive Gaussian white noise is investigated.Firstly,the non-Markov process is reduced tothe Markov process through a path-integral approach;Secondly,the approximate Fokker-Planck equation is obtainedby applying the unified coloured noise approximation,the small time delay approximation and the Novikov Theorem.The functional analysis and simplification are employed to obtain the approximate expressions of MFPT.The effects ofnon-Gaussian parameter (measures deviation from Gaussian character) r,the delay time τ,the noise correlation timeτ_0,the intensities D and α of noise on the MFPT are discussed.It is found that the escape time could be reduced byincreasing the delay time τ,the noise correlation time τ_0,or by reducing the intensities D and α.As far as we know,thisis the first time to consider the effect of delay time on the mean first-passage time in the stochastic dynamical system.

The mean first passage time of a three-level atomic optical bistable system subjected to noise

The transient properties of a three-level atomic optical bistable system in the presence of multiplicative and additive noises are investigated. The explicit expressions of the mean first-passage time （MFPT） of the transition from the high intracavity intensity state to the low one are obtained by numerical computations. The impacts of the intensities of the multiplicative noise DM and the additive noise DA, the intensity of correlation between two noises λ, and the intensity of the incident light y on the MFPT are discussed, respectively. Our results show： （i） for the case of no correlation between two noises （2, = 0.0）, the increase in DM and DA can lead to an increase in the probability of the transition to the low intracavity intensity state, while the increase in y can lead to a retardation of the transition; and （ii） for the case of correlation between two noises （λ≠ 0.0）, the increase in λ can cause an increase in the probability of the transition, and the increase in DA can cause a retardation of the transition firstly and then an increase in the probability of the transition, i.e., the noise-enhanced stability is observed for the case of correlation between two noises.

Fuzzy Time Series Forecasting Based On K-Means Clustering

Many forecasting models based on the concepts of Fuzzy time series have been proposed in the past decades. These models have been widely applied to various problem domains, especially in dealing with forecasting problems in which historical data are linguistic values. In this paper, we present a new fuzzy time series forecasting model, which uses the historical data as the universe of discourse and uses the K-means clustering algorithm to cluster the universe of discourse, then adjust the clusters into intervals. The proposed method is applied for forecasting University enrollment of Alabama. It is shown that the proposed model achieves a significant improvement in forecasting accuracy as compared to other fuzzy time series forecasting models.

Mean First Passage Time for System with Fluctuating Potential Barrier and Coupled Noise

在这篇论文，我们首先学习平均数在 a coupled 噪音驾驶的一个变化潜力障碍上的经过时间(MFPT ) 。在变化潜力障碍上的 MFPT 作为变化潜力障碍的扭动的率的函数，并且作为两分的噪音转变率的函数显示反响的激活，这被显示出。

Mean First-Passage Time of an Asymmetric Kinetic Model Driven by Two Different Kinds of Colored Noises

跨关联的时间被调查的在有非零的趋于增加的 non-Gaussian 噪音和添加剂 Gaussian 白噪音之间的一个不对称的双稳态的系统的吝啬的第一经过的时间(MFPT ) 。第一， non-Markov 过程通过一条路径积分途径被归结为 Markov 过程；第二，近似佛克普朗克常数方程被使用统一有颜色的噪音近似和 Novikov 定理获得。不变的概率分发(SPD ) 也被获得。基础功能的分析和简化被采用获得 MFPT T ± 的近似表情。不对称现象参数 β 的效果， non-Gaussian 参数(从 Gaussian 特性的措施偏差) r，噪音关联时间 τ 和 τ2, 联合系数 λ ，紧张 D 和 MFPT 上的噪音的 α 被讨论。不对称现象参数 β ， non-Gaussian 参数 r 和联合系数 λ 能导致阶段转变，这被发现。而且，主要调查结果是噪音的自存的参数(D， α ，和 τ) 的效果和跨关联的参数(λ ，在 MFPT T ± 上的噪音之间的 τ2) 是不同的。

Time is Not Money!——It Is a Providence of Opportunities

The essay discusses the interrelations between Time and Money and the right ways for managing them.Additionally it discusses other aspects of life and time,such as:definition of time,smart use of time,use of time as distincting between men and animals,time,age and responsibility,time and the“meaning of life”,quality and quantity of lifetime,social aspects of time and science,technology and time.The author clearly expresses his opinion,that Time is a neutral abstract entity,exists in free democratic regimes and in less-liberatated autocracies.It is the explicit responsibility of every man and woman,anywhere,and everywhere,to prepare and train themselves for a smart use of the time awarded to them.On the other hand,Time is available for everyone and everything.The busy diligent hard-working person always seeks more challenging missions,while the less-energetic idle person,is always busy and tire of doing nothing.The author also claims that Time is an opportunity.It is available and inviting every active person,a thinker,a doer,and an entrepreneur to use and have it to achieve their goals.The author advises:Do not complain I have no time-dare to make the first step and“the other will come,tumbling after”.Active individuals have time for every challenging initiative;passive ones have no time for anything.

离散时间的完全服务并行优化轮询排队系统特性分析

轮询是一种依次有序服务的系统资源动态调度机制.针对服务器在站点间查询、服务和转移过程中的流水线作业方式导致了系统整体服务效率较低的问题,本文提出了完全服务的并行优化轮询系统.首先,构建了系统的单服务器多队列排队模型和相应的系统状态方程,并精确解析出系统特性参数的完整数学解析表达式.此外,还提出了一种系统状态稳定性的判定方法,对不同负载状态下的系统稳定性进行了定量分析.计算机仿真的统计分析结果与理论计算值相一致.最后,系统性能分析表明,在保持周期性、无冲突服务的基础上,系统的队长、时延特性和稳定状态下负载能力均得到了较大的提高.

Clustering Countries on COVID-19 Data among Different Waves Using K-Means Clustering

The COVID-19 pandemic has caused an unprecedented spike in confirmed cases in 230 countries globally. In this work, a set of data from the COVID-19 coronavirus outbreak has been subjected to two well-known unsupervised learning techniques: K-means clustering and correlation. The COVID-19 virus has infected several nations, and K-means automatically looks for undiscovered clusters of those infections. To examine the spread of COVID-19 before a vaccine becomes widely available, this work has used unsupervised approaches to identify the crucial county-level confirmed cases, death cases, recover cases, total_cases_per_million, and total_deaths_per_million aspects of county-level variables. We combined countries into significant clusters using this feature subspace to assist more in-depth disease analysis efforts. As a result, we used a clustering technique to examine various trends in COVID-19 incidence and mortality across nations. This technique took the key components of a trajectory and incorporates them into a K-means clustering process. We separated the trend lines into measures that characterize various features of a trend. The measurements were first reduced in dimension, then clustered using a K-means algorithm. This method was used to individually calculate the incidence and death rates and then compare them.

基于不同统计模型对压力蒸汽灭菌器故障数据集的可靠性分析

目的:基于医院压力蒸汽灭菌器的故障数据,分析评估医疗机构中压力蒸汽灭菌器的可靠性。方法:利用威布尔分布(Weibull分布)、指数分布(Exponential分布)、对数-正态分布(Log-Normal分布)和q-威布尔分布(q-Weibull分布)4种统计模型对压力蒸汽灭菌器的故障数据进行分析,并使用图表工具展示不同分布统计模型在拟合数据时的性能。结果:4种统计模型对比显示,Log-Normal分布统计模型的修正赤池信息准则为564.4512,贝叶斯准则(568.7691)值最低,柯尔莫哥洛夫-斯米尔诺夫(KS)统计量(0.0739)最小,P值最大(P>0.05),表明分布拟合效果最好,最适合用于分析压力蒸汽灭菌器故障数据集的模型。结论:通过使用不同统计模型对压力蒸汽灭菌器故障数据的可靠性分析,可以为临床工程师优化压力蒸汽灭菌器维护策略提供依据。

天然气管道可靠性增长预测方法研究

为减少天然气管道投产前的设计和制造缺陷,提高使用寿命、运行可靠性和安全性、减少后期维修费用,通过统计模型结合试验数据实现对天然气管道可靠性增长水平的预测,提出天然气管道可靠性增长预测方法;分析常用可靠性增长模型并结合天然气管道可维修、小子样的特点,将Duane模型与AMSAA模型应用于天然气管道,结合点估计、趋势检验、拟合优度检验、区间估计和标准差,得出天然气管道可靠性增长模型,预测可靠性增长并进行实例验证。研究结果表明:Duane模型与AMSAA模型作为天然气管道可靠性增长试验具有可行性;其中AMSAA模型更具优势,得出天然气管道的瞬时无故障工作时间(MTBF)估计值可达到试验目标值,并预测MTBF达到2000 h时所需要的试验时间为317954611.3 h,未来第51次故障预测区间为[848.4609,939.6226],误差为1.25%,方法具有良好的适用性,可有效预测天然气管道可靠性增长。研究结果可为天然气管道设计改进提供指导。

融合均值榜样的反向互学习水母搜索算法

为解决水母搜索算法(jellyfish search algorithm,JS)的洋流运动缺乏多样性、群内运动缺乏引导性、种群间信息无交流,造成搜索速度慢、稳定性差及易早熟的问题,构建了一种融合均值榜样的反向互学习水母搜索算法(oppositional-mutual learning jellyfish search algorithm based on mean-value example,OMLJS).首先在水母跟随洋流运动(全局搜索)部分,利用前两代水母的平均位置代替只考虑上一代水母的平均位置来引导水母个体的位置更新,提高算法的全局搜索能力;其次在水母的群内主动运动(局部搜索)部分,利用最优个体代替随机个体来引导水母进行更有效的搜索,加快算法的收敛速度;然后在水母进入下一次迭代前增加对水母种群进行动态反向互学习步骤,增加种群多样性及增强种群间的信息交流,达到互补另外两个策略,提高算法的整体优化性能.选用12个经典的基准测试优化函数,将OMLJS与5个对比算法从解的平均值、最优值及方差进行对比分析,并用于求解最小生成树问题,OMLJS能够更快地找到最小生成树.实验结果表明,OMLJS的收敛速度、求解精度明显提高.