Comprehensive K-Means Clustering

The k-means algorithm is a popular data clustering technique due to its speed and simplicity. However, it is susceptible to issues such as sensitivity to the chosen seeds, and inaccurate clusters due to poor initial seeds, particularly in complex datasets or datasets with non-spherical clusters. In this paper, a Comprehensive K-Means Clustering algorithm is presented, in which multiple trials of k-means are performed on a given dataset. The clustering results from each trial are transformed into a five-dimensional data point, containing the scope values of the x and y coordinates of the clusters along with the number of points within that cluster. A graph is then generated displaying the configuration of these points using Principal Component Analysis (PCA), from which we can observe and determine the common clustering patterns in the dataset. The robustness and strength of these patterns are then examined by observing the variance of the results of each trial, wherein a different subset of the data keeping a certain percentage of original data points is clustered. By aggregating information from multiple trials, we can distinguish clusters that consistently emerge across different runs from those that are more sensitive or unlikely, hence deriving more reliable conclusions about the underlying structure of complex datasets. Our experiments show that our algorithm is able to find the most common associations between different dimensions of data over multiple trials, often more accurately than other algorithms, as well as measure stability of these clusters, an ability that other k-means algorithms lack.

Hierarchical hesitant fuzzy K-means clustering algorithm

Due to the limitation and hesitation in one＇s knowledge, the membership degree of an element to a given set usually has a few different values, in which the conventional fuzzy sets are invalid. Hesitant fuzzy sets are a powerful tool to treat this case. The present paper focuses on investigating the clustering technique for hesitant fuzzy sets based on the K-means clustering algorithm which takes the results of hierarchical clustering as the initial clusters. Finally, two examples demonstrate the validity of our algorithm.

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。

K-MEANS CLUSTERING FOR CLASSIFICATION OF THE NORTHWESTERN PACIFIC TROPICAL CYCLONE TRACKS

Based on the Joint Typhoon Warning Center(JTWC) best-track dataset between 1965 and 2009 and the characteristic parameters including tropical cyclone(TC) position,intensity,path length and direction,a method for objective classification of the Northwestern Pacific tropical cyclone tracks is established by using k-means Clustering.The TC lifespan,energy,active season and landfall probability of seven clusters of tropical cyclone tracks are comparatively analyzed.The characteristics of these parameters are quite different among different tropical cyclone track clusters.From the trend of the past two decades,the frequency of the western recurving cluster(accounting for 21.3% of the total) increased,and the lifespan elongated slightly,which differs from the other clusters.The annual variation of the Power Dissipation Index(PDI) of most clusters mainly depended on the TC intensity and frequency.However,the annual variation of the PDI in the northwestern moving then recurving cluster and the pelagic west-northwest moving cluster mainly depended on the frequency.

Geochemical and Geostatistical Studies for Estimating Gold Grade in Tarq Prospect Area by K-Means Clustering Method

Tarq geochemical 1:100,000 Sheet is located in Isfahan province which is investigated by Iran’s Geological and Explorations Organization using stream sediment analyzes. This area has stratigraphy of Precambrian to Quaternary rocks and is located in the Central Iran zone. According to the presence of signs of gold mineralization in this area, it is necessary to identify important mineral areas in this area. Therefore, finding information is necessary about the relationship and monitoring the elements of gold, arsenic, and antimony relative to each other in this area to determine the extent of geochemical halos and to estimate the grade. Therefore, a well-known and useful K-means method is used for monitoring the elements in the present study, this is a clustering method based on minimizing the total Euclidean distances of each sample from the center of the classes which are assigned to them. In this research, the clustering quality function and the utility rate of the sample have been used in the desired cluster (S(i)) to determine the optimum number of clusters. Finally, with regard to the cluster centers and the results, the equations were used to predict the amount of the gold element based on four parameters of arsenic and antimony grade, length and width of sampling points.

Optimization of constitutive parameters of foundation soils k-means clustering analysis

The goal of this study was to optimize the constitutive parameters of foundation soils using a k-means algorithm with clustering analysis. A database was collected from unconfined compression tests, Proctor tests and grain distribution tests of soils taken from three different types of foundation pits： raft foundations, partial raft foundations and strip foundations. k-means algorithm with clustering analysis was applied to determine the most appropriate foundation type given the un- confined compression strengths and other parameters of the different soils.

Blind source separation by weighted K-means clustering

Blind separation of sparse sources （BSSS） is discussed. The BSSS method based on the conventional K-means clustering is very fast and is also easy to implement. However, the accuracy of this method is generally not satisfactory. The contribution of the vector x（t） with different modules is theoretically proved to be unequal, and a weighted K-means clustering method is proposed on this grounds. The proposed algorithm is not only as fast as the conventional K-means clustering method, but can also achieve considerably accurate results, which is demonstrated by numerical experiments.

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。

基于改进K-means数据聚类算法的网络入侵检测

随着入侵手段的不断更新和升级,传统入侵检测方法准确率下降、检测时间延长,无法满足网络防御要求。为此,提出一种经过改进K均值(K-means)数据聚类算法,以应对不断升级的网络入侵行为。先以防火墙日志为基础转换数值,然后基于粒子群算法求取最优初始聚类中心,实现K-means数据聚类算法的改进;最后以计算得出的特征值为输入项,实现对网络入侵行为的精准检测。结果表明:K-means算法改进后较改进前的戴维森堡丁指数更小,均低于0.6,达到了改进目的。改进K-means算法各样本的准确率均高于90%,相对更高,检测时间均低于10 s,相对更少,说明该方法能够以高效率完成更准确的网络入侵检测。

基于蚁群算法的三支k-means聚类算法

在聚类分析中,三支k-means聚类算法较具有较强的处理边界不确定数据的能力,但仍然存在对初始聚类中心敏感的问题.通过将蚁群算法和三支k-means聚类算法相结合,给出了一种基于蚁群算法的三支k-means聚类算法来解决这一问题.利用蚁群算法中随机概率选择策略和信息素的正负反馈机制,动态调整权重的方法,对三支k-means聚类算法进行优化.在UCI数据集上实验证明,该方法对聚类结果的性能指标有所提高.

管制扇区运行稳度K-means聚类与分析

为更好地分析管制扇区运行存在的稳定亚安全状态和不稳定亚安全状态,使用K-means算法划分超容比(ECR)、滞留度和飞行姿态混合比3个管制扇区运行稳度评价指标聚类,确定管制扇区运行稳度最佳等级划分;聚类分析单一指标,获得各等级对应的指标阈值,结合熵权法计算的指标权重,遵循隶属度最大原则,获取各时间段的管制扇区运行稳度等级,构建管制扇区运行稳度综合评价模型;选取厦门01号扇区的实际飞行数据,从稳度和趋度2个角度更加全面地分析管制扇区运行态势。结果表明:管制扇区运行稳度等级划分为3类时效果最好;稳度受空中交通流和管制状况的影响会随时间而变化,尤其7:30—9:15和20:00—21:00这2个时间段管制扇区运行稳度的变化最为明显,需引起管制员高度重视,提高空域运行安全。

基于改进K-means聚类和遗传算法的混合算法求解异构车辆路径问题

由于目前单一车型配送存在资源浪费和效率低下等问题,选取确定数量的不同车型对各客户点进行配送服务往往可以得到更优的配送路径方案。针对这一点,描述了一种异构车辆路径问题,并建立了具有固定车辆数且考虑固定成本、可变成本以及时间窗惩罚成本的混合整数规划模型。同时,提出了一种基于改进K-means聚类和遗传算法的混合算法对模型进行求解。实验仿真先求解不考虑时间窗的问题初步证明混合算法的有效性,再在带时间窗的问题中求解不同规模算例的单一及异构车型结果,以证明异构车型配送更优。最后,对该混合算法的求解结果与其他混合算法的求解结果进行对比分析,证明了混合算法的优越性。研究结果表明:该混合算法求解的异构车型结果优于单一车型,并且比其他混合算法求解的异构车型结果更优,异构车辆配送使用的配送车辆数更少,总成本也更低,该混合算法具有更好的效率和性能。

基于k-means聚类算法的兴义维蚋幼虫龄数的估算

目的探讨基于k-means聚类算法估算兴义维蚋幼虫的龄数,以明确虫龄与日龄及鳃斑发育阶段的关系。方法采集贵州青岩河流中兴义维蚋虫卵,于实验室的蚋类饲养系统中培育至幼虫,每日收集幼虫至大量化蛹,持续20 d;收集到幼虫1112头,于体视显微镜下测量头壳长(HCW)、后颊长(PGL)、上颚基横骨长(MPL)及体长(BL),观察不同虫龄幼虫的破卵器、鳃斑及性腺的形态学特征,并判断其龄期、分析虫龄与日龄和鳃斑发育关系;选取具有明显腮斑发育的兴义维蚋幼虫10头、制作石蜡切片,采用HE染色鉴定精巢和卵巢、辅助确认性别鉴定结果;采用k-means聚类方法划分形态计量学数据、利用Brooks-Dyar定律检测k-means聚类结果,R语言下行聚类与Brooks-Dyar定律检验、t检验等,根据拟合度分析判断兴义维蚋幼虫龄数。结果1112头兴义维蚋幼虫中有破卵器89头,出现鳃斑发育334头,6~7龄幼虫320头,有预蛹特征34头;Brooks-Dyar定律与破卵器、鳃斑形态特征显示7龄幼虫假设符合昆虫幼虫生长规律;组织学观察见幼虫精巢为椭圆形、体积大、外有几丁质层包裹,卵巢为长条形、体积小、后端有色素细胞包裹;鉴定6、7龄幼虫性别结果,仅7龄幼虫雌雄性PGL有差异(P<0.05);幼虫虫龄与日龄、鳃斑发育关系结果显示,约2~3 d对应1个幼虫生长龄期,第17天首见幼虫蛹化,6龄幼虫出现明显的鳃斑。结论兴义维蚋幼虫具7龄,实验室下幼虫发育约需3周,最短17 d;腮斑发育起始于6龄,7龄出现明显形态学特征。

基于交通拥堵信息的高速公路拥堵路段ACK-Means聚类

为了充分利用实际高速公路路段交通拥堵信息,更合理地聚类交通拥堵的内在规律和特征变化,提出自适应确定聚类中心C和类别K值(adaptive center and K-means value,ACK-Means)的聚类算法,进行高速公路拥堵路段聚类。ACK-Means算法借助簇类密度、簇类间距以及簇类强度,同时又考虑到数据样本的偶然性,对离群点进行合理分配,ACK-Means算法可实现自适应确定聚类中心C和类别K值。基于实际交通拥堵信息构建数据集,Python编程实现高速公路拥堵路段ACK-Means聚类,巧妙解决了高速公路拥堵路段聚类数目K和聚类中心C设定问题。聚类结果表明,ACK-Means算法实现高速公路拥堵路段无监督聚类,聚类结果完全基于实际的高速公路交通拥堵信息,具有更高的实用性。

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。

基于改进K-means聚类的轨道交通基础设施分布式光伏发电典型场景生成及出力特性分析

受限于自然条件,光伏出力具有很强的随机性。为准确评估轨道交通基础设施分布式光伏发电的光伏出力特性,提出一种基于改进K-means聚类算法的轨道交通基础设施分布式光伏发电典型场景生成方法,并基于此进行光伏出力特性分析。首先,基于分布式光伏发电设施以及气象数据,利用PVsyst软件模拟光伏发电出力数据。然后,针对基本K-means聚类算法聚类参数和初始聚类中心盲目性高的问题,结合聚类有效性指标(Density based index,DBI)和层次聚类对其进行改进并利用改进K-means聚类算法生成光伏典型日出力场景。最后,基于华中地区某地轨道交通基础设施分布式光伏系统对所提方法的有效性和优越性进行验证,并通过定性和定量分析各典型场景的出力特性揭示轨道交通基础设施分布式光伏出力的规律和特点。

Hybrid Genetic Algorithm with K-Means for Clustering Problems

The K-means method is one of the most widely used clustering methods and has been implemented in many fields of science and technology. One of the major problems of the k-means algorithm is that it may produce empty clusters depending on initial center vectors. Genetic Algorithms (GAs) are adaptive heuristic search algorithm based on the evolutionary principles of natural selection and genetics. This paper presents a hybrid version of the k-means algorithm with GAs that efficiently eliminates this empty cluster problem. Results of simulation experiments using several data sets prove our claim.

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 .

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。