The reflection of hierarchical cluster analysis of co-occurrence matrices in SPSS

Purpose： To discuss the problems arising from hierarchical cluster analysis of co-occurrence matrices in SPSS, and the corresponding solutions. Design/methodology/approach： We design different methods of using the SPSS hierarchical clustering module for co-occurrence matrices in order to compare these methods. We offer the correct syntax to deactivate the similarity algorithm for clustering analysis within the hierarchical clustering module of SPSS. Findings： When one inputs co-occurrence matrices into the data editor of the SPSS hierarchical clustering module without deactivating the embedded similarity algorithm, the program calculates similarity twice, and thus distorts and overestimates the degree of similarity. Practical implications： We offer the correct syntax to block the similarity algorithm for clustering analysis in the SPSS hierarchical clustering module in the case of co-occurrence matrices. This syntax enables researchers to avoid obtaining incorrect results. Originality/value： This paper presents a method of editing syntax to prevent the default use of a similarity algorithm for SPSS＇s hierarchical clustering module. This will help researchers, especially those from China, to properly implement the co-occurrence matrix when using SPSS for hierarchical cluster analysis, in order to provide more scientific and rational results.

Analyzing the Urban Hierarchical Structure Based on Multiple Indicators of Economy and Industry: An Econometric Study in China

For a city,analyzing its advantages,disadvantages and the level of economic development in a country is important,especially for the cities in China developing at flying speed.The corresponding literatures for the cities in China have not considered the indicators of economy and industry in detail.In this paper,based on multiple indicators of economy and industry,the urban hierarchical structure of 285 cities above the prefecture level in China is investigated.The indicators from the economy,industry,infrastructure,medical care,population,education,culture,and employment levels are selected to establish a new indicator system for analyzing urban hierarchical structure.The factor analysis method is used to investigate the relationship between the variables of selected indicators and obtain the score of each common factor and comprehensive scores and rankings for 285 cities above the prefecture level in China.According to the comprehensive scores,285 cities above the prefecture level are clustered into 15 levels by using K-means clustering algorithm.Then,the hierarchical structure system of the cities above the prefecture level in China is obtained and corresponding policy implications are proposed.The results and implications can not only be applied to the urban planning and development in China but also offer a reference on other developing countries.The methodologies used in this paper can also be applied to study the urban hierarchical structure in other countries.

Cluster Analysis Assisted Float-Encoded Genetic Algorithm for a More Automated Characterization of Hydrocarbon Reservoirs

A genetic algorithm-based joint inversion method is presented for evaluating hydrocarbon-bearing geological formations. Conventional inversion procedures routinely used in the oil industry perform the inversion processing of borehole geophysical data locally. As having barely more types of data than unknowns in a depth, a set of marginally over-determined inverse problems has to be solved along a borehole, which is a rather noise sensitive procedure. For the reduction of noise effect, the amount of overdetermination must be increased. To fulfill this requirement, we suggest the use of our interval inversion method, which inverts simultaneously all data from a greater depth interval to estimate petrophysical parameters of reservoirs to the same interval. A series expansion based discretization scheme ensures much more data against unknowns that significantly reduces the estimation error of model parameters. The knowledge of reservoir boundaries is also required for reserve calculation. Well logs contain information about layer-thicknesses, but they cannot be extracted by the local inversion approach. We showed earlier that the depth coordinates of layerboundaries can be determined within the interval inversion procedure. The weakness of method is that the output of inversion is highly influenced by arbitrary assumptions made for layer-thicknesses when creating a starting model (i.e. number of layers, search domain of thicknesses). In this study, we apply an automated procedure for the determination of rock interfaces. We perform multidimensional hierarchical cluster analysis on well-logging data before inversion that separates the measuring points of different layers on a lithological basis. As a result, the vertical distribution of clusters furnishes the coordinates of layer-boundaries, which are then used as initial model parameters for the interval inversion procedure. The improved inversion method gives a fast, automatic and objective estimation to layer-boundaries and petrophysical parameters, which is demonstrated by a hydrocarbon field example.

高密度PCB锡膏喷印的分层路径规划

针对传统算法求解高密度印制电路板锡膏喷印路径规划问题存在收敛速度慢、易陷入局部最优的不足,提出了一种融合密度峰值聚类算法和蚁群算法的分层路径规划方法。利用密度峰值聚类算法处理分布呈矩形或线形的高密度焊盘,将原始问题分解为上层聚类中心与下层小规模子问题集合;蚁群算法求解下层子问题获得子路径集合,求解上层聚类中心得到初始全局路径的重组路线;为避免子路径重组过程中陷入局部最优,利用局部搜索算法对初始全局路径进行二次优化,得到最优全局路径。实验结果表明,该分层路径规划方法降低了全局路径求解的复杂度,提升了算法收敛速度,缩短了加工路径总长度,有效提高了高密度印制电路板锡膏喷印的加工效率。

突发公共卫生事件下救援物资配送方案研究

在突发公共卫生事件封控情况下,大规模应急救援物资的配送需要兼顾效率、成本及安全性,在有限的救援投入下获取最大化资源利用和最小化配送成本,同时避免人员的交叉感染。为此,提出了基于两层配送网络的应急物资配送方案,并提出改进粒子群优化算法(Improved Particle Swarm Optimization Algorithm,IPSOA)对配送路径进行优化。首先,根据行政区划分以及物资需求点的空间分布、各需求点的居民人数和需求量,采用层次聚类算法建立由“物资储备中心-物资集散中心”和“物资集散中心-物资需求点”构成的两层配送网络,每层配送网络都由多配送中心和多需求点组成,该物资配送属于多配送车辆的多中心车辆路径规划问题(Multi-Depot Vehicle Routing Problem,MDVRP)。其次,为了获取合理高效的配送路径,以配送成本最小为目标,构建基于多约束的物资配送优化模型,并提出基于人工鱼群算法(Artificial Fish Swarm Algorithm,AFSA)的粒子群优化(AFSA-PSO)算法对两层配送网络进行求解。最后,以某市9个行政区在疫情封控期间的数据为例验证两层配送网络和AFSA-PSO算法的有效性。结果表明:构建的两层配送网络和AFSA-PSO算法能够对多车辆MDVRP问题进行有效求解,科学规划配送路径;算法对比发现,AFSA-PSO能够避免模型过早收敛,且能够获取比遗传算法和粒子群优化算法更少的车辆数和更短的配送路径,有效地降低配送成本,提高经济效益。

Detecting community structure using label propagation with consensus weight in complex network

Community detection is a fundamental work to analyse the structural and functional properties of complex networks. The label propagation algorithm （LPA） is a near linear time algorithm to find a good community structure. Despite various subsequent advances, an important issue of this algorithm has not yet been properly addressed. Random update orders within the algorithm severely hamper the stability of the identified community structure. In this paper, we executed the basic label propagation algorithm on networks multiple times, to obtain a set of consensus partitions. Based on these consensus partitions, we created a consensus weighted graph. In this consensus weighted graph, the weight value of the edge was the proportion value that the number of node pairs allocated in the same cluster was divided by the total number of partitions. Then, we introduced consensus weight to indicate the direction of label propagation. In label update steps, by computing the mixing value of consensus weight and label frequency, a node adopted the label which has the maximum mixing value instead of the most frequent one. For extending to different networks, we introduced a proportion parameter to adjust the proportion of consensus weight and label frequency in computing mixing value. Finally, we proposed an approach named the label propagation algorithm with consensus weight （LPAcw）, and the experimental results showed that the LPAcw could enhance considerably both the stability and the accuracy of community partitions.

A Novel Stable Clustering Design Method for Hierarchical Satellite Network

This article proposes a novel stable clustering design method for hierarchical satellite network in order to increase its stability,reduce the overhead of storage and exert effective control of the delay performances based on a 5-dimensional vector model. According to the function of stability measureinent and owing to the limitation of minimal average routing table length, the hierarchical satellite network is grouped into separate stable connected clusters to improve destruction resistance and reconstruction ability in the future integrated network. In each cluster, redundant communication links with little contribution to network stability and slight influences on delay variation are deleted to satisfy the requirements for stability and connectivity by means of optimal link resources, and, also, the idea of logical weight is introduced to select the optimal satellites used to communicate with neighboring cluster satellites. Finally, the feasibility and effectiveness of the proposed method are verified by comparing it with the simulated performances of other two typical hierarchical satellite networks, double layer satellite constellation（DLSC） and satellite over satellite（SOS）.

基于凝聚层次聚类算法的ATT&CK模型改进

在应用ATT&CK模型(网络攻击模型)进行网络安全威胁分析的过程中,ATT&CK模型提供的技术集合过于复杂。针对ATT&CK模型应用复杂的问题,论文对模型的技术集进行聚类简化研究,提出了基于聚类算法的模型改进方法,首先对ATT&CK模型的技术集合进行量化和聚类趋势评估,然后对量化的数据应用凝聚层次聚类算法得到简化的聚类结果,最后通过实验验证模型改进有效性。

基于多信息融合的层次聚类测井曲线自动分层方法

随着人工智能的快速发展,机器学习的应用范围越来越广泛,将机器学习的方法用于测井曲线分层可以提高分层效率和精度。在利用测井资料进行岩性识别、沉积相分析等研究时,先要对测井曲线进行分层。文中提出一种基于多信息融合的层次聚类分层方法,实现了对测井曲线的自动分层。首先,采用滤波的方式滤除曲线上的噪点,对数据进行归一化处理,消除量纲的影响;其次,通过特征优选,选择包含较多地层信息的特征曲线,构造一个滤波器,将其中相似性较高的曲线融合,曲线融合的权值通过遗传算法求得;最后,使用层次聚类方法对多信息融合后的测井数据进行划分,将分层结果与人工分层结果进行对比验证。该方法能够提高分层效率,为地质勘探工作提供可靠的分层依据。

基于风电分时电价的虚拟电厂参与清洁供暖运营优化方法

随着“碳达峰、碳中和”目标的提出,迅速发展的风电由于其随机性与波动性,面临突出的风电消纳问题。蓄热式电采暖作为中国北方地区主要供暖设备,虚拟电厂作为需求侧资源的主要聚合技术手段,聚合蓄热式电采暖的虚拟电厂可为消纳风电、提高风电利用率提供解决途径。对此,提出一种基于风电功率的分时电价划分方法,实现虚拟电厂聚合蓄热式电采暖参与基于分时电价的清洁供暖交易优化运营。首先,阐述虚拟电厂聚合蓄热式电采暖用户参与风电供暖的交易模式;其次,考虑热惯性对蓄热式电采暖和房屋进行精细化建模,提出基于层次凝聚聚类算法的分时电价方法,建立基于Weber-Fechner定律的负荷模糊响应模型,并构建多方主体综合收益最大、弃风量最小和负荷波动最小的虚拟电厂多目标运营优化模型;最后,通过算例分析风电消纳效果和虚拟电厂收益,验证该方法能够有效促进风电消纳、提高多方主体积极性,并具有一定的规模经济性,以期为缓解弃风问题提供参考。

间歇式信息传输条件下无人机搜索覆盖规划

在基站通信范围受限条件下,若无人机(unmanned aerial vehicle,UAV)执行覆盖搜索任务时经常返回至基站通信范围内实现间歇式信息传输,能够扩展其覆盖区域和提高执行任务的灵活性。为最小化所有环境位点信息传回基站的时间之和,需解决覆盖规划和间歇式通信时机选择的耦合问题。在覆盖的目标点较少且分散时,采用改进的层次聚类方法求解每次往返需要覆盖的路径点集合。在需要进行区域全覆盖时,则在求解完区域的覆盖路径后,以最小化时间之和为目标,对目标函数进行分析,确定最优返回次数的搜索范围,压缩解空间。对该搜索范围进行遍历搜索得到最优往返次数,然后利用遗传算法优化UAV返回位点。与前沿算法对比,所提算法在目标函数和覆盖路径质量上具有一定的提升。

基于等效电势动态相似性的直驱式风电场分群等值方法

针对大规模直驱式风电场并网系统暂态电压等值建模困难的问题,考虑了直驱风机全功率变流器不同控制环节的作用机理,提出了一种直驱风机的暂态电压等值模型与动态聚类方法。建立计及Chopper电路动作过程的直驱风机暂态模型,构建了适用于暂态电压分析的等效电势指标。该指标能够反映暂态过程中直驱风机并网功率和端口电压的动态过程,并根据该指标的动态变化来反映系统故障下的暂态电压特性。针对风电场内各直驱风机物理位置、行为特征的差异性,提出了一种基于约束动态时间规整的相似度分析方法,构建了能够表征不同机组等效电势指标差异性的相似度矩阵。在此基础上,采用层次凝聚聚类算法实现了不同直驱风机的动态聚合。在PSCAD/EMTDC中建立了直驱式风电场多机等值模型,通过对比不同故障场景下的等值精度验证了所提方法的有效性和优越性。

无线传感器网络中一种基于聚合层次聚类的分簇路由算法

针对无线传感器网络中节点连接以及能量受限不足的问题,为了延长网络寿命,提出了一种基于AHC的分簇路由算法(HACCRA)。该算法首先运用AHC对网络节点分簇,接着为簇首选择、簇形成和路径构建分别定义了恰当的决策目标函数,运用能量阈值、提出距离阈值、并且路由过程优先考虑簇首节点之间的一对一连接,有效解决了路由算法中分簇和路由不衔接的问题。仿真结果表明,与JCR、ICR以及DCK-LEACH相比,HACCRA能够更好地实现网络节点的能耗均衡,保证网络数据传输的连接性,从而延长网络寿命。

基于BiLSTM算法的课程评论情感分类及其成因探究

设计了一种基于BiLSTM算法的中文评论情感分类模型,针对在线教育平台的学生评论进行情感分析,分为“Positive”“Negative”和“Neutral”三类。利用网易云课程平台的评论数据,结合Bert预训练模型进行词向量训练。结合SVM分类原理与重采样技术进行模型优化,实验结果显示优化后的模型在精确率、准确率、召回率和F1值上表现优异。通过层次聚类与语义网络分析,可视化展示评论的情感成因,为课程改进提供科学依据。

基于分层关系度量网络的单样本人脸识别

单样本训练集中的每个类只有一张样本,训练样本数量的不足将使模型得不到有效训练,使得模型无法准确提取具有类内变化的人脸面部特征,导致模型的识别率低下.针对该问题,提出了一种基于分层关系度量网络(Hierarchical Relation Measure Network,HRMN)的单样本人脸识别模型.首先,使用语义网络将训练集中人脸进行性别层次的语义划分;随后,应用小批量K均值聚类算法对所划分的第一层语义人脸特征进行分层聚类,得到具有多个不同抽象层次的分层特征树(Hierarchical Feature Tree,HFT).最后,使用所构建的多层关系度量网络计算出不同抽象层次面部特征与目标样本间的加权融合相似度,根据相似度得出目标样本的类别信息.为了验证所提算法的有效性,本文进行了大量的实验,实验结果表明,该模型优于几种近年来应用较为广泛的单样本人脸识别模型.

基于机器学习空间聚类的出租车停靠站点布局规划

针对出租车随意停靠给城市交通带来的负面影响,为规范出租车营运秩序、改善出租车营运环境和居民乘车条件,提出一种将出租车出行空间信息与机器学习算法相结合的出租车停靠站点布局规划方法。首先利用出租车GPS轨迹数据提取出租车出行起点,然后采用HDBSCAN聚类算法对起点进行空间密度聚类,形成聚类簇后以其中心点作为出租车停靠站点布局的备选点。最后,为验证所提方法的可行性和有效性,选取重庆市中心城区一土地利用类型丰富、人口密度高的典型区域进行案例分析。结果显示,107个备选点主要分布于商业中心区和居住集中区,与出租车出行高需求区域的空间分布基本吻合;布局的出租车停靠站点在300 m范围内的覆盖率达到76.0%,未覆盖区域主要为城市绿地和水体。研究表明,机器学习算法可实现出租车停靠站点的高效布局规划,但在规划和实施阶段,停靠站点的设置还应结合邻近区域的建成环境特点综合考虑。

基于贝叶斯层级模型的用户异常行为检测研究

大多数操作系统的安全防护主要依赖基于签名或基于规则的方法,因此现有大多数的异常检测方法精度较低。因此,利用贝叶斯模型为同类群体建模,并结合时间效应与分层原则,为用户实体行为分析(User and Entity Behavior Analytics,UEBA)研究提供精度更高的数据集。然后,将基于实际记录的用户行为数据与贝叶斯层级图模型推测出的数据进行比较,降低模型中的误报率。该方法主要分为两个阶段:在第1阶段,基于数据驱动的方法形成用户行为聚类,定义用户的个人身份验证模式;在第2阶段,同时考虑到周期性因素和分层原则,并通过泊松分布建模。研究表明,数据驱动的聚类方法在减少误报方面能够取得更好的结果,并减轻网络安全管理的负担,进一步减少误报数量。

基于自编码器的网络流量异常检测

现有流量异常检测方案在面对日益复杂的网络流量和维度增加的数据结构时,存在误报率高、效率低以及实用性差等问题。针对这些问题,本文提出一种基于自编码器的网络流量异常检测模型。该模型首先基于随机森林算法对网络流量提取特征并筛选最优特征集,通过层次聚类算法将特征向量集划分为若干子集来降低特征维度;然后由自编码器并行处理特征子集并计算RMSE值,定义多次实验的最大平均RMSE值为正常流量阈值;利用测试数据的平均RMSE值和阈值判定异常流量。实验结果表明,本文模型召回率较传统的异常检测方法平均提高了4.3个百分点,运行时间降低了约37%。

促进用户负荷特性优化的分时电价机制设计方法

在电力供应结构和消费方式变化背景下,提出一种分时电价机制设计方法,旨在改善用户负荷特性,促进电网削峰填谷。根据工业、商业和居民三类用户的负荷分布特性,通过分层聚类方法对不同季节的峰谷时段进行重新划分,并引入深谷时段,解决原有分时电价机制时段划分不准确的问题。在满足覆盖发电成本前提下,通过减少用户用电成本与扩大峰谷价差,进一步激励用户调整用电行为,并采用量子遗传算法(quantum genetic algorithm,QGA)对时段电价制定的优化问题进行求解。通过实际算例,计算用户响应改进后分时电价机制前后的削峰量和填谷量,验证所设计的分时电价机制可以降低用户用电成本,并有效转移电网高峰时段负荷,缓解时段性、季节性的供电压力问题。

基于集体离群点挖掘的电网潜在故障检测算法

针对城市电网故障早期阶段的隐蔽性、潜伏性特点,通过构建“集体离群点-故障模式”的度量规则,对电网系统中全等级异常电流波动信号进行层次聚类分析,将区域性潜在故障检测问题转换为挖掘故障信号数据中的集体离群点问题。为提高检测效率,设计了一种基于不动点迭代法的层次聚类改进算法(Fixed point iteration based k-medoids,FPK-medoids),利用不动点较强的局部搜索能力提高聚类收敛速度。在测试数据集和实例数据集上进行实验,结果表明改进算法的收敛性能优于传统算法,检测模型能够精准识别电网中的区域性潜在故障。