Semi-supervised Affinity Propagation Clustering Based on Subtractive Clustering for Large-Scale Data Sets

In the face of a growing number of large-scale data sets, affinity propagation clustering algorithm to calculate the process required to build the similarity matrix, will bring huge storage and computation. Therefore, this paper proposes an improved affinity propagation clustering algorithm. First, add the subtraction clustering, using the density value of the data points to obtain the point of initial clusters. Then, calculate the similarity distance between the initial cluster points, and reference the idea of semi-supervised clustering, adding pairs restriction information, structure sparse similarity matrix. Finally, the cluster representative points conduct AP clustering until a suitable cluster division.Experimental results show that the algorithm allows the calculation is greatly reduced, the similarity matrix storage capacity is also reduced, and better than the original algorithm on the clustering effect and processing speed.

Scaling up Kernel Grower Clustering Method for Large Data Sets via Core-sets

核栽培者是聚类最近 Camastra 和 Verri 建议的方法的一个新奇的核。它证明为各种各样的数据的好性能关于流行聚类的算法有利地设定并且比较。然而，方法的主要缺点是在处理大数据集合的弱可伸缩能力，它极大地限制它的应用程序。在这份报纸，我们用核心集合建议一个可伸缩起来的核栽培者方法，它是比为聚类的大数据的原来的方法显著地快的。同时，它能处理很大的数据集合。象合成数据集合一样的基准数据集合的数字实验显示出建议方法的效率。方法也被用于真实图象分割说明它的性能。

Picture-Neutrosophic Trusted Safe Semi-Supervised Fuzzy Clustering for Noisy Data

Clustering is a crucial method for deciphering data structure and producing new information.Due to its significance in revealing fundamental connections between the human brain and events,it is essential to utilize clustering for cognitive research.Dealing with noisy data caused by inaccurate synthesis from several sources or misleading data production processes is one of the most intriguing clustering difficulties.Noisy data can lead to incorrect object recognition and inference.This research aims to innovate a novel clustering approach,named Picture-Neutrosophic Trusted Safe Semi-Supervised Fuzzy Clustering(PNTS3FCM),to solve the clustering problem with noisy data using neutral and refusal degrees in the definition of Picture Fuzzy Set(PFS)and Neutrosophic Set(NS).Our contribution is to propose a new optimization model with four essential components:clustering,outlier removal,safe semi-supervised fuzzy clustering and partitioning with labeled and unlabeled data.The effectiveness and flexibility of the proposed technique are estimated and compared with the state-of-art methods,standard Picture fuzzy clustering(FC-PFS)and Confidence-weighted safe semi-supervised clustering(CS3FCM)on benchmark UCI datasets.The experimental results show that our method is better at least 10/15 datasets than the compared methods in terms of clustering quality and computational time.

Autonomous Clustering Using Rough Set Theory

This paper proposes a clustering technique that minimizes the need for subjective human intervention and is based on elements of rough set theory （RST）. The proposed algorithm is unified in its approach to clustering and makes use of both local and global data properties to obtain clustering solutions. It handles single-type and mixed attribute data sets with ease. The results from three data sets of single and mixed attribute types are used to illustrate the technique and establish its efficiency.

Encephalitis Detection from EEG Fuzzy Density-Based Clustering Model with Multiple Centroid

Encephalitis is a brain inflammation disease.Encephalitis can yield to seizures,motor disability,or some loss of vision or hearing.Sometimes,encepha-litis can be a life-threatening and proper diagnosis in an early stage is very crucial.Therefore,in this paper,we are proposing a deep learning model for computerized detection of Encephalitis from the electroencephalogram data(EEG).Also,we propose a Density-Based Clustering model to classify the distinctive waves of Encephalitis.Customary clustering models usually employ a computed single centroid virtual point to define the cluster configuration,but this single point does not contain adequate information.To precisely extract accurate inner structural data,a multiple centroids approach is employed and defined in this paper,which defines the cluster configuration by allocating weights to each state in the cluster.The multiple EEG view fuzzy learning approach incorporates data from every sin-gle view to enhance the model's clustering performance.Also a fuzzy Density-Based Clustering model with multiple centroids(FDBC)is presented.This model employs multiple real state centroids to define clusters using Partitioning Around Centroids algorithm.The Experimental results validate the medical importance of the proposed clustering model.

A Direct Data-Cluster Analysis Method Based on Neutrosophic Set Implication

Raw data are classified using clustering techniques in a reasonable manner to create disjoint clusters.A lot of clustering algorithms based on specific parameters have been proposed to access a high volume of datasets.This paper focuses on cluster analysis based on neutrosophic set implication,i.e.,a k-means algorithm with a threshold-based clustering technique.This algorithm addresses the shortcomings of the k-means clustering algorithm by overcoming the limitations of the threshold-based clustering algorithm.To evaluate the validity of the proposed method,several validity measures and validity indices are applied to the Iris dataset(from the University of California,Irvine,Machine Learning Repository)along with k-means and threshold-based clustering algorithms.The proposed method results in more segregated datasets with compacted clusters,thus achieving higher validity indices.The method also eliminates the limitations of threshold-based clustering algorithm and validates measures and respective indices along with k-means and threshold-based clustering algorithms.

Clustering method based on data division and partition

Many classical clustering algorithms do good jobs on their prerequisite but do not scale well when being applied to deal with very large data sets(VLDS).In this work,a novel division and partition clustering method(DP) was proposed to solve the problem.DP cut the source data set into data blocks,and extracted the eigenvector for each data block to form the local feature set.The local feature set was used in the second round of the characteristics polymerization process for the source data to find the global eigenvector.Ultimately according to the global eigenvector,the data set was assigned by criterion of minimum distance.The experimental results show that it is more robust than the conventional clusterings.Characteristics of not sensitive to data dimensions,distribution and number of nature clustering make it have a wide range of applications in clustering VLDS.

Big Data Clustering Optimization Based on Intuitionistic Fuzzy Set Distance and Particle Swarm Optimization forWireless Sensor Networks

Big data clustering plays an important role in the field of data processing in wireless sensor networks.However,there are some problems such as poor clustering effect and low Jaccard coefficient.This paper proposes a novel big data clustering optimization method based on intuitionistic fuzzy set distance and particle swarm optimization for wireless sensor networks.This method combines principal component analysis method and information entropy dimensionality reduction to process big data and reduce the time required for data clustering.A new distance measurement method of intuitionistic fuzzy sets is defined,which not only considers membership and non-membership information,but also considers the allocation of hesitancy to membership and non-membership,thereby indirectly introducing hesitancy into intuitionistic fuzzy set distance.The intuitionistic fuzzy kernel clustering algorithm is used to cluster big data,and particle swarm optimization is introduced to optimize the intuitionistic fuzzy kernel clustering method.The optimized algorithm is used to obtain the optimization results of wireless sensor network big data clustering,and the big data clustering is realized.Simulation results show that the proposed method has good clustering effect by comparing with other state-of-the-art clustering methods.

Application of Self-Organizing Feature Map Neural Network Based on K-means Clustering in Network Intrusion Detection

Due to the widespread use of the Internet,customer information is vulnerable to computer systems attack,which brings urgent need for the intrusion detection technology.Recently,network intrusion detection has been one of the most important technologies in network security detection.The accuracy of network intrusion detection has reached higher accuracy so far.However,these methods have very low efficiency in network intrusion detection,even the most popular SOM neural network method.In this paper,an efficient and fast network intrusion detection method was proposed.Firstly,the fundamental of the two different methods are introduced respectively.Then,the selforganizing feature map neural network based on K-means clustering(KSOM)algorithms was presented to improve the efficiency of network intrusion detection.Finally,the NSLKDD is used as network intrusion data set to demonstrate that the KSOM method can significantly reduce the number of clustering iteration than SOM method without substantially affecting the clustering results and the accuracy is much higher than Kmeans method.The Experimental results show that our method can relatively improve the accuracy of network intrusion and significantly reduce the number of clustering iteration.

基于最小数据集的油茶林土壤质量评价

为给油茶(Camellia)林土壤质量提升和改善提供理论支撑,测定土壤pH值及有机质、全氮、全磷、全钾、水解氮、有效磷、速效钾、代换性钙、代换性镁、有效铜、有效锌、有效硼、有效铁和有效锰含量,采用主成分分析法和聚类分析法建立最小数据集,基于土壤质量指数(SQI)对油茶林土壤质量进行评价。结果表明,油茶林养分属于中等水平,土壤pH值为4.77,酸化现象明显。基于主成分分析法建立最小数据集的评价指标包括全氮、有效磷、代换性镁、有效铜和有效锰含量。基于主成分分析法建立最小数据集计算的油茶林SQI为0.249~0.684,均值为0.459,土壤质量等级以Ⅱ~Ⅴ级为主,无Ⅰ级土壤。与聚类分析法相比,基于主成分分析法建立最小数据集能提取大部分数据信息,可有效评价油茶林土壤质量。

重庆市植烟土壤质量评价指标体系的构建与应用

为准确评价重庆市烟区土壤质量,以重庆2 513个代表性植烟单元(每个单元面积约6.7 hm^(2))的典型烟田土壤理化指标数据为基础,采用聚类分析法和主成分分析法建立了土壤质量评价最小数据集,构建了植烟土壤质量评价指标体系。结果表明:(1)基于主成分分析法建立的土壤质量评价体系更适合重庆烟区土壤质量评价,评价指标从原来的16个减为7个,具体为:p H、有机质、有效磷、有效铁、有效锌、有效硫和水稳性大团聚体。(2)烟区土壤酸化较为严重,有35.1%的烟田土壤偏酸;土壤氮素较为适宜,而有效磷和速效钾偏高的烟田占比分别为62.9%和75.8%,其他元素缺乏和过量并存,水稳性大团聚体偏低的烟田占比47.2%。(3)对基于最小数据集构建模型进行的合理性验证发现,基于主成分分析法确定的最小数据集(MDS-PCA)模型的R2比基于聚类分析法确定的最小数据模型的R~2高,前者的MAE、RMSE相比后者更小,说明MDS-PCA能够替代全量数据集对烟田土壤质量进行评价;基于MDS-PCA得到的土壤质量指数平均值为0.61,表明烟区土壤质量总体处于中等偏低水平,45.04%的烟田土壤质量急需提升。(4)土壤质量评价指标隶属度值雷达图表明,pH、有效磷、有效铁、有效硫和水稳性大团聚体的隶属度比较小,为烟区土壤质量限制性因子。

基于ICA改进ICEEMD的UDS重采样数学模型

为了增强不平衡数据集处理效果,提出一种基于ICA改进ICEEMD的不平衡数据集重采样数学模型研究方法。分析不平衡数据集的分布特征,通过改进完备集成经验模态分解(ICEEMD)方法和独立分量分析(ICA)分解不平衡数据集,去除不平衡数据集中的噪声。通过DP聚类算法和σ准则构建重采样数学模型,利用该模型自动判别不平衡数据集的聚类中心和离群点,同时对多数和少数类样本分析处理,确保样本相对均衡,最终完成不平衡数据集的重采样处理。经实验测试结果表明,所提模型的整体性能明显优于其它重采样模型,验证了其应用价值。

用迭代自组织数据分析技术A(ISODATA)对零件进行模糊分类

本文将机械零件的 GT 分类编码视为模糊样品集,进行分类成组。给出了模糊数学模型,用 ISODATA 模糊聚类方法进行求解,程序运行的结果表明:比普通聚类法运行速度快;结果更切合客观实际。

基于特征聚类和等距映射的无监督特征选择算法

为了提高无标签场景下特征选择的准确率和稳定性,提出一种基于特征聚类和等距映射的无监督特征选择算法。特征聚类将相似性较高的特征聚成一类,然后结合等距映射和稀疏系数矩阵定义新的特征得分计量函数。该函数对各特征簇中的特征进行打分,选择出每个类簇中得分最高的代表特征,构成特征子集。在14个广泛应用的数据集上的实验结果表明:本文所提算法能够选择出具有强分类能力的特征,且算法具有很强的泛化性。

基于数据驱动期望场景集序列的微电网鲁棒经济调度算法

针对新能源和负荷功率的不确定性,提出基于数据驱动期望场景集序列的微电网鲁棒经济调度算法。通过聚类方法将大量历史场景数据进行聚类处理,形成聚类场景集序列,基于概率缩减为期望场景集序列。日前计划阶段,以任意场景可行作为约束条件,以期望场景所对应的微电网运行成本的概率加权指标作为目标函数,通过列约束生成算法对微电网经济调度问题进行求解。日内调度阶段,利用新能源和负荷的测量数据,基于日前计划调度结果对微电网进行再调度,通过对传统能源发电功率和电网交互功率调整进行惩罚,来追踪日前计划调度结果,优选出微电网设备最优出力,提高微电网经济性。仿真案例验证了该方法的有效性。

基于集对分析的半监督ISODATA聚类

提出一个基于集对分析的半监督ISODATA聚类算法,用于网络异常检测。在三方面进行了改进:首先,算法能够直接处理字符数字混合属性的数据,并使用集对分析来计算数据记录之间的距离;其次,算法同时处理有标号和无标号的数据,并利用少量的有标号数据来指导算法的分裂过程;最后,将算法的输入参数减少到只有两个。在KDD99入侵检测数据集上的实验结果显示,该算法获得了95.62%的检测率和1.29%的误报率。

基于可视化技术的海量数据安全特征提取算法

由于传统算法在海量数据安全特征提取中应用效果不佳,不仅提取误差比较大,而且提取时间比较长,无法达到预期的特征提取效果,提出基于可视化技术的海量数据安全特征提取算法。在网络日志记录集中拾取与数据提取源相关的海量数据,利用聚类分析法对海量数据进行聚类分析,以数据的可靠性对海量数据安全特征进行识别,利用可视化技术对安全特征进行统计提取,以此完成基于可视化技术的海量数据安全特征提取。实验证明,设计方法数据安全特征提取误差小于1%,提取时间在1s以内,可以有效保证海量数据安全特征提取精度和速度。

一种改进的自适应网格划分的分布式聚类算法

在众多聚类算法中,基于网格划分思想的聚类算法是较为常用的算法类型之一,但现有的算法对于处理海量高维数据而言,会存在以下两个问题:一是聚类结果的准确率较低;二是算法耗时较长.为了解决现有算法的不适应性,该文在网格聚类算法的基础上结合降维技术、自适应网格划分、相对熵和分布式计算,提出了一种改进的自适应网格划分的分布式聚类算法(AMCBS),可以较好解决以上问题.经实验证明,该算法对于D31标准数据集、UCI数据集、人脸图片数据集和GitHub文本数据集等的效果均优于常见的聚类算法,具有较好的准确率和较高的运行效率.

基于改进的YOLOv3-SPP算法目标检测研究

为了更好的对复杂战场环境下军事目标检测和侦查,提出一种基于YOLOv3-SPP的改进算法。通过收集不同目标尺寸、类别等条件下坦克、步战车、雷达等军事对象,构建军事目标小型数据集;对数据集进行数据增强处理,扩充样本数,提高训练模型鲁棒性;将DIoU和Focal Loss替换均方误差函数和交叉熵函数,提高目标检测算法精度;利用K-means++聚类算法计算得出适用的锚框,进一步提高模型检测精度。实验结果表明,改进的YOLOv3-SPP军事目标检测算法相对于原YOLOv3-SPP算法,模型收敛更快,平均精度提高了10%,精度和召回率分别提高了9%和8%,具备良好的检测能力,能为战场环境下军事目标的检测和侦查任务提供技术支持。

基于最小数据集的典型绿洲农田土壤质量评价

【目的】基于最小数据集对新疆莫索湾灌区农田土壤质量进行评价。【方法】利用GPS定位和随机均匀抽样的方式采集新疆莫索湾灌区内共50个土壤样品,测定土壤有机质、速效磷、速效钾、碱解氮、pH值、EC、K^(+)、Ca^(2+)、Na^(+)、Mg^(2+)、Cl^(-)、NO_(3)^(-)、SO_(4)^(2-)共13项指标,采用主成分分析和聚类分析分别构建最小数据集,基于土壤综合指数法对新疆莫索湾灌区农田土壤质量进行评价,并比较主成分分析和聚类分析得出的结果与灌区土壤实际条件的符合程度。【结果】莫索湾灌区农田土壤有机质量较少,碱解氮量较低,速效磷量和速效钾量较为丰富但分布不均;盐分空间分布差异大,土壤盐碱化程度高。大部分土壤质量处于中等偏下水平,且土壤质量差异较大。主成分分析法得出的评价结果更符合莫索湾灌区土壤质量的实际条件。【结论】新疆莫索湾灌区土壤质量水平总体较差,采用不同分析方法对其进行评价,主成分分析法最合理,聚类分析法次之。