In this paper, we propose a novel objective function called the adaptive Fuzzy Weighted Sum Validity Function (FWSVF), which is a merged weight of the several fuzzy cluster validity functions, including XB, PE, PC...
详细信息
In this paper, we propose a novel objective function called the adaptive Fuzzy Weighted Sum Validity Function (FWSVF), which is a merged weight of the several fuzzy cluster validity functions, including XB, PE, PC and PBMF. The improved validity function is more efficient than others. Furthermore, we present a Mixed Strategy evolutionaryclusteringalgorithm based adaptive validity function (AMSECA), which is merged from evolutionaryalgorithm along with Mixed Strategy and Fuzzy C-means algorithm. Moreover, in the experiments, we show the effectiveness of AMSECA, AMSECA could find the proper number of clusters automatically as well as appropriate partitions of the data set and avoid local optima.
clustering is a commonly used method for exploring and analysing data where the primary objective is to categorise observations into similar clusters. In recent decades, several algorithms and methods have been develo...
详细信息
clustering is a commonly used method for exploring and analysing data where the primary objective is to categorise observations into similar clusters. In recent decades, several algorithms and methods have been developed for analysing clustered data. We notice that most of these techniques deterministically define a cluster based on the value of the attributes, distance, and density of homogenous and single-featured datasets. However, these definitions are not successful in adding clear semantic meaning to the clusters produced. evolutionary operators and statistical and multidisciplinary techniques may help in generating meaningful clusters. Based on this premise, we propose a new evolutionary clustering algorithm (ECA*) based on social class ranking and meta-heuristic algorithms for stochastically analysing heterogeneous and multifeatured datasets. The ECA* is integrated with recombinational evolutionary operators, Levy flight optimisation, and some statistical techniques, such as quartiles and percentiles, as well as the Euclidean distance of the K-means algorithm. Experiments are conducted to evaluate the ECA* against five conventional approaches: K-means (KM), K-means++ (KM++), expectation maximisation (EM), learning vector quantisation (LVQ), and the genetic algorithm for clustering++ (GENCLUST++). That the end, 32 heterogeneous and multifeatured datasets are used to examine their performance using internal and external and basic statistical performance clustering measures and to measure how their performance is sensitive to five features of these datasets (cluster overlap, the number of clusters, cluster dimensionality, the cluster structure, and the cluster shape) in the form of an operational framework. The results indicate that the ECA* surpasses its counterpart techniques in terms of the ability to find the right clusters. Significantly, compared to its counterpart techniques, the ECA* is less sensitive to the five properties of the datasets mentioned abo
In the field of data mining and machine learning,clustering is a typical issue which has been widely studied by many researchers,and lots of effective algorithms have been proposed,including K-means,fuzzy c-means(FCM)...
详细信息
In the field of data mining and machine learning,clustering is a typical issue which has been widely studied by many researchers,and lots of effective algorithms have been proposed,including K-means,fuzzy c-means(FCM)and ***,the traditional clustering methods are easily trapped into local ***,many evolutionary-based clustering methods have been *** the effectiveness of brain storm optimization(BSO)in increasing the diversity while the diversity optimization is performed,in this paper,we propose a new clustering model based on BSO to use the global ability of *** our experiment,we apply the novel binary model to solve the *** the period of processing data,BSO was mainly utilized for ***,in the process of K-means,we set the more appropriate parameters selected to match it *** datasets were used in our *** our model,BSO was first introduced in solving the clustering *** the algorithm running on each dataset repeatedly,our experimental results have obtained good convergence and *** addition,by comparing the results with other clustering models,the BSO clustering model also guarantees high ***,from many aspects,the simulation results show that the model of this paper has good performance.
暂无评论