Search

Clustering is a difficult and widely studied data mining task, with many varieties of clustering algorithms proposed in the literature. Nearly all algorithms use a similarity measure such as a distance metric (e.g., Euclidean distance) to decide which instances to assign to the same cluster. These similarity measures are generally predefined and cannot be easily tailored to the properties of a particular dataset, which leads to limitations in the quality and the interpretability of the clusters produced. In this article, we propose a new approach to automatically evolving similarity functions for a given clustering algorithm by using genetic programming. We introduce a new genetic programming-based method which automatically selects a small subset of features (feature selection) and then combines them using a variety of functions (feature construction) to produce dynamic and flexible similarity functions that are specifically designed for a given dataset. We demonstrate how the evolved similarity functions can be used to perform clustering using a graph-based representation. The results of a variety of experiments across a range of large, high-dimensional datasets show that the proposed approach can achieve higher and more consistent performance than the benchmark methods. We further extend the proposed approach to automatically produce multiple complementary similarity functions by using a multi-tree approach, which gives further performance improvements. We also analyse the interpretability and structure of the automatically evolved similarity functions to provide insight into how and why they are superior to standard distance metrics.

Background: Scoping reviews of research help determine the feasibility and the resource requirements of conducting a systematic review, and the potential to generate a description of the literature quickly is attractive., Aims: To test the utility and applicability of an automated clustering tool to describe and group research studies to improve the efficiency of scoping reviews., Methods: A retrospective study of two completed scoping reviews was conducted. This compared the groups and descriptive categories obtained by automatically clustering titles and abstracts with those that had originally been derived using traditional researcher-driven techniques., Results: The clustering tool rapidly categorised research into themes, which were useful in some instances, but not in others. This provided a dynamic means to view each dataset. Interpretation was challenging where there were potentially multiple meanings of terms. Where relevant clusters were unambiguous, there was a high precision of relevant studies, although recall varied widely., Conclusions: Policy-relevant scoping reviews are often undertaken rapidly, and this could potentially be enhanced by automation depending on the nature of the dataset and information sought. However, it is not a replacement for researcher-developed classification. The possibilities of further applications and potential for use in other types of review are discussed., (Copyright © 2013 John Wiley & Sons, Ltd.)

The density peaks clustering (DPC) algorithm plays an important role in data mining by quickly identifying cluster centers using decision graphs to identify arbitrary clusters. However, the decision graph introduces uncertainty in determining the cluster centers, which can result in an incorrect number of clusters. In addition, the cut-off distance parameter relies on prior knowledge, which poses a limitation. To address these issues, we propose an improved automatic density peaks clustering (ADPC) algorithm. First, a novel clustering validity index called density-distance clustering (DDC) is introduced. The DDC index draws inspiration from the density and distance characteristics of cluster centers, which is applicable to DPC and aligns with the general definition of clustering. Based on the DDC index, the ADPC algorithm automatically selects the suitable cut-off distance and acquires the optimal number of clusters without additional parameters. Numerical experimental results validate that the introduced ADPC algorithm successfully automatically determines the optimal number of clusters and cut-off distance, significantly outperforming DPC, AP and DBSCAN algorithms. [ABSTRACT FROM AUTHOR]

Time series is a set of sequential data point in time order. The sizes and dimensions of the time series datasets are increasing day by day. Clustering is an unsupervised data mining technique that groups objects based on their similarities. It is used to analyze various datasets, such as finance, climate, and bioinformatics datasets. k -means is one of the most used clustering algorithms. However, it is challenging to determine the value of k parameter, which is the number of clusters. One of the most used methods to determine the number of clusters (such as k) is cluster validity indexes. Several internal and external validity indexes are used to find suitable cluster numbers based on characteristics of datasets. In this study, we propose a hybrid validity index to determine the value of k parameter of k -means algorithm. The proposed hybrid validity index comprises four internal validity indexes, such as Dunn, Silhouette, C index, and Davies–Bouldin indexes. The proposed method was applied to nine real-life finance and benchmarks time series datasets. The financial dataset was obtained from Yahoo Finance, consisting of daily closing data of stocks. The other eight benchmark datasets were obtained from UCR time series classification archive. Experimental results showed that the proposed hybrid validity index is promising for finding the suitable number of clusters with respect to the other indexes for clustering time-series datasets. [ABSTRACT FROM AUTHOR]

Cluster analysis is an essential tool in data mining. Several clustering algorithms have been proposed and implemented, most of which are able to find good quality clustering results. However, the majority of the traditional clustering algorithms, such as the K-means, K-medoids, and Chameleon, still depend on being provided a priori with the number of clusters and may struggle to deal with problems where the number of clusters is unknown. This lack of vital information may impose some additional computational burdens or requirements on the relevant clustering algorithms. In real-world data clustering analysis problems, the number of clusters in data objects cannot easily be preidentified and so determining the optimal amount of clusters for a dataset of high density and dimensionality is quite a difficult task. Therefore, sophisticated automatic clustering techniques are indispensable because of their flexibility and effectiveness. This paper presents a systematic taxonomical overview and bibliometric analysis of the trends and progress in nature-inspired metaheuristic clustering approaches from the early attempts in the 1990s until today's novel solutions. Finally, key issues with the formulation of metaheuristic algorithms as a clustering problem and major application areas are also covered in this paper. [ABSTRACT FROM AUTHOR]

Visual methods have been extensively studied and performed in cluster data analysis. Given a pairwise dissimilarity matrix D of a set of n objects, visual methods such as Enhanced-Visual Assessment Tendency (E-VAT) algorithm generally represent D as an n x n image I(D̅) where the objects are reordered to expose the hidden cluster structure as dark blocks along the diagonal of the image. A major constraint of such methods is their lack of ability to highlight cluster structure when D contains composite shaped datasets. This paper addresses this limitation by proposing an enhanced visual analysis method for cluster tendency assessment, where D is mapped to D' by graph based analysis and then reordered to D̅' using E-VAT resulting graph based Enhanced Visual Assessment Tendency (GE-VAT). An Enhanced Dark Block Extraction (E-DBE) for automatic determination of the number of clusters in I(D̅') is then proposed as well as a visual data partitioning method for cluster formation from I(D̅') based on the disparity between diagonal and off-diagonal blocks using permuted indices of GE-VAT. Cluster validation measures are also performed to evaluate the cluster formation. Extensive experimental results on several complex synthetic, UCI and large real-world data sets are analyzed to validate our algorithm. [ABSTRACT FROM AUTHOR]

Web mining in searching based on keywords by automatic clustering is a document searching method by classifying documents based on its keyword. Following is the clustering by centroid linkage hierarchical method (CLHM) to the number of keywords from each document. In clustering, initialization is commonly required for the number of cluster to be formed first, however, in some clustering cases, the user cannot determine how many clusters can be built. Therefore, on this paper, the Valley tracing method is applied as a constraint which identifies variants movement from each cluster formation step and also analyzes its pattern to form automatic clustering. Document data used are from text mining process on documents. Based on 424 documents, this research shows that clustering method using CLHM algorithm can be generally used to classifying documents with exact number automatically. [ABSTRACT FROM AUTHOR]

Clustering is an essential tool in data mining research and applications. It is the subject of active research in many fields of study, such as computer science, data science, statistics, pattern recognition, artificial intelligence, and machine learning. Several clustering techniques have been proposed and implemented, and most of them successfully find excellent quality or optimal clustering results in the domains mentioned earlier. However, there has been a gradual shift in the choice of clustering methods among domain experts and practitioners alike, which is precipitated by the fact that most traditional clustering algorithms still depend on the number of clusters provided a priori. These conventional clustering algorithms cannot effectively handle real-world data clustering analysis problems where the number of clusters in data objects cannot be easily identified. Also, they cannot effectively manage problems where the optimal number of clusters for a high-dimensional dataset cannot be easily determined. Therefore, there is a need for improved, flexible, and efficient clustering techniques. Recently, a variety of efficient clustering algorithms have been proposed in the literature, and these algorithms produced good results when evaluated on real-world clustering problems. This study presents an up-to-date systematic and comprehensive review of traditional and state-of-the-art clustering techniques for different domains. This survey considers clustering from a more practical perspective. It shows the outstanding role of clustering in various disciplines, such as education, marketing, medicine, biology, and bioinformatics. It also discusses the application of clustering to different fields attracting intensive efforts among the scientific community, such as big data, artificial intelligence, and robotics. This survey paper will be beneficial for both practitioners and researchers. It will serve as a good reference point for researchers and practitioners to design improved and efficient state-of-the-art clustering algorithms. • Provide an up-to-date comprehensive review of the different clustering techniques. • Highlight novel and most recent practical applications areas of clustering. • Provide a convenient research path for new researchers. • Help experts develop new algorithms for emerging challenges in the research area. [ABSTRACT FROM AUTHOR]

Today's real-world data mostly involves incomplete, inconsistent, and/or irrelevant information that causes many drawbacks to transform it into an understandable format. In order to deal with such issues, data preprocessing is a proven discipline in data mining. One of the typical tasks in data preprocessing, feature selection aims to reduce the dimensionality in the data and thereby contributes to further processing. Feature selection is widely used to enhance the performance of a supervised learning algorithm (e.g., classification) but is rarely used in unsupervised tasks (e.g., clustering). This paper introduces a new multi-objective differential evolution approach in order to find relatively homogeneous clusters without the prior knowledge of cluster number using a smaller number of features from all available features in the data. To analyze the goodness of the introduced approach, several experiments are conducted on a various number of real-world and synthetic benchmarks using a variety of clustering approaches. From the analyzes through several different criteria, it is suggested that our method can significantly improve the clustering performance while reducing the dimensionality at the same time. [ABSTRACT FROM AUTHOR]