Hybrid Hierarchical Clustering Research Articles

Large-scale multimodal multiobjective evolutionary optimization based on hybrid hierarchical clustering

Large-scale multimodal multiobjective optimization problems (MMOPs) have different equivalent Pareto optimal solution sets (PSs) for the same Pareto front and contain a great number of decision variables. In particular, when most variables among the Pareto optimal solutions are zero, such problems are termed large-scale MMOPs with sparse Pareto optimal solutions. Due to the multimodal properties of these problems, the curse of dimensionality, and the unknown sparsity of the search space, it is extremely difficult for existing optimizers to solve them. In this study, we propose a multipopulation multimodal evolutionary algorithm based on hybrid hierarchical clustering to solve such problems. The proposed algorithm uses hybrid hierarchical clustering on subpopulations to distinguish the resources of different equivalent PSs and partition them into different subpopulations to achieve efficient cooperative coevolution among multiple subpopulations. Moreover, an adaptive variation method incorporating both local and global guiding information is designed, and an improved environmental selection method based on local guiding information is conducted to improve the convergence in a large search space and introduce diversity to the population. Experimental results verified that the proposed algorithm outperforms the state-of-the-art MOEAs in terms of performance and convergence speed, especially when the number of equivalent PSs is large.

Hybrid Hierarchical Clustering dalam Pengelompokan Daerah Rawan Bencana Tanah Longsor di Sulawesi Selatan

This study aims to describe and classify areas prone to landslides in South Sulawesi. The method used is Hybrid Hierarchical Clustering. The data used is landslide disaster data sourced from the National Disaster Management Agency (BNPB) for 2018-2020 in South Sulawesi. The variables used are the number of landslides, deaths, damaged houses, injured victims, and damaged public facilities. Grouping using the Hybrid Hierarchical Clustering method with mutual clusters using bottom-up and top-down methods. Grouping with bottom-up method produces 2 groups, top-down method produces 2 groups and 1 best mutual cluster. The ratio results in the bottom-up method is 0.84, the top-down method is 1.07 and the mutual cluster is 0.84. The grouping results obtained were 2 groups.

FLAG: fuzzy logic augmented game theoretic hybrid hierarchical clustering algorithm for wireless sensor networks

Stability of the wireless sensor network (WSN) is the most critical factor in real-time and data-sensitive applications like military and surveillance systems. Many energy optimization techniques and algorithms have been proposed to extend the stability of a wireless sensor network. Clustering is a well regarded method in the research communities among them. Hence, this paper presents hybrid hierarchical artificial intelligence based clustering techniques, named FLAG and I-FLAG. The first phase of these algorithms use game-theoretic technique to elect suitable cluster heads (CHs) and later phase of the algorithms use fuzzy inference system to select appropriate super cluster heads (SCHs) among CHs. The I-FLAG is an improved version of FLAG where additional parameters like energy and distance are considered to elect CHs. Simulations are performed to check superiority of the proposed algorithms over the existing protocols like LEACH, CHEF, and CROSS. Simulation results show that the average stability period of WSN is better in FLAG and I-FLAG compared to other protocols, and so is the throughput of WSN during the stability period.

An improved ant-based algorithm based on heaps merging and fuzzy c-means for clustering cancer gene expression data

The microarray technology enables the analysis of the gene expression data and the understanding of the important biological processes in an efficient way. We have developed an efficient clustering scheme for microarray gene expression data based on correlation-based feature selection, ant-based clustering, fuzzy c-means algorithm and a novel heaps merging heuristic. The algorithm utilizes the feature selection algorithm to overcome the high-dimensionality problem encountered in bioinformatics domain. Based on extensive empirical analysis on microarray data, clustering quality of the ant-based clustering algorithm is enhanced with the use of fuzzy c-means algorithm and heaps merging heuristic. The performance of the proposed clustering scheme is compared with k-means, PAM algorithm, CLARA, self-organizing map, hierarchical clustering, divisive analysis clustering, self-organizing tree algorithm, hybrid hierarchical clustering, consensus clustering, AntClass algorithm and fuzzy c-means clustering algorithms. The experimental results indicate that the proposed clustering scheme yields better performance in clustering cancer gene expression data.

Regency grouping in East Java based on Variable Type of Agriculture uses Hybrid Hierarchical Clustering Via Mutual Cluster Method

AbstractEast Java Province is one of the provinces that has the largest agricultural resources in Indonesia. The Government of East Java needs to produce superior commodities in each region. This study aims to group districts in East Java Province based on variable types of agriculture with the hybrid hierarchical clustering via mutual cluster method that combines the merging of bottom-up clustering advantages and top-down clustering advantages. Mutual cluster is a grouping with the largest distance between small groups of the shortest distance for each point outside the group. In this research, the calculation uses Euclidean distance. The data used in this study are from the East Java Central Statistics Agency (BPS) in 2017. The division calculation is obtained by finding the minimum (standard deviation of intra cluster) value and the maximum (standard deviation of inter clusters) value and using the analysis of variance calculation. The grouping results obtained were nine groups with value of 725.934, value of 1.475.978 and value of 7,908.Keywords: agriculture; Hybrid Hierarchical Clustering; mutual cluster; Euclidean distance; analysis of variance. AbstrakProvinsi Jawa Timur merupakan salah satu provinsi yang memiliki sumber daya pertanian terbesar di Indonesia. Pemerintah Jawa Timur perlu mengembangkan komoditi unggulan di tiap daerah di Jawa Timur. Penelitian ini bertujuan untuk mengelompokkan kabupaten di Provinsi Jawa Timur berdasarkan variabel jenis pertanian dengan metode hybrid hierarchical clustering via mutual cluster yaitu menggabungkan kelebihan bottom-up clustering dan kelebihan top-down clustering. Mutual cluster yakni pengelompokkan dengan jarak terbesar antara bagian dalam kelompok yang kecil dari jarak yang terpendek kepada tiap titik di luar kelompok. Dalam penelitian ini, perhitungan jarak menggunakan jarak Euclidean. Data yang digunakan dalam penelitian ini dari Badan Pusat Statistik Jawa Timur tahun 2017. Perhitungan pembagian didapat dengan mencari nilai (simpangan baku dalam klaster) yang minimal dan nilai (simpangan baku antar klaster) yang maksimal, serta digunakan perhitungan analyze of varians. Hasil pengelompokkan yang diperoleh didapatkan sebanyak sembilan kelompok dengan nilai sebesar 725.934, nilai sebesar 1.475.978 dan nilai sebesar 7,908.Kata Kunci: pertanian; Hybrid Hierarchical Clustering; mutual cluster; jarak Euclid; analisis variansi.

Identification of management zones in precision agriculture: An evaluation of alternative cluster analysis methods

The definition of management zones (MZs) in agricultural fields has been suggested as an economically viable approach to precision agriculture. The most used methods for this task are the cluster analysis algorithms Fuzzy C-means (FCM) and K-means. However, some studies have presented that these algorithms may not provide the best classes to define MZs. Considering that these studies presented comparisons of only a few clustering methods, the objective of our research was to evaluate 20 algorithms for defining MZs, including more than 10 methods that have not been investigated in the literature for this purpose. The following algorithms were evaluated: Average Linkage, Bagged Clustering, Centroid Linkage, Clara, Complete Linkage, Diana, Fanny, FCM, Fuzzy C-shells, Hard Competitive Learning, Hybrid Hierarchical Clustering, K-means, McQuitty's Method, Median Linkage, Neural Gas, Partitioning Around Medoids, Single Linkage, Spherical K-means, Unsupervised Fuzzy Competitive Learning and Ward's Method. The evaluation was conducted with data obtained between 2010 and 2015 from three commercial agricultural fields cultivated with soya bean and maize in Brazil. The results of the analysis of variance suggested a division of the three fields into two classes with significantly different yields and a division of one of the fields into three classes. These divisions were satisfactorily performed using 17 algorithms, but McQuitty's Method and Fanny were considered to be the best choices because they produced the largest reductions in the variance of the yield in the three fields. In addition, they generated classes with high internal homogeneity and delimited MZs without spatial fragmentation.

Enhanced Three Layer Hybrid Clustering Mechanism for Energy Efficient Routing in IoT.

Recently, different routing techniques were proposed for three layer clustering topology in Wireless Sensor Network (WSN) which outperform the basic two layer clustering hierarchy. The problem that remains in these approaches is the heavy control packet exchange between nodes after every round in order to choose efficient lower layer heads. Among these techniques is Hybrid Hierarchical Clustering Approach (HHCA), in which a distributed approach is proposed. According to HHCA, the upper layer heads are centrally selected by base station, while sensor nodes only have to select lower layer heads distributively. In this paper, enhanced three layer hybrid clustering mechanism is proposed that limits the exchange of control packets between nodes after every round for lower layer head selection. The energy of nodes are divided into levels upon which it is decided when nodes of a cluster need to enter into new cluster head selection phase. The proposed mechanism helps to limit control packet exchange between nodes to a large extent, at the same time keeping energy consumption between nodes balanced. Moreover, it is focused that higher layer heads are selected by base station in a manner that reduces backward transmission in the network as much as possible. Simulation results show that nodes in the proposed mechanism stay alive for a longer time as compared to other approaches, and it outperforms HHCA technique in network lifetime based on Half of the Nodes Alive (HNA) by 18 percent.

Data-Driven Phenotypic Categorization for Neurobiological Analyses: Beyond DSM-5 Labels

BackgroundData-driven approaches can capture behavioral and biological variation currently unaccounted for by contemporary diagnostic categories, thereby enhancing the ability of neurobiological studies to characterize brain-behavior relationships. MethodsA community-ascertained sample of individuals (N = 347, 18–59 years of age) completed a battery of behavioral measures, psychiatric assessment, and resting-state functional magnetic resonance imaging in a cross-sectional design. Bootstrap-based exploratory factor analysis was applied to 49 phenotypic subscales from 10 measures. Hybrid hierarchical clustering was applied to resultant factor scores to identify nested groups. Adjacent groups were compared via independent samples t tests and chi-square tests of factor scores, syndrome scores, and psychiatric prevalence. Multivariate distance matrix regression examined functional connectome differences between adjacent groups. ResultsReduction yielded six factors, which explained 77.8% and 65.4% of the variance in exploratory and constrained exploratory models, respectively. Hybrid hierarchical clustering of these six factors identified two, four, and eight nested groups (i.e., phenotypic communities). At the highest clustering level, the algorithm differentiated functionally adaptive and maladaptive groups. At the middle clustering level, groups were separated by problem type (maladaptive groups; internalizing vs. externalizing problems) and behavioral type (adaptive groups; sensation-seeking vs. extraverted/emotionally stable). Unique phenotypic profiles were also evident at the lowest clustering level. Group comparisons exhibited significant differences in intrinsic functional connectivity at the highest clustering level in somatomotor, thalamic, basal ganglia, and limbic networks. ConclusionsData-driven approaches for identifying homogenous subgroups, spanning typical function to dysfunction, not only yielded clinically meaningful groups, but also captured behavioral and neurobiological variation among healthy individuals.

Model-based clustering for RNA-seq data

RNA-seq technology has been widely adopted as an attractive alternative to microarray-based methods to study global gene expression. However, robust statistical tools to analyze these complex datasets are still lacking. By grouping genes with similar expression profiles across treatments, cluster analysis provides insight into gene functions and networks, and hence is an important technique for RNA-seq data analysis. In this manuscript, we derive clustering algorithms based on appropriate probability models for RNA-seq data. An expectation-maximization algorithm and another two stochastic versions of expectation-maximization algorithms are described. In addition, a strategy for initialization based on likelihood is proposed to improve the clustering algorithms. Moreover, we present a model-based hybrid-hierarchical clustering method to generate a tree structure that allows visualization of relationships among clusters as well as flexibility of choosing the number of clusters. Results from both simulation studies and analysis of a maize RNA-seq dataset show that our proposed methods provide better clustering results than alternative methods such as the K-means algorithm and hierarchical clustering methods that are not based on probability models. An R package, MBCluster.Seq, has been developed to implement our proposed algorithms. This R package provides fast computation and is publicly available at http://www.r-project.org

A novel hybrid methodology combining back propagation neural network with rough set and its application

In the increasingly complex world, decision makers need assistance in making informed transportation planning decisions. This article describes the application of rough set (RS) and back propagation neural network (BPNN) in the development of a novel hybrid intelligent model for forecasting the railway passenger traffic demand. The model intends to exploit the respective advantages of both RS and BPNN methods, but to avoid their respective weak points. The basic idea is to think of RS as the pre-treatment unit for BPNN that can mine knowledge from historical data. To do so, RS was used in data pre-treatment and constructing the decision table, and obtaining the minimum rule set from the decision table reduced by discretizing continuous attributes through a hybrid hierarchical k-means clustering. Input such rule set to the BPNN, trained on a sample dataset to determine parameters by using the Levenberg–Marquardt algorithm and the golden section algorithm. A hybrid intelligent forecasting model based on RS and BPNN is thus constructed and applied to forecast railway passenger traffic demand with pre-treated forecasting data. In the experiment, the railway passenger traffic data in China from 1991 to 2008 are selected as learning samples and testing samples, and the effectiveness of this method is verified in comparison to the linear recursive method.

Efficient bottom-up hybrid hierarchical clustering techniques for protein sequence classification

Hybrid hierarchical clustering techniques which combine the characteristics of different partitional clustering techniques or partitional and hierarchical clustering techniques are interesting. In this paper, efficient bottom-up hybrid hierarchical clustering (BHHC) techniques have been proposed for the purpose of prototype selection for protein sequence classification. In the first stage, an incremental partitional clustering technique such as leader algorithm (ordered leader no update (OLNU) method) which requires only one database (db) scan is used to find a set of subcluster representatives. In the second stage, either a hierarchical agglomerative clustering (HAC) scheme or a partitional clustering algorithm—‘K-medians’ is used on these subcluster representatives to obtain a required number of clusters. Thus, this hybrid scheme is scalable and hence would be suitable for clustering large data sets and we also get a hierarchical structure consisting of clusters and subclusters and the representatives of which are used for pattern classification. Even if more number of prototypes are generated, classification time does not increase much as only a part of the hierarchical structure is searched. The experimental results (classification accuracy (CA) using the prototypes obtained and the computation time) of the proposed algorithms are compared with that of the hierarchical agglomerative schemes, K-medians and nearest neighbour classifier (NNC) methods. The proposed methods are found to be computationally efficient with reasonably good CA.

A new algorithm for hybrid hierarchical clustering with visualization and the bootstrap

We propose a hybrid clustering method, hierarchical ordered partitioning and collapsing hybrid (HOPACH), which is a hierarchical tree of clusters. The methodology combines the strengths of both partitioning and agglomerative clustering methods. At each node, a cluster is partitioned into two or more smaller clusters with an enforced ordering of the clusters. Collapsing steps uniting the two closest clusters into one cluster can be used to correct for errors made in the partitioning steps. We implement a version of HOPACH which optimizes a measure of clustering strength, such as average silhouette, at each partitioning and collapsing step. An important benefit of a hierarchical tree is that one can look at clusters at increasing levels of detail. We propose to visualize the clusters at any level of the tree by plotting the distance matrix corresponding with an ordering of the clusters and an ordering of elements within the clusters. A final ordered list of elements is obtained by running down the tree completely. The bootstrap can be used to establish the reproducibility of the clusters and the overall variability of the followed procedure. The power of the methodology compared to current algorithms is illustrated with simulated and publicly available cancer gene expression data sets.

A fuzzy hybrid hierarchical clustering method with a new criterion able to find the optimal partition

Classical fuzzy clustering methods are not able to compute a partition in a set of points when classes have nonconvex shape. Furthermore we know that in this case, the usual criteria of class validity such as fuzzy hypervolume or compactness–separability, do not allow to find the optimal partition. The purpose of our paper is to provide a clustering method able to divide a set of points into nonconvex classes without knowing a priori their number. We will show that it is possible to reconcile a fuzzy clustering method with a hierarchical ascending one while maintaining a fuzzy partition by a method called unsupervised fuzzy graph clustering. To that effect, we shall use the Fuzzy C-Means algorithm to divide the set of points into an overspecified number of subclasses. A fuzzy relation is then established between them in order to extract the structure of the set of points. It can be represented by a graduated hierarchy. Finally, we present a new criterion to find the cut of the hierarchy giving the optimal regrouping. This one allows to find the real classes existing into the set of points. The given results are compared with those obtained by other classical cluster validity criteria and we propose to study the influence of the number of initial subclasses on the final computed partition.