Multi-objective Clustering Research Articles

Analysis of the multi-objective cluster head selection problem in WSNs

The target of wireless sensor networks is to gather data regarding certain phenomena. This is why they are meant to last as long as possible. An efficient strategy to extend the wireless sensor network lifetime is to organize sensors hierarchically into clusters and, for each cluster, select one of the sensors as the cluster head. The task of the cluster head is to collect data from the cluster members and retransmit it to the base station across the network. By means of cluster organization, the process of acquiring data is enhanced and, consequently, the lifetime of the network is increased. Nevertheless, in addition to data collection and transmission, every cluster head performs additional tasks. Thus, they spend their energy quicker than the cluster members. This is the reason why cluster head selection is a multi-objective optimization problem. In this paper, we consider the three objectives, distance, delay, and residual energy, and apply three multi-objective evolutionary algorithms, specifically NSGA-II, SMS-EMOA, and MOEA/D, for studying the problem by means of solving several instances. We analyze the conflict between the objectives, present a proper multi-objective performance comparison of the algorithms, and investigate the efficiency of the found solutions regarding network energy consumption.

Evolutionary Multiobjective Clustering Algorithms With Ensemble for Patient Stratification.

Patient stratification has been studied widely to tackle subtype diagnosis problems for effective treatment. Due to the dimensionality curse and poor interpretability of data, there is always a long-lasting challenge in constructing a stratification model with high diagnostic ability and good generalization. To address these problems, this article proposes two novel evolutionary multiobjective clustering algorithms with ensemble (NSGA-II-ECFE and MOEA/D-ECFE) with four cluster validity indices used as the objective functions. First, an effective ensemble construction method is developed to enrich the ensemble diversity. After that, an ensemble clustering fitness evaluation (ECFE) method is proposed to evaluate the ensembles by measuring the consensus clustering under those four objective functions. To generate the consensus clustering, ECFE exploits the hybrid co-association matrix from the ensembles and then dynamically selects the suitable clustering algorithm on that matrix. Multiple experiments have been conducted to demonstrate the effectiveness of the proposed algorithm in comparison with seven clustering algorithms, twelve ensemble clustering approaches, and two multiobjective clustering algorithms on 55 synthetic datasets and 35 real patient stratification datasets. The experimental results demonstrate the competitive edges of the proposed algorithms over those compared methods. Furthermore, the proposed algorithm is applied to extend its advantages by identifying cancer subtypes from five cancer-related single-cell RNA-seq datasets.

Transfer learning from synthetic labels for histopathological images classification

This study introduces a new strategy that combines unsupervised learning (clustering) and transfer learning. Clustering methods are employed to generate synthetic labels for the source dataset (ICAR-2018). The generated dataset is then used for transfer learning to other histopathological datasets (KimiaPath960, CRC, Biomaging− 2015, Breakhis, and Lymphoma). The comparative study based on two clustering algorithms (K-means and multi-objective clustering stream) demonstrates the efficiency of MOC-Stream. The generated synthetic histopathological dataset by this clustering algorithm outperformed the original labeled dataset and the imageNet models in transfer learning.

A Novel Approach For Diagnosis Of Dermatologic Diseases Based On Multi-Objective Clustering Using Particle Swarm Optimization

The stratification of skin diseases plays a major role in enabling effective and customized medicine. An important task in the stratification of skin diseases is to discover subtypes of diseases for effective treatment. To achieve this goal, research into cluster algorithms for the stratification of skin diseases has attracted the attention of both scholars and the medical community in recent decades. However, cluster algorithms suffer from realistic limitations such as experimental sounds, high dimension and poor interpretation. In particular, cluster algorithms usually determine the quality of clusters with only one internal evaluation operation. Unfortunately, it is obvious that one internal evaluation operation is difficult to create and strong for all datasets. Therefore, this article proposes a novel of many descriptive frameworks called a multi objective cluster algorithm with a quick search and finding the density of peaks to deal with these limitations altogether. In the proposed framework, the variable component of the candidate is developed under many objectives to select properties and estimate the density of the cluster automatically. To guide the development of multi-objective, two cluster value indices are used, including the Calinski-Harabasz index and the Davies-Bouldin index. The clustering is performed with the help of a k-means cluster by finding the best clusters using particle optimization. PSO will solve the multi-objective to determine the best cluster. Here, the proposed method will test on the dermatology dataset from UCI repository using MATLAB R2020a, under windows10 environment. Then, the proposed method performance will be evaluating using the cluster evaluation indices.

Multiobjective Sine Cosine Algorithm for Remote Sensing Image Spatial-Spectral Clustering.

Remote sensing image data clustering is a tough task, which involves classifying the image without any prior information. Remote sensing image clustering, in essence, belongs to a complex optimization problem, due to the high dimensionality and complexity of remote sensing imagery. Therefore, it can be easily affected by the initial values and trapped in locally optimal solutions. Meanwhile, remote sensing images contain complex and diverse spatial-spectral information, which makes them difficult to model with only a single objective function. Although evolutionary multiobjective optimization methods have been presented for the clustering task, the tradeoff between the global and local search abilities is not well adjusted in the evolutionary process. In this article, in order to address these problems, a multiobjective sine cosine algorithm for remote sensing image data spatial-spectral clustering (MOSCA_SSC) is proposed. In the proposed method, the clustering task is converted into a multiobjective optimization problem, and the Xie-Beni (XB) index and Jeffries-Matusita (Jm) distance combined with the spatial information term (SI_Jm measure) are utilized as the objective functions. In addition, for the first time, the sine cosine algorithm (SCA), which can effectively adjust the local and global search capabilities, is introduced into the framework of multiobjective clustering for continuous optimization. Furthermore, the destination solution in the SCA is automatically selected and updated from the current Pareto front through employing the knee-point-based selection approach. The benefits of the proposed method were demonstrated by clustering experiments with ten UCI datasets and four real remote sensing image datasets.

Analysis method for factors influencing gear hobbing quality based on density peak clustering and improved multi-objective differential evolution algorithm

ABSTRACT For addressing the problem that the quality indicators of gear hobbing are complicated and the influencing factors are unknown, a characteristic processing method combining improved multi-objective differential evolution (IMODE) and clustering based on peak density (DPCA) is proposed. This method can extract the characteristic parameters that strongly influence gear hobbing quality for multi-process parameters and multi-quality indicators, and quantify their importance to the comprehensive quality indicators. First, based on correlation analysis of the quality inspection parameters by DPCA, a set of relatively independent gear hobbing quality inspection indicators is obtained, and the dimensions of the quality inspection parameters are reduced for more effectively reflecting the hobbing processing quality. Next, multi-threshold Birch (IBirch) clusters are obtained for different gear hobbing quality inspection data under different process parameters to obtain cluster labels. Finally, Rough Sets theory and IMODE are used to reduce the gear hobbing process parameters and design parameters. Feature parameters that significantly affect the hobbing process quality are extracted from the process parameters and their importance is quantified. The validity and practicability of the method are verified by processing experiments, and the advantages of the proposed method are proved.

An initialization friendly Gaussian mixture model based multi-objective clustering method for SAR images change detection

Speckle noise is a main obstacle for change detection tasks of synthetic aperture radar (SAR) images. However, change detection methods often focus on removing noise and ignore the importance of preserving details of SAR images, which results in a loss of classification accuracy. In order to alleviate the contradiction between removing noise and preserving details, a multi-objective change detection method based on a modified Gaussian mixture model (GMM) is proposed in our paper. In the framework of our multi-objective model, one objective is composed of an special GMM of being applied to distinguish changed and unchanged regions and preserve details. The another is a carefully crafted noise reduction operator for removing speckle noise, which is constructed as a penalty to refine the result of classification. The aforementioned conflicting objectives are optimized simultaneously, which is conducted by a common multi-objective evolutionary algorithm based on decomposition (MOEA/D). Then, a series of solutions are obtained, all of which represent a balance of detail preservation and noise reduction. Compared with three classical change detection methods, the proposed method is applied to four real datasets in experimental studies. Experimental results and theoretical analysis reveal its effectiveness.

Multi-objective cluster head selection using fitness averaged rider optimization algorithm for IoT networks in smart cities

Typically, there are a lot of challenges to be faced with providing better performance and energy optimization in the Internet of Things (IoT) in a smart city. In IoT and wireless sensor networks (WSNs), the nodes are generally grouped as clusters, which lead to forming Cluster Head (CH) that collects data from all other nodes and explicitly communicates with Base Station. In this paper, numerous objectives like delay minimization, energy sustainability could be accomplished through implementing a clustering algorithm on the intra-distance inter-distance between the CH and nodes. The optimization variables such as distance, delay, and energy used in IoT devices are taken into account to achieve the desired CH selection. In order to develop an enhanced IoT-Wireless Sensor Network (WSN) model, this paper introduces an advanced approach for CH selection using a modified Rider Optimization Algorithm (ROA). In the proposed algorithm, the solutions are sorted into two sets based on the best fitness value. The first set is updated using the averaged value of bypass and follower riders while the second set is updated through the averaged value of attacker and overtaker riders, which is called as Fitness Averaged-ROA (FA-ROA). The performance of the proposed FA-ROA is verified through a comparative analysis using various state-of-the-arts optimization models by concerning the number of alive nodes and normalized energy.

BiDETS: Binary Differential Evolutionary based Text Summarization

In extraction-based automatic text summarization (ATS) applications, feature scoring is the cornerstone of the summarization process since it is used for selecting the candidate summary sentences. Handling all features equally leads to generating disqualified summaries. Feature Weighting (FW) is an important approach used to weight the scores of the features based on their presence importance in the current context. Therefore, some of the ATS researchers have proposed evolutionary-based machine learning methods, such as Particle Swarm Optimization (PSO) and Genetic Algorithm (GA), to extract superior weights to their assigned features. Then the extracted weights are used to tune the scored-features in order to generate a high qualified summary. In this paper, the Differential Evolution (DE) algorithm was proposed to act as a feature weighting machine learning method for extraction-based ATS problems. In addition to enabling the DE to represent and control the assigned features in binary dimension space, it was modulated into a binary coded format. Simple mathematical calculation features have been selected from various literature and employed in this study. The sentences in the documents are first clustered according to a multi-objective clustering concept. DE approach simultaneously optimizes two objective functions, which are compactness measuring and separating the sentence clusters based on these objectives. In order to automatically detect a number of sentence clusters contained in a document, representative sentences from various clusters are chosen with certain sentence scoring features to produce the summary. The method was tested and trained using DUC2002 dataset to learn the weight of each feature. To create comparative and competitive findings, the proposed DE method was compared with evolutionary methods: PSO and GA. The DE was also compared against the best and worst systems benchmark in DUC 2002. The performance of the BiDETS model is scored with 49% similar to human performance (52%) in ROUGE-1; 26% which is over the human performance (23%) using ROUGE-2; and lastly 45% similar to human performance (48%) using ROUGE-L. These results showed that the proposed method outperformed all other methods in terms of F-measure using the ROUGE evaluation tool.

Automated coronary artery tree segmentation in coronary CTA using a multiobjective clustering and toroidal model-guided tracking method

Background and objectiveAccurate coronary artery tree segmentation can now be developed to assist radiologists in detecting coronary artery disease. In clinical medicine, the noise, low contrast, and uneven intensity of medical images along with complex shapes and vessel bifurcation structures make coronary artery segmentation challenging. In this work, we propose a multiobjective clustering and toroidal model-guided tracking method that can accurately extract coronary arteries from computed tomography angiography (CTA) imagery. MethodsUtilizing integrated noise reduction, candidate region detection, geometric feature extraction, and coronary artery tracking techniques, a new segmentation framework for 3D coronary artery trees is presented. The candidate regions are extracted using a multiobjective clustering method, and the coronary arteries are tracked by a toroidal model-guided tracking method. ResultsThe qualitative and quantitative results demonstrate the effectiveness of the presented framework, which achieves better performance than the compared segmentation methods in three widely used evaluation indices: the Dice similarity coefficient (DSC), Jaccard index and Recall across the CTA data. The proposed method can accurately identify the coronary artery tree with a mean DSC of 84%, a Jaccard index of 74%, and a Recall of 93%. ConclusionsThe proposed segmentation framework effectively segments the coronary tree from the CTA volume, which improves the accuracy of 3D vascular tree segmentation.

Multi-view feature selection for identifying gene markers: a diversified biological data driven approach

BackgroundIn recent years, to investigate challenging bioinformatics problems, the utilization of multiple genomic and proteomic sources has become immensely popular among researchers. One such issue is feature or gene selection and identifying relevant and non-redundant marker genes from high dimensional gene expression data sets. In that context, designing an efficient feature selection algorithm exploiting knowledge from multiple potential biological resources may be an effective way to understand the spectrum of cancer or other diseases with applications in specific epidemiology for a particular population.ResultsIn the current article, we design the feature selection and marker gene detection as a multi-view multi-objective clustering problem. Regarding that, we propose an Unsupervised Multi-View Multi-Objective clustering-based gene selection approach called UMVMO-select. Three important resources of biological data (gene ontology, protein interaction data, protein sequence) along with gene expression values are collectively utilized to design two different views. UMVMO-select aims to reduce gene space without/minimally compromising the sample classification efficiency and determines relevant and non-redundant gene markers from three cancer gene expression benchmark data sets.ConclusionA thorough comparative analysis has been performed with five clustering and nine existing feature selection methods with respect to several internal and external validity metrics. Obtained results reveal the supremacy of the proposed method. Reported results are also validated through a proper biological significance test and heatmap plotting.

An automatic clustering method using multi-objective genetic algorithm with gene rearrangement and cluster merging

As an unsupervised approach of machine learning, clustering is an important method to understand and learn structural information from data. However, current adaptive clustering approach based on multi-objective genetic algorithm have two apparent limitations. The first is that prior knowledge, i.e., sample information is needed to get the correct cluster number. The second is that no effective method can be found to select the best clustering solution from the Pareto Optimal Front (POF) generated by a multi-objective optimization. These problems become severer in applications applied on non-category datasets. Therefore, the primary goal of this research is to establish a genetic optimization based multi-objective clustering framework, in which multiple clustering validity indexes (CVIs) can be tested simultaneously to automatically obtain the optimal cluster number without knowing any sample label information in advance. In this effort, we will not only be able to consider clustering measurements such as cluster cohesion and separation, but also take other aspects, such as compactness, connectivity, variation among data elements, into consideration as well. Then, we aim to design a procedure to recommend three best solutions from the POF by using appropriate combination of CVIs without increasing computational cost. This procedure is expected to control the cluster number in a reasonable range and consequently decrease the difficulty in best solution recommendation. Finally, since we have the knowledge that using gene rearrangement in the genetic optimization does not affect partition, we take this advantage to merge clusters effectively and significantly speed the convergence of the algorithm. Our approach can outperform the state-of-the-art counterparts across diverse benchmark datasets in terms of partitioning accuracy and performance, as demonstrated in three experiments conducted on both artificial and typical real-world datasets.

Distributed clustering in peer to peer networks using multi-objective whale optimization

Multi-objective clustering algorithms have superiority over its single objective counterparts as they include additional knowledge on properties of data in the form of objectives to discover the underlying clusters present in various datasets. This paper proposes a distributed clustering algorithm using multi-objective whale optimization (DMOWOA) for peer to peer network. The algorithm minimizes two objective functions to perform clustering, namely : Total Euclidean Deviation and Total Symmetrical Deviation. Both objective values are shared using diffusion method of cooperation to obtain correct partitioning at each peer. A single solution from the non-dominated solutions is selected as final solution based on its minimum distance to origin in the normalized objective space. The proposed algorithm’s performance is evaluated on four synthetic and five real-life wireless sensor network datasets (Canada weather station dataset, Delhi air pollution content dataset, Intel laboratory dataset, Washington cook agronomy farm dataset and Thames river water quality dataset). The comparison is carried out with multi-objective distributed particle swarm optimization (DMOPSO), distributed K-Means (DK-Means) and other seven recently developed nature inspired multi-objective clustering techniques. The proposed algorithm in most of the cases outperforms the existing techniques in terms of statistical measures Minkowski Score, Dunn index and Silhouette index. The average rank of the proposed algorithm is also better in Kruskal–Wallis statistical test.

Multi-view clustering for multi-omics data using unified embedding

In real world applications, data sets are often comprised of multiple views, which provide consensus and complementary information to each other. Embedding learning is an effective strategy for nearest neighbour search and dimensionality reduction in large data sets. This paper attempts to learn a unified probability distribution of the points across different views and generates a unified embedding in a low-dimensional space to optimally preserve neighbourhood identity. Probability distributions generated for each point for each view are combined by conflation method to create a single unified distribution. The goal is to approximate this unified distribution as much as possible when a similar operation is performed on the embedded space. As a cost function, the sum of Kullback-Leibler divergence over the samples is used, which leads to a simple gradient adjusting the position of the samples in the embedded space. The proposed methodology can generate embedding from both complete and incomplete multi-view data sets. Finally, a multi-objective clustering technique (AMOSA) is applied to group the samples in the embedded space. The proposed methodology, Multi-view Neighbourhood Embedding (MvNE), shows an improvement of approximately 2−3% over state-of-the-art models when evaluated on 10 omics data sets.

MCH-EOR: Multi-objective Cluster Head Based Energy-aware Optimized Routing algorithm in Wireless Sensor Networks

Hierarchical Wireless Sensor Networks (WSNs) have got vital application domains in modern era especially in monitoring and tracking of events, and without human intervention. In WSN, sensor nodes are characterized to have short life span due to continuous sensing and consequently the battery drains quickly. Under heavy traffic condition, sensors in close proximity to sink die quickly and initiate energy-hole problem. Thus, optimal usage of available energy is a key challenge in WSN assisted applications. A precise clustering and optimal path selection from sensor nodes to sink has become extremely important to preserve energy. Keeping this in view, the paper presents a Multi-Objective Based Clustering and Sailfish Optimizer (SFO) guided routing method to sustain energy efficiency in WSNs. In it the Cluster Head (CH) is selected, based on effective fitness function which is formulated from multiple objectives. It helps to minimize energy consumption and reduces number of dead sensor nodes. After CH selection, SFO is used to select an optimal path to sink node for data transmission. The proposed approach is analytically analyzed and results are compared with the similar existing approaches namely, Grey wolf optimization (GWO), Genetic algorithm (GA), Ant Lion optimization (ALO), and Particle Swarm Optimization (PSO) in terms of energy consumption, throughput, packet delivery ratio, and network lifetime. The simulation results show that proposed method has performed 21.9% and 24.4% better in terms of energy consumption and number of alive sensor nodes respectively when compared to GWO. Further, it shows significantly better results than other optimization-based approaches.

Data Forecasting and Storage Sizing for PV Battery System Using Fuzzy Markov Chain Model

Although photovoltaic (PV) power is a green energy source, the high output variability of PV power generation leads to lags in network availability. To increase PV power plant reliability, an energy storage system can be incorporated. However, improper selection of storage size increases system cost or decreases network availability due to over- or under-sizing of the storage capacity, respectively. For this reason, we develop a generalized Markov chain-based battery charging–discharging procedure for determining proper storage size. In this work, multi-objective clustering and fuzzy decision-making (FDM) techniques for selecting the most optimal storage size with optimal availability are also proposed to avoid issues associated with conventional selection procedures. The reliability of our approach is analyzed based on forecasted data. As better prediction yields more dispatchable storage sizing, thereby improving system reliability, a first-order fuzzy time-series, Markov chain-based prediction method is used owing to its high prediction efficiency. To explore PV power generation performance in both cool and hot, sunny conditions, the temperature effect is considered in the storage sizing–availability analysis.

Multi-objective clustering analysis via combinatorial pigeon inspired optimization

Multi-objective data clustering is an important issue in data mining, and the realization of data clustering using the multi-objective optimization technique is a significant topic. A combinatorial multi-objective pigeon inspired optimization (CMOPIO) with ring topology is proposed to solve the clustering problem in this paper. In the CMOPIO, a delta-locus based coding approach is employed to encode the pigeons. Thus, the length of pigeon representation and the dimension of the search space are significantly reduced. Thereby, the computational load can be effectively depressed. In this way, the pigeon inspired optimization (PIO) algorithm can be discretized with an auxiliary vector to address data clustering. Moreover, an index-based ring topology with the ability of contributing to maintain flock diversity is adopted to improve the CMOPIO performance. Comparative simulation results demonstrate the feasibility and effectiveness of our proposed CMOPIO for solving data clustering problems.

Multiobjective clustering algorithm for complex data in learning management systems

Learning Management Systems (LMS) is now an emergent technology where massive data are collected and requires handling. This data comes from different sources with multiple features which represents another complex paradigm. However, as part of business intelligence and decision support, this data needs to be classified and analyzed for the management, teachers, as well as students to make the appropriate decisions. Thus, one of the effective data analysis methods is clustering. However, LMS data encompasses multi-features, which are not sufficient to make appropriate decisions. Therefore, single feature clustering algorithms would not help LMS decision-makers. Consequently, multifeatured/multiobjective clustering algorithms could be one of the proposed solutions. Thus, looking at different multiobjective clustering algorithms as compared to the LMS nature of data, those algorithms do not satisfy the clustering purpose. In addition, the LMS data could be huge, complex, and sequential algorithms would not help as well. Thus, this paper is a step forward towards clustering LMS data for better decision making. The paper proposes a new clustering framework based upon distributed systems and a new multiobjective algorithm for the purpose of LMS clustering. The algorithm has been examined experimentally in order to answer some of the questions that help taking decision based upon LMS collected data.

Multi-objective clustering algorithm using particle swarm optimization with crowding distance (MCPSO-CD)

Clustering, an unsupervised method of grouping sets of data, is used as a solution technique in various fields to divide and restructure data to become more significant and transform them into more useful information. Generally, clustering is difficult and complex phenomenon, where the appropriate numbers of clusters are always unknown, comes with a large number of potential solutions, and as well the datasets are unsupervised. These problems can be addressed by the Multi-Objective Particle Swarm Optimization (MOPSO) approach, which is commonly used in addressing optimization problems. However, MOPSO algorithm produces a group of non-dominated solutions which make the selection of an “appropriate” Pareto optimal or non-dominated solution more difficult. According to the literature, crowding distance is one of the most efficient algorithms that was developed based on density measures to treat the problem of selection mechanism for archive updates. In an attempt to address this problem, the clustering-based method that utilizes crowding distance (CD) technique to balance the optimality of the objectives in Pareto optimal solution search is proposed. The approach is based on the dominance concept and crowding distances mechanism to guarantee survival of the best solution. Furthermore, we used the Pareto dominance concept after calculating the value of crowding degree for each solution. The proposed method was evaluated against five clustering approaches that have succeeded in optimization that comprises of K-means Clustering, MCPSO, IMCPSO, Spectral clustering, Birch, and average-link algorithms. The results of the evaluation show that the proposed approach exemplified the state-of-the-art method with significant differences in most of the datasets tested.

A Unified Multi-view Clustering Algorithm Using Multi-objective Optimization Coupled with Generative Model

There is a large body of works on multi-view clustering that exploit multiple representations (or views) of the same input data for better convergence. These multiple views can come from multiple modalities (image, audio, text) or different feature subsets. Obtaining one consensus partitioning after considering different views is usually a non-trivial task. Recently, multi-objective based multi-view clustering methods have suppressed the performance of single objective based multi-view clustering techniques. One key problem is that it is difficult to select a single solution from a set of alternative partitionings generated by multi-objective techniques on the final Pareto optimal front. In this article, we propose a novel multi-objective based multi-view clustering framework that overcomes the problem of selecting a single solution in multi-objective based techniques. In particular, our proposed framework has three major components as follows: (i) multi-view based multi-objective algorithm, Multiview-AMOSA, for initial clustering of data points; (ii) a generative model for generating a combined solution having probabilistic labels; and (iii) K -means algorithm for obtaining the final labels. As the first component, we have adopted a recently developed multi-view based multi-objective clustering algorithm to generate different possible consensus partitionings of a given dataset taking into account different views. A generative model is coupled with the first component to generate a single consensus partitioning after considering multiple solutions. It exploits the latent subsets of the non-dominated solutions obtained from the multi-objective clustering algorithm and combines them to produce a single probabilistic labeled solution. Finally, a simple clustering algorithm, namely K -means, is applied on the generated probabilistic labels to obtain the final cluster labels. Experimental validation of our proposed framework is carried out over several benchmark datasets belonging to three different domains; UCI datasets, multi-view datasets, search result clustering datasets, and patient stratification datasets. Experimental results show that our proposed framework achieves an improvement of around 2%--4% over different evaluation metrics in all the four domains in comparison to state-of-the art methods.