K-harmonic Means Clustering Research Articles

Two-pronged feature reduction in spectral clustering with optimized landmark selection

Spectral clustering is widely employed for clustering data points, particularly for non-linear and non-convex structures in high-dimensional spaces. However, it faces challenges due to the high computational cost of eigen decomposition operations and the performance limitations with high-dimensional data. In this paper, we introduce BVA_LSC, a novel spectral clustering algorithm designed to address these challenges. Firstly, we incorporate an advanced feature reduction stage utilizing Barnes-Hut t-SNE and a deep Variational Autoencoder (VAE) to efficiently reduce the dimensionality of the data, thereby accelerating eigen decomposition. Secondly, we propose an adaptive landmark selection strategy that combines the Grey Wolf Optimizer (GWO) with a novel objective function and K-harmonic means clustering. This strategy dynamically determines an optimal number of landmarks, enhancing the representativeness of the data and reducing the size of the similarity matrix. We assess the performance of our algorithm on various standard datasets, demonstrating its superiority over state-of-the-art methods in terms of accuracy and efficiency.

Variation Trend Prediction of Dam Displacement in the Short-Term Using a Hybrid Model Based on Clustering Methods

The deformation behavior of a dam can comprehensively reflect its structural state. By comparing the actual response with model predictions, dam deformation prediction models can detect anomalies for effective advance warning. Most existing dam deformation prediction models are implemented within a single-step prediction framework; the single-time-step output of these models cannot represent the variation trend in the dam deformation, which may contain important information on dam evolution during the prediction period. Compared with the single value prediction, predicting the tendency of dam deformation in the short term can better interpret the dam’s structural health status. Aiming to capture the short-term variation trends of dam deformation, a multi-step displacement prediction model of concrete dams is proposed by combining the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) algorithm, the k-harmonic means (KHM) algorithm, and the error minimized extreme learning machine (EM-ELM) algorithm. The model can be divided into three stages: (1) The CEEMDAN algorithm is adopted to decompose dam displacement series into different signals according to their timing characteristics. Moreover, the sample entropy (SE) method is used to remove the noise contained in the decomposed signals. (2) The KHM clustering algorithm is employed to cluster the denoised data with similar characteristics. Furthermore, the sparrow search algorithm (SSA) is utilized to optimize the KHM algorithm to avoid the local optimal problem. (3) A multi-step prediction model to capture the short-term variation of dam displacement is established based on the clustered data. Engineering examples show that the model has good prediction performance and strong robustness, demonstrating the feasibility of applying the proposed model to the multi-step forecasting of dam displacement.

Maneuvering target oriented digital camouflage image generation method

Since the digital camouflage generation method based on fixed single background image cannot fully meet the hidden need of maneuvering targets. In this paper, a method of generating digital camouflage image based on several background images is proposed. Firstly, according to the active range of the maneuvering target, several background images are collected. Secondly, in order to resolve the problem that the clustering algorithm is sensitive to the initial clustering center and easy to fall into local optimum, K-harmonic means (KHM) clustering algorithm is introduced and initial clustering center is determined based on color histogram. Again, KHM clustering is used to extract color features from several background images, the first clustering is extracted from a single background image, and the second clustering is extracted with several color features sets extracted from the first clustering of background images as input. Finally, the regular hexagon is used as the basic unit of the digital camouflage image to construct the spot template, and the digital camouflage image is generated by the lowest horizontal line algorithm. Example verification and camouflage effect detection show that the digital camouflage image generated by this method can effectively realize the concealment of maneuvering targets and has good camouflage effect.

Determination of Pork Meat Storage Time Using Near-Infrared Spectroscopy Combined with Fuzzy Clustering Algorithms.

The identification of pork meat quality is a significant issue in food safety. In this paper, a novel strategy was proposed for identifying pork meat samples at different storage times via Fourier transform near-infrared (FT-NIR) spectroscopy and fuzzy clustering algorithms. Firstly, the FT-NIR spectra of pork meat samples were collected by an Antaris II spectrometer. Secondly, after spectra preprocessing with multiplicative scatter correction (MSC), the orthogonal linear discriminant analysis (OLDA) method was applied to reduce the dimensionality of the FT-NIR spectra to obtain the discriminant information. Finally, fuzzy C-means (FCM) clustering, K-harmonic means (KHM) clustering, and Gustafson–Kessel (GK) clustering were performed to establish the recognition model and classify the feature information. The highest clustering accuracies of FCM and KHM were both 93.18%, and GK achieved a clustering accuracy of 65.90%. KHM performed the best in the FT-NIR data of pork meat considering the clustering accuracy and computation. The overall experiment results demonstrated that the combination of FT-NIR spectroscopy and fuzzy clustering algorithms is an effective method for distinguishing pork meat storage times and has great application potential in quality evaluation of other kinds of meat.

A hybrid clustering algorithm based on improved GWO and KHM clustering

To solve the problem that the K-means algorithm is sensitive to the initial clustering centers and easily falls into local optima, we propose a new hybrid clustering algorithm called the IGWOKHM algorithm. In this paper, we first propose an improved strategy based on a nonlinear convergence factor, an inertial step size, and a dynamic weight to improve the search ability of the traditional grey wolf optimization (GWO) algorithm. Then, the improved GWO (IGWO) algorithm and the K-harmonic means (KHM) algorithm are fused to solve the clustering problem. This fusion clustering algorithm is called IGWOKHM, and it combines the global search ability of IGWO with the local fast optimization ability of KHM to both solve the problem of the K-means algorithm’s sensitivity to the initial clustering centers and address the shortcomings of KHM. The experimental results on 8 test functions and 4 University of California Irvine (UCI) datasets show that the IGWO algorithm greatly improves the efficiency of the model while ensuring the stability of the algorithm. The fusion clustering algorithm can effectively overcome the inadequacies of the K-means algorithm and has a good global optimization ability.

A novel centroid initialization in missing value imputation towards mixed datasets

Currently, many databases contain missing values, especially in medical data. Statistical and data mining approaches often require complete data conditions, where these two approaches will not provide adequate performance if the data contains missing values. Several techniques have been made to overcome missing values, one of which is by deleting data containing missing values. However, this approach will omit a lot of information if the data found includes many missing values. This study used an imputation approach (filling in the missing attributes) with a clustering approach. One of the most common clustering approaches is K-Means Clustering. In K-means clustering, the value of the centroid gets from the closest observed value. In this study, we propose updating the centroid value based on the harmonic average of the distance across all observations per centroid. This method is known as K-Harmonic Means Clustering (KHM). We proposed a new program approach for a mixed dataset on three scenarios for missing values of 10%, 20%, and 30%. From the experiments conducted on experimental data sets containing missing values, we get a small proportion of missing values (10%) with a small number of clusters or K, which gives a smaller RMSE value compared to other scenarios.

A decision support system using hybrid AI based on multi-image quality model and its application in color design

The product-color image conveys consumers’ color demands through emotion cognition. In this paper, a decision support system is proposed based on the hybrid artificial intelligence algorithm. The proposed system explores the internal correlation between the color image and demand of users. In the proposed system, an artificial neural network based on the radial basis function is employed. The network model is trained with an improved particle swarm optimization combined with the weight-adaptive strategy and chaos theory. The proposed model predicts the multi-uses’ color images. Then, the decision colors are extracted from the predicted colors by K-harmonic means clustering. The experimental results show that the proposed color decision support system is promising in designing the color scheme and providing theoretical guidance for the product-color design.

Situational awareness of coherency behavior of synchronous generators in a power system with utility-scale photovoltaics

The smart grid innovation targets at the problems of integrating large portion of intermittent generation resources such as utility-scale and rooftop photovoltaics (PVs), while ensuring both the security and reliability of the electric power grid operation during severe disturbances. To enhance the operators’ performance, the information processing of the large-scale widely interconnected electric power grid needs to be simplified and presented with situational awareness (SA) in a meaningful way, for timely response by the system operators in control centers. Coherency group identification separates the generators in the system into groups that feature similar behavior, which is a method for grid simplification. Meanwhile, wide area measurement systems (WAMS) using data from phasor measurement units (PMUs) provides a solution – enhanced situational awareness to power operation control centers addressing the concerns of capturing and transmitting dynamic data in near real-time. Based upon these technologies, a synchrophasor based identification of generator coherency groups and new visualizations for SA are proposed and developed for online application with using K-harmonic means clustering. Furthermore, a generator vulnerability index (GVI) and a corresponding power system vulnerability index (SVI) are proposed based on the dynamic coherency groups identified. These indices alert system operators on the coherency behavior of the synchronous generators in the system for variations of PV power and/or under severe system disturbances. Typical results are provided for four different disturbances including sudden PV power increase and decrease, unexpected bus faults on major tie-line (inter-area) transmission corridors. In summary, new algorithms, indices and visualization tools have been developed to enhance SA and provide actionable information to system operators in control centers in the presence of variable utility-scale PV power in a power system.

The selection of temperature-sensitivity points based on K-harmonic means clustering and thermal positioning error modeling of machine tools

In the thermal error compensation technology of CNC machine tools, the core is to establish a mathematical model of thermal error with high predictive accuracy and strong robustness. The prerequisite for the error model is to select the optimum temperature-sensitivity points, which can inhibit the multi-collinearity problem among temperature points and improve the predictive accuracy and robustness of the error model. In this paper, K-harmonic means (KHM) clustering is introduced for the first time to select the temperature-sensitivity points in the field of error modeling. In statistical numerical experiments, it is verified that KHM clustering is very stable and requires relatively small number of iterations to converge comparing with the common clustering methods such as K-means (KM) clustering and fuzzy C-means clustering (FCM). Then, the effect of KHM clustering on the selection of temperature-sensitivity points is validated in the actual experiments. Multiple linear regression model combined with KHM clustering (MLR-KHM) is adopted to construct the thermal error model of positioning error. The experimental results demonstrate that the predictive accuracy and robustness of MLR-KHM error model can conform with the requirements of the error compensation.

An efficient hybrid clustering method based on improved cuckoo optimization and modified particle swarm optimization algorithms

Partitional data clustering with K-means algorithm is the dividing of objects into smaller and disjoint groups that has the most similarity with objects in a group and most dissimilarity from the objects of other groups. Several techniques have been proposed to avoid the major limitations of K-Means such as sensitive to initialization and easily convergence to local optima. An alternative to solve the drawback of the sensitive to centroids’ initialization in K-Means is the K-Harmonic Means (KHM) clustering algorithm. However, KHM is sensitive to the noise and easily runs into local optima. Over the past decade, many algorithms are developed for solving this problems based on evolutionary method. However, each algorithm has its own advantages, limitations and shortcomings. In this paper, we combined K-Harmonic Means (KHM) clustering algorithm with an improved Cuckoo Search (ICS) and particle swarm optimization (PSO). ICS is intended to global optimum solution using Lévy flight method through changing radius in a dynamic and shrewd manner. Therefore, it is faster than standard cuckoo search. ICS is effected with PSO to avoid falling into local optima. The proposed algorithm, called ICMPKHM, solves the local optima problem of KHM with significant improvement on efficacy and stability. Experiments with benchmark datasets show that the proposed algorithm is quite insensitive to the centroids’ initialization. Comparative studies with other algorithms reveal that the proposed algorithm produce high quality and stable clustering results.

P-CSREC: A New Approach for Personalized Cloud Service Recommendation

It is becoming a challenging issue for users to choose a satisfied service to fit their need due to the rapid growing number of cloud services and the vast amount of service type varieties. This paper proposes an effective cloud service recommendation approach, named personalized cloud service recommendation (P-CSREC), based on the characterization of heterogeneous information network, the use of association rule mining, and the modeling and clustering of user interests. First, a similarity measure is defined to improve the average similarity (AvgSim) measure by the inclusion of the subjective evaluation of users’ interests. Based on the improved AvgSim, a new model for measuring the user interest is established. Second, the traditional K-Harmonic Means (KHM) clustering algorithm is improved by means of involving multi meta-paths to avoid the convergence of local optimum. Then, a frequent pattern growth (FP-Growth) association rules algorithm is proposed to address the issue and the limitation of traditional association rule algorithms to offer personalization in recommendation. A new method to define a support value of nodes is developed using the weight of user’s score. In addition, a multi-level FP-Tree is defined based on the multi-level association rules theory to extract the relationship in higher level. Finally, a combined user interest with the improved KHM clustering algorithm and the improved FP-Growth algorithm is provided to improve accuracy of cloud services recommendation to target users. The experimental results demonstrated the effectiveness of the proposed approach in improving the computational efficiency and recommendation accuracy.

K-harmonic means clustering algorithm using feature weighting for color image segmentation

This paper mainly proposes K-harmonic means (KHM) clustering algorithms using feature weighting for color image segmentation. In view of the contribution of features to clustering, feature weights which can be updated automatically during the clustering procedure are introduced to calculate the distance between each pair of data points, hence the improved versions of KHM and fuzzy KHM are proposed. Furthermore, the Lab color space, local homogeneity and texture are utilized to establish the feature vector to be more applicable for color image segmentation. The feature group weighting strategy is introduced to identify the importance of different types of features. Experimental results demonstrate the proposed feature group weighted KHM-type algorithms can achieve better segmentation performances, and they can effectively distinguish the importance of different features to clustering.

An Optimized K-Harmonic Means Algorithm Combined with Modified Particle Swarm Optimization and Cuckoo Search Algorithm

Abstract Among the data clustering algorithms, k-means (KM) algorithm is one of the most popular clustering techniques due to its simplicity and efficiency. However, k-means is sensitive to initial centers and it has the local optima problem. K-harmonic-means (KHM) clustering algorithm solves the initialization problem of k-means algorithm, but it also has local optima problem. In this paper, we develop a new algorithm for solving this problem based on an improved version of particle swarm optimization (IPSO) algorithm and KHM clustering. In the proposed algorithm, IPSO is equipped with Cuckoo Search algorithm and two new concepts used in PSO in order to improve the efficiency, fast convergence and escape from local optima. IPSO updates positions of particles based on a combination of global worst, global best with personal worst and personal best to dynamically be used in each iteration of the IPSO. The experimental result on five real-world datasets and two artificial datasets confirms that this improved version is superior to k-harmonic means and regular PSO algorithm. The results of the simulation show that the new algorithm is able to create promising solutions with fast convergence, high accuracy and correctness while markedly improving the processing time.

A Hybrid K-Harmonic Means with ABC Clustering Algorithm Using an Optimal K Value for High Performance Clustering

Large quantities of data are emerging every year and an accurate clustering algorithm is needed to derive information from these data. K-means clustering algorithm is popular and simple, but has many limitations like its sensitivity to initialization, provides local optimum solutions. K-harmonic means clustering is an improved variant of K-means which is insensitive to the initialization of centroids, but still in some cases it ends up with local optimum solutions. Clustering using Artificial Bee Colony (ABC) algorithm always gives global optimum solutions. In this paper a new hybrid clustering algorithm (KHM-ABC) is presented by combining both K-harmonic means and ABC algorithm to perform accurate clustering. Experimental results indicate that the performance of the proposed algorithm is superior to the available algorithms in terms of the quality of clusters.

Combining K-Means and K-Harmonic with Fish School Search Algorithm for data clustering task on graphics processing units

Data clustering is related to the split of a set of objects into smaller groups with common features. Several optimization techniques have been proposed to increase the performance of clustering algorithms. Swarm Intelligence (SI) algorithms are concerned with optimization problems and they have been successfully applied to different domains. In this work, a Swarm Clustering Algorithm (SCA) is proposed based on the standard K-Means and on K-Harmonic Means (KHM) clustering algorithms, which are used as fitness functions for a SI algorithm: Fish School Search (FSS). The motivation is to exploit the search capability of SI algorithms and to avoid the major limitation of falling into locally optimal values of the K-Means algorithm. Because of the inherent parallel nature of the SI algorithms, since the fitness function can be evaluated for each individual in an isolated manner, we have developed the parallel implementation on GPU of the SCAs, comparing the performances with their serial implementation. The interest behind proposing SCA is to verify the ability of FSS algorithm to deal with the clustering task and to study the difference of performance of FSS-SCA implemented on CPU and on GPU. Experiments with 13 benchmark datasets have shown similar or slightly better quality of the results compared to standard K-Means algorithm and Particle Swarm Algorithm (PSO) algorithm. There results of using FSS for clustering are promising.

An Optimized K-Harmonic Means Algorithm Combined with Modified Particle Swarm Optimization and Cuckoo Search Algorithm

Abstract Among the data clustering algorithms, the k-means (KM) algorithm is one of the most popular clustering techniques because of its simplicity and efficiency. However, KM is sensitive to initial centers and it has a local optima problem. The k-harmonic means (KHM) clustering algorithm solves the initialization problem of the KM algorithm, but it also has a local optima problem. In this paper, we develop a new algorithm for solving this problem based on a modified version of particle swarm optimization (MPSO) algorithm and KHM clustering. In the proposed algorithm, MPSO is equipped with the cuckoo search algorithm and two new concepts used in PSO in order to improve the efficiency, fast convergence, and escape from local optima. MPSO updates the positions of particles based on a combination of global worst, global best with personal worst, and personal best to dynamically be used in each iteration of the MPSO. The experimental result on eight real-world data sets and two artificial data sets confirms that this modified version is superior to KHM and the regular PSO algorithm. The results of the simulation show that the new algorithm is able to create promising solutions with fast convergence, high accuracy, and correctness while markedly improving the processing time.

Solubility prediction of supercritical carbon dioxide in 10 polymers using radial basis function artificial neural network based on chaotic self-adaptive particle swarm optimization and K-harmonic means

Excellent prediction modeling of CO2solubility in polymers using hybrid computation algorithm.

A hybrid fuzzy K-harmonic means clustering algorithm

K-means (KM) clustering is very sensitive to the initialization and easily converges to the local optima. K-harmonic means (KHM) clustering solves this problem by introducing the harmonic averages of the distances as components to its objective function. It is demonstrated through many experiments that KHM is insensitive to the initialization of the cluster centers attributed to a boosting function. However, KHM has a noise sensitivity problem in clustering noisy data because of its probabilistic constraint the same as fuzzy c-means (FCM) clustering. In this paper, we present a hybrid fuzzy K-harmonic means (HFKHM) clustering algorithm based on improved possibilistic c-means clustering (IPCM) and KHM. HFKHM solves the noise sensitivity problem of KHM and improves the memberships of IPCM by combining the merits of KHM and IPCM. The performance of HFKHM is compared with those of KHM and IPCM on several data sets. Experimental results show the superiority of HFKHM.

New Genetic Gravitational Search approach for Data Clustering using K-Harmonic Means

this article the new hybrid data clustering approach, Gravitational Genetic KHM, based on Genetic algorithm (GA), Gravitational Search Algorithm (GSA) and K-harmonic Means (KHM) is proposed. Data Clustering is used to group similar set of objects into set of disjoint classes, object in class are highly similar than the objects in other classes. Among various clustering methods, KHM is one of the most popular clustering techniques. KHM is applied widely and works well in many fields, but this method runs in local optima. In the proposed approach the merits of Genetic Algorithm are used to escape the KHM clustering from local optima and to overcome the slow convergence speed of GSA. This paper is presented as work-in-progress in which the work model is proposed and some intermediate results are discussed which in turn will be compared with existing hybrid algorithms. The results are tested on several datasets. Keywords-Harmonic Means (KHM), Clustering, Gravitational Search Algorithm (GSA), Genetic Algorithm (GA).

Candidate groups search for K-harmonic means data clustering

Clustering is a very popular data analysis and data mining technique. K-means is one of the most popular methods for clustering. Although K-mean is easy to implement and works fast in most situations, it suffers from two major drawbacks, sensitivity to initialization and convergence to local optimum. K-harmonic means clustering has been proposed to overcome the first drawback, sensitivity to initialization. In this paper we propose a new algorithm, candidate groups search (CGS), combining with K-harmonic mean to solve clustering problem. Computational results showed CGS does get better performance with less computational time in clustering, especially for large datasets or the number of centers is big.