Clustering Scheme Research Articles

An efficient fuzzy hyper-edge clustering and popularity-based caching scheme for CCN-enabled IoT networks

An efficient fuzzy hyper-edge clustering and popularity-based caching scheme for CCN-enabled IoT networks

An effective clustering scheme for high-dimensional data

An effective clustering scheme for high-dimensional data

A resource of single-cell gene expression profiles in a planarian Dugesia japonica.

The freshwater planarian Dugesia japonica maintains an abundant heterogeneous cell population called neoblasts, which include adult pluripotent stem cells. Thus, it is an excellent model organism for stem cell and regeneration research. Recently, many single-cell RNA sequencing (scRNA-seq) databases of several model organisms, including other planarian species, have become publicly available; these are powerful and useful resources to search for gene expression in various tissues and cells. However, the only scRNA-seq dataset for D. japonica has been limited by the number of genes detected. Herein, we collected D. japonica cells, and conducted an scRNA-seq analysis. A novel, automatic, iterative cell clustering strategy produced a dataset of 3,404 cells, which could be classified into 63 cell types based on gene expression profiles. We introduced two examples for utilizing the scRNA-seq dataset in this study using D. japonica. First, the dataset provided results consistent with previous studies as well as novel functionally relevant insights, that is, the expression of DjMTA and DjP2X-A genes in neoblasts that give rise to differentiated cells. Second, we conducted an integrative analysis of the scRNA-seq dataset and time-course bulk RNA-seq of irradiated animals, demonstrating that the dataset can help interpret differentially expressed genes captured via bulk RNA-seq. Using the R package "Seurat" and GSE223927, researchers can easily access and utilize this dataset.

Self-Configuration Management towards Fix-Distributed Byzantine Sensors for Clustering Schemes in Wireless Sensor Networks

To avoid overloading a network, it is critical to continuously monitor the natural environment and disseminate data streams in synchronization. Based on self-maintaining technology, this study presents a technique called self-configuration management (SCM). The purpose is to ensure consistency in the performance, functionality, and physical attributes of a wireless sensor network (WSN) over its lifetime. During device communication, the SCM approach delivers an operational software package for the radio board of system problematic nodes. We offered two techniques to help cluster heads manage autonomous configuration. First, we created a separate capability to determine which defective devices require the operating system (OS) replica. The software package was then delivered from the head node to the network’s malfunctioning device via communication roles. Second, we built an autonomous capability to automatically install software packages and arrange the time. The simulations revealed that the suggested technique was quick in transfers and used less energy. It also provided better coverage of system fault peaks than competitors. We used the proposed SCM approach to distribute homogenous sensor networks, and it increased system fault tolerance to 93.2%.

A monolithic hyper ROM FE2 method with clustered training at finite deformations

The usage of numerical homogenization to obtain structure–property relations by applying the finite element method at both the micro- and macroscale has gained much interest in the research community. The computational cost of this so-called FE2 method, however, is typically so high that algorithmic modifications and reduction methods are essential. In the present contribution, a monolithic solution algorithm is combined with reduced order modeling (ROM) and the empirical cubature method (ECM) for hyper integration. It is further complemented by a clustered training strategy, which lowers the training effort and the number of necessary ROM modes immensely. The applied methods can be combined modularly as desired in finite element approaches. An implementation in terms of an extension to the previously established MonolithFE2 code is provided. Numerical examples show the efficiency and accuracy of the monolithic hyper ROM FE2 method and the advantages of the clustered training strategy. Even for two-scale problems with complex geometry and complex, inelastic material behaviors it was shown that speedup factors of almost 1000 (i.e., three orders of magnitude) regarding the online simulation time and of up to 30 regarding all necessary computing effort are obtainable in comparison to the conventional FE2 scheme. The training stage requires only around 3% of that time, meaning that the offline phase is relatively inexpensive, in contrast to many Neural Network approaches, whose employment, in terms of total computational efficiency, only pays off if a large number of online simulations is to be conducted, without requiring additional training.

A semi-distributed charging strategy for electric vehicle clusters

Uncoordinated charging of electric vehicle (EV) clusters can lead to unanticipated surges in demand that strain the grid, hence reducing its reliability. To address this challenge, this paper proposes a semi-distributed control method for EV clusters charging where the decision-making process takes place locally, rather than relying on an external controller. The method ensures that charging demand can be fulfilled while achieving several goals, including following local renewable energy generation, pausing charging for transformer protection, and continuing charging progress in the absence of external information. The proposed method is validated through simulations and experimental tests during a public demonstration. The results demonstrate the functionality of the control method and show that it can effectively manage the charging of a cluster of EVs while reducing strain on the power grid.

Optimizing Clustering Approaches in Cloud Environments

This study focuses on the challenge of developing abstract models to differentiate various cloud resources. It explores the advancements in cloud products that offer specialized services to meet specific external needs. The study proposes a new approach to request processing in clusters, improving downtime, load distribution, and overall performance. A comparison of three clustering approaches is conducted: local single cluster, local multiple clusters, and multiple cloud clusters. Performance, scalability, fault tolerance, resource allocation, availability, and cost-effectiveness are evaluated through experiments with 50 requests. All three approaches achieve a 100% success rate, but processing times vary. The local single cluster has the longest duration, while the local multiple clusters and multiple cloud clusters perform better and offer faster processing, scalability, fault tolerance, and availability. From a cost perspective, the local single cluster and local multiple clusters incur capital and operational expenses, while the multiple cloud clusters follow a pay-as-you-go model. Overall, the local multiple clusters and multiple cloud clusters outperform the local single cluster in terms of performance, scalability, fault tolerance, resource allocation, availability, and cost-effectiveness. These findings provide valuable insights for selecting appropriate clustering strategies in cloud environments.

Random clustering and dynamic recognition-based operation strategy for energy storage system in industrial park

The high volatility and intermittency of power load pose significant challenges to achieving optimal operation of energy storage system (ESS), which ultimately affects the economic benefits of industrial parks. To address this issue, this paper proposes a random clustering and dynamic recognition-based operation strategy for ESS in industrial parks. Firstly, we propose an expected cost minimization-driven random clustering method to determine the optimal cluster number of load curves. We then develop optimal day-ahead self-operating strategies of ESS corresponding to each of the clustered load curves. The uncertainty of power load is described by linearized risk assessment indexes. Secondly, we present a dynamic recognition technology that consists of the characteristics of value range, slope similarity, power size similarity, and curve step similarity to recognize the cluster to which the intra-day load curve belongs. Finally, we select the optimal intra-day charging/discharging strategy of ESS according to the recognized cluster as the operation strategy of the industrial park. Numerical experiments on a real-life industrial park with photovoltaic and ESS validate that the proposed strategy can reduce operation costs as well as promote photovoltaic local accommodation.

A Parameter Estimation of Photovoltaic Models Using a Boosting Flower Pollination Algorithm.

An accurate and reliable estimation of photovoltaic models holds immense significance within the realm of energy systems. In pursuit of this objective, a Boosting Flower Pollination Algorithm (BFPA) was introduced to facilitate the robust identification of photovoltaic model parameters and enhance the conversion efficiency of solar energy into electrical energy. The incorporation of a Gaussian distribution within the BFPA serves the dual purpose of conserving computational resources and ensuring solution stability. A population clustering strategy is implemented to steer individuals in the direction of favorable population evolution. Moreover, adaptive boundary handling strategies are deployed to mitigate the adverse effects of multiple individuals clustering near problem boundaries. To demonstrate the reliability and effectiveness of the BFPA, it is initially employed to extract unknown parameters from well-established single-diode, double-diode, and photovoltaic module models. In rigorous benchmarking against eight control methods, statistical tests affirm the substantial superiority of the BFPA over these controls. Furthermore, the BFPA successfully extracts model parameters from three distinct commercial photovoltaic cells operating under varying temperatures and light irradiances. A meticulous statistical analysis of the data underscores a high degree of consistency between simulated data generated by the BFPA and observed data. These successful outcomes underscore the potential of the BFPA as a promising approach in the field of photovoltaic modeling, offering substantial enhancements in both accuracy and reliability.

Trading strategy for virtual power plant clusters based on a multi-subject game model

With the rapid development of renewable energy and the continuous growth of new loads, VPP has become an important form of smart grid and energy internet due to its flexible and effective management of distributed energy. During the operation of Virtual power plant, there is a game relationship between the system operator and VPP, and they are in a non-complete information environment. However, most of the current game optimization modeling is under the condition of complete information, and the game model based on complete information cannot solve this problem. This article focuses on the VPP cluster trading problem based on non-complete information game theory, constructs a Bayesian game model for multiple VPPs with multiple subjects under the master-slave game framework by introducing the Bayesian concept to optimize the cluster transactions within VPPs, and verifies the effectiveness of the model through simulation experiments. The experimental results show that the multi-VPP multi-subject Bayesian game model established in the study can guarantee the privacy of each subject and effectively reduce PAR, thus ensuring the security and stability of the VPP network and reducing cost expenditures, which has practicality in actual VPP cluster transactions.

Optimized clustering sample selection for spectral reflectance recovery

The accuracy of spectral recovery depends heavily on the selection of an appropriate sample set, so the optimized sample selection by clustering strategy can improve the spectral recovery results. This paper presents a sample optimization method that combines hierarchical clustering and K-mean angle similar clustering to achieve this process. The proposed method employs the hierarchical clustering to divide the training sample dataset into 15 subspaces and obtain 15 subspace centroids. The similarity distance is then calculated between the testing sample and each subspace samples, and the subspace with the sample having the smallest distance is selected. The testing sample is utilized as a priori centroid, which clusters the optimal subspace by competition with the centroid of the subspace selected. This iterative process continues until the centroid of the subspace remains unaltered. Finally, the training samples within the optimal subspace use to recover spectral reflectance through Euclidean distance weighting. Experimental results demonstrate that the proposed method outperforms existing methods in terms of spectral and colorimetric accuracy, as well as stability and robustness. This research provides a solution to the problem of data redundancy in the spectral recovery process and enhances the accuracy and efficiency of spectral recovery.

JOCP: A jointly optimized clustering protocol for industrial wireless sensor networks using double‐layer selection evolutionary algorithm

SummaryIndustrial Wireless Sensor Networks (IWSNs) have gained significant popularity for their ability to improve plant productivity and production efficiency through self‐organization and rapid deployment. However, the challenge of achieving reliable and sustainable data transmission remains due to the large amount of heterogeneous data generated by large‐scale IWSNs. In this paper, we present a systematic approach that addresses this challenge by focusing on data transmission clustering strategies, optimal cluster head selection, and routing design. We propose a novel Jointly Optimized Clustering Protocol (JOCP), which enhances cluster head selection by considering multiple critical factors that impact the IWSN life cycle. JOCP incorporates two key modules: the many‐objective clustering model and the double‐layer selection evolutionary algorithm. Specifically, the many‐objective clustering model considers cluster head selection from different perspectives, including maximum node survival cycle, minimum node distance, minimum network overall energy consumption, and balanced cluster energy consumption, with the aim of extending the network life cycle. Additionally, the double‐layer selection evolutionary algorithm optimizes the many‐objective clustering model to select appropriate cluster heads. Through performance verification, we demonstrate that the JOCP protocol effectively enhances the network life cycle and increases the number of surviving nodes compared to baseline clustering algorithms. Our research provides a comprehensive solution to the challenges associated with reliable and sustainable data transmission in large‐scale IWSNs, highlighting the potential for improved performance in industrial applications.

Grant-Free NOMA: A Low-Complexity Power Control through User Clustering.

Non-orthogonal multiple access (NOMA) has emerged as a promising solution to support multiple devices on the same network resources, improving spectral efficiency and enabling massive connectivity required by ever-increasing Internet of Things devices. However, traditional NOMA schemes operate in a grant-based fashion and require channel-state information and power control, which hinders its implementation for massive machine-type communications. Accordingly, this paper proposes synchronous grant-free NOMA (GF-NOMA) frameworks that effectively integrate user equipment (UE) clustering and low-complexity power control to facilitate the power-reception disparity required by the power-domain NOMA. Although single-level GF-NOMA (SGF-NOMA) designates an identical transmit power for all UEs, multi-level GF-NOMA (MGF-NOMA) groups UEs into partitions based on the sounding reference signals strength and assigns partitions with different identical power levels. Based on the objective of interest (e.g., max-sum or max-min rate), the proposed UE clustering scheme iteratively admits UEs to form clusters whose size is dynamically determined based on the number of UEs and available resource blocks (RBs). Once the UEs are acknowledged with power levels and allocated RBs through random-access response (RAR) messages, UEs can transmit anytime without grant acquisition. Numerical results show that the proposed GF-NOMA frameworks can compute clusters in the order of milliseconds for hundreds of UEs. The MGF-NOMA can reach up to 96-99% of the optimal benchmark max-sum rate, and the SGF-NOMA reaches 87% of the optimal benchmark max-sum rate at the same power consumption. Since the MGF-NOMA and optimal benchmark enforce the strongest and weakest channel UEs to transmit at maximum and minimum transmit powers, respectively, the SGF-NOMA also offers a significantly higher energy consumption fairness and network lifetime as all UEs consume equal transmit powers. Although the MGF-NOMA delivers an inferior max-min rate performance, the SGF-NOMA is shown to reach 3e6 MbpJ energy efficiency compared to the 1e7 MbpJ benchmark.

Exploring disease axes as an alternative to distinct clusters for characterizing sepsis heterogeneity.

Various studies have analyzed sepsis subtypes, yet the reproducibility of such results remains unclear. This study aimed to determine the reproducibility of sepsis subtypes across multiple cohorts. The study examined 63,547 sepsis patients from six distinct cohorts who had similar sepsis-related characteristics (vital signs, lactate, sequential organ failure assessment score, bilirubin, serum, urine output, and Glasgow coma scale). Identical cluster analysis techniques were used, employing 27 clustering schemes, and normalized mutual information (NMI), a metric ranging from 0 to 1 with higher values indicating better concordance, was employed to quantify the clustering solutions' reproducibility. Principal component analysis (PCA) was utilized to obtain the disease axis, and its uniformity across cohorts was evaluated through patterns of feature loading and correlation. The reproducibility of sepsis clustering subtypes across the various studies was modest (median NMI ranging from 0.08 to 0.54). The top-down transfer learning method (model trained on cohorts with greater severity was transferred to cohorts with lower severity score) had a higher NMI value than the bottom-up approach (median [Q1, Q3]: 0.64 [0.49, 0.78] vs. 0.23 [0.2, 0.31], p < 0.001). The reproducibility was greater when the transfer solution was performed within United States (US) cohorts. The PCA analysis revealed that the correlation pattern between variables was consistent across all cohorts, and the first two disease axes were the "shock axis" and "systemic inflammatory response syndrome (SIRS) axis." Cluster analysis of sepsis patients across various cohorts showed modest reproducibility. Sepsis heterogeneity is better characterized through continuous disease axes that coexist to varying degrees within the same individual instead of mutually exclusive subtypes.

A Primer on Clustering of Forest Management Units for Reliable Design-Based Direct Estimates and Model-Based Small Area Estimation

This study employs clustering analysis to group forest management units using auxiliary, satellite imagery-derived height metrics and past wall-to-wall tree census data from a natural, uneven-aged forest. Initially, we conducted an exhaustive exploration to determine the optimal number of clusters k, considering a wide range of clustering schemes, indices, and two specific k ranges. The optimal k is influenced by various factors, including the minimum k considered, the selected clustering algorithm, the clustering indices used, and the auxiliary variables. Specifically, the minimum k, the Euclidean distance metric, and the clustering index were instrumental in determining the optimal cluster numbers, with algorithms exerting minimal influence. Unlike traditional validation indices, we assessed the performance of these optimally defined clusters based on direct estimates and additional criteria. Subsequently, our research introduces a twofold methodology for Small Area Estimation (SAE). The first approach focuses on aggregating forest management units at the cluster level to increase the sample size, thereby yielding reliable design-based direct estimates for key forest attributes, including growing stock volume, basal area, tree density, and mean tree height. The second approach prepares area-level data for the future application of model-based estimators, contingent on establishing a strong correlation between target and auxiliary variables. Our methodology has the potential to enhance forest inventory practices across a wide range of forests where area-level auxiliary covariates are available.

Calibrating TDDFT Calculations of the X-ray Emission Spectrum of Liquid Water: The Effects of Hartree-Fock Exchange.

The structure and dynamics of liquid water continue to be debated, with insight provided by, among others, X-ray emission spectroscopy (XES), which shows a split in the high-energy 1b1 feature. This split is yet to be reproduced by theory, and it remains unclear if these difficulties are related to inaccuracies in dynamics simulations, spectrum calculations, or both. We investigate the performance of different methods for calculating XES of liquid water, focusing on the ability of time-dependent density functional theory (TDDFT) to reproduce reference spectra obtained by high-level coupled cluster and algebraic-diagrammatic construction scheme calculations. A metric for evaluating the agreement between theoretical spectra termed the integrated absolute difference (IAD), which considers the integral of shifted difference spectra, is introduced and used to investigate the performance of different exchange-correlation functionals. We find that computed spectra of symmetric and asymmetric model water structures are strongly and differently influenced by the amount of Hartree-Fock exchange, with best agreement to reference spectra for ∼40-50%. Lower percentages tend to yield high density of contributing states, resulting in too broad features. The method introduced here is useful also for other spectrum calculations, in particular where the performance for ensembles of structures are evaluated.

China's new urban clusters strategy for coordinated economic growth: Evidence from the sports industry.

In 2014, the Chinese government unveiled the New Urbanization Plan and Document No. 46, which profoundly influenced the development trajectory of the regional economy and sports industry. Using the coupling coordination model, this study aimed to assess the development progress of the sports industry and urban clusters economy. This study sampled Greater Bay Area urban clusters (GBAUC) and Yangtze River Delta urban clusters (YRDUC). The statistics covered one year after the release of the policies to date. We developed a total of 15 macro indicators to evaluate the sports industry and urban cluster economy as two distinct, yet interdependent, economic systems. Using the entropy weight method, we determined the standardized values and weights for the two systems before calculating the coupling coordination degree (D). Between 2015 and 2021, the sampled sports industry and urban clusters economy exhibited coordinated high growth across all economic metrics, with multiple sports industry metrics exhibiting double-digit growth. In 2015, both showed extreme imbalance: D of GBAUC = 0.092, D of YRDUC = 0.091. In 2017, both improved to bare coordination: D of GBAUC = 0.600, D of YRDUC = 0.566. In 2019, both reached well coordination: D of GBAUC = 0.851, D of YRDUC = 0.814. By 2021, both achieved quality coordination: D of GBAUC = 0.990, D of YRDUC = 1. This study provides the first evidence from the sports industry that China's new urbanization model and Document No. 46 are highly effective for synergistic regional economic growth.

NSCKL: Normalized Spectral Clustering With Kernel-Based Learning for Semisupervised Hyperspectral Image Classification.

Spatial-spectral classification (SSC) has become a trend for hyperspectral image (HSI) classification. However, most SSC methods mainly consider local information, so that some correlations may not be effectively discovered when they appear in regions that are not contiguous. Although many SSC methods can acquire spatial-contextual characteristics via spatial filtering, they lack the ability to consider correlations in non-Euclidean spaces. To address the aforementioned issues, we develop a new semisupervised HSI classification approach based on normalized spectral clustering with kernel-based learning (NSCKL), which can aggregate local-to-global correlations to achieve a distinguishable embedding to improve HSI classification performance. In this work, we propose a normalized spectral clustering (NSC) scheme that can learn new features under a manifold assumption. Specifically, we first design a kernel-based iterative filter (KIF) to establish vertices of the undirected graph, aiming to assign initial connections to the nodes associated with pixels. The NSC first gathers local correlations in the Euclidean space and then captures global correlations in the manifold. Even though homogeneous pixels are distributed in noncontiguous regions, our NSC can still aggregate correlations to generate new (clustered) features. Finally, the clustered features and a kernel-based extreme learning machine (KELM) are employed to achieve the semisupervised classification. The effectiveness of our NSCKL is evaluated by using several HSIs. When compared with other state-of-the-art (SOTA) classification approaches, our newly proposed NSCKL demonstrates very competitive performance. The codes will be available at https://github.com/yuanchaosu/TCYB-nsckl.

Autonomous Cross Domain Adaptation Under Extreme Label Scarcity.

A cross domain multistream classification is a challenging problem calling for fast domain adaptations to handle different but related streams in never-ending and rapidly changing environments. Notwithstanding that existing multistream classifiers assume no labeled samples in the target stream, they still incur expensive labeling costs since they require fully labeled samples of the source stream. This article aims to attack the problem of extreme label shortage in the cross domain multistream classification problems where only very few labeled samples of the source stream are provided before process runs. Our solution, namely, Learning Streaming Process from Partial Ground Truth (LEOPARD), is built upon a flexible deep clustering network where its hidden nodes, layers, and clusters are added and removed dynamically with respect to varying data distributions. A deep clustering strategy is underpinned by a simultaneous feature learning and clustering technique leading to clustering-friendly latent spaces. A domain adaptation strategy relies on the adversarial domain adaptation technique where a feature extractor is trained to fool a domain classifier by classifying source and target streams. Our numerical study demonstrates the efficacy of LEOPARD where it delivers improved performances compared to prominent algorithms in 15 of 24 cases. Source codes of LEOPARD are shared in https://github.com/wengweng001/LEOPARD.git to enable further study.

ASCFL: Accurate and Speedy Semi-Supervised Clustering Federated Learning

The influence of non-Independent Identically Distribution (non-IID) data on Federated Learning (FL) has been a serious concern. Clustered Federated Learning (CFL) is an emerging approach for reducing the impact of non-IID data, which employs the client similarity calculated by relevant metrics for clustering. Unfortunately, the existing CFL methods only pursue a single accuracy improvement, but ignore the convergence rate. Additionlly, the designed client selection strategy will affect the clustering results. Finally, traditional semi-supervised learning changes the distribution of data on clients, resulting in higher local costs and undesirable performance. In this paper, we propose a novel CFL method named ASCFL, which selects clients to participate in training and can dynamically adjust the balance between accuracy and convergence speed with datasets consisting of labeled and unlabeled data. To deal with unlabeled data, the prediction labels strategy predicts labels by encoders. The client selection strategy is to improve accuracy and reduce overhead by selecting clients with higher losses participating in the current round. What is more, the similarity-based clustering strategy uses a new indicator to measure the similarity between clients. Experimental results show that ASCFL has certain advantages in model accuracy and convergence speed over the three state-of-the-art methods with two popular datasets.