Clustering Algorithm Research Articles

Research on the Design of Performance Evaluation System for Physical Education Major Based on Multimedia Information Processing Technology

The Massive Open Online Course (MOOC) platform, despite its reach and potential, faces significant challenges related to learner diversity, including variations in student backgrounds, work experiences, and learning environments. By integrating the principles of ant colony clustering algorithms with MOOC platform dynamics, our study devises a strategy for grouping students based on shared characteristics, thereby fostering a tailored learning environment. A streamlined MOOC platform design framework is outlined, accompanied by a detailed blueprint for a peer-evaluation information system, aimed at accurately gauging students' academic progress within their disciplines. This platform enables students to effortlessly access and engage with courses aligned with their interests, while the reciprocal assessment mechanism heightens understanding of course materials and alleviates pressure on educators. Our research contributes a pragmatic solution to the challenge of student assignment clustering within MOOCs, enhancing both individual learning outcomes and the broader instructional quality.

Distributed enhanced multi-objective evolutionary algorithm based on decomposition for cluster analysis in wireless sensor network

Conventional clustering algorithms do not recognize patterns and structures with contradicting objectives in large, distributed datasets. Distributed clustering leverages rapid processing capabilities to allow multiple nodes to work together. This paper proposes a Distributed clustering based on Multiobjective Evolutionary Algorithm by Decomposition (D-MOEA/d) to solve various multiobjective optimization problems in wireless sensor networks (WSNs). In MOEA/d, a multiobjective optimization problem decomposes into several scalar optimization subproblems, each focusing on a distinct objective. Each subproblem is expressed as a clustering problem that uses local data to perform distributed clustering. The proposed method has been extended to achieve improved accuracy in less time by using a smaller feature subset with less redundancy. The Distributed Enhanced MOEA/d (DE-MOEA/d) avoids local optima by achieving diversity in the population using fuzzy-based nearest neighbor selection, sparse population initialization, and evolved mutation operator. This integration improves the accuracy of the clustering process at WSN nodes, ensuring the attainment of well-balanced solutions across multiple optimization criteria in the distributed environment. Average Euclidean and total symmetrical deviations are the two cost functions used to minimize while clustering on the MOEA/d framework. Six real-life WSN datasets are used to assess the performance of the proposed technique: (1) the Delhi air pollution dataset, (2) the Canada weather station dataset, (3) the Thames River water quality dataset, (4) the Narragansett Bay water quality dataset, (5) the Cook Agricultural land dataset and 6) Gordon Soil dataset. The simulation results of both proposed algorithms are compared with Multiobjective distributed particle swarm optimization (DMOPSO) and Distributed K-means (DK-Means). The proposed algorithm DE-MOEA/d performs better in terms of the Silhouette index (SI), Dunn index (DI), Davies–Bouldin index (DBI), and Kruskal–Wallis (KW) statistical test.

Clustering and Interpretation of time-series trajectories of chronic pain using evidential c-means

The most well-known unsupervised classification algorithms allow for the identification of hard or probabilistic partitions. However, when working with complex datasets such as those found in the healthcare domain, it is important to note that these partitions may have limitations, particularly when considering the uncertainty associated with medical data. Indeed, these algorithms do not account for modeling outliers, imprecise, or uncertain observations. In this study, we focused on analyzing time series of barometers attributes related to pain intensity in individuals with chronic pain. Our goal was to identify different typologies of care trajectories, highlighting distinct trajectories of chronic pain through clustering techniques. We propose a soft clustering approach based on feature extraction and selection from sequential data, aiming to improve interpretability and enhance the performance of the clustering procedure. Time series feature extraction and selection effectively handles complex and noisy data, improving interpretability and clustering performance. Evidential soft clustering models data uncertainty and imprecision, providing a better representation of nuances and variations in complex, raw data. The first step involves extracting features from the available time series and selecting the most important attributes. For this purpose, we use a time series feature extractor (Tsfresh) and unsupervised feature selection methods, including unsupervised Random Forest, Laplacian Score, and unsupervised Spectral Feature Selection. The second step involves using the evidential c-means (ECM) clustering algorithm on the extracted attributes. The ECM method, based on belief functions, allows for generating a credal partition that has the ability to model various forms of uncertainty. This partition can then be transformed into a hard partition to study individuals based on this uncertainty criterion. The results reveal the existence of two clusters of chronic pain related to discomfort and well-being, exhibiting excellent separability and compactness. Additionally, an uncertain cluster emerges grouping patients with intermediate characteristics. The interpretability of the determined partitions through descriptive analysis, statistical tests, and repeated measures multinomial regression on clinical and demographic data allowed us to determine the profile of patients in the identified trajectories.

Measuring emotions to classify songs: The impact of the COVID-19 pandemic on music streaming data

Data from music streaming has gained increasing attention since it allowsstudying music preferences across diverse cultures and different periods of time.Indeed, the study of “music and emotion” is crucial for understanding the psychologicalrelationship between human sentiments and music. The temporal studyof musical emotions provides beneficial insights into the analysis of the mood oflisteners during periods of particular relevance and stress (e.g., the COVID-19pandemic). This study performs music streaming data analysis to retrieve themusical emotions of the top Italian streamed songs during the pandemic. To thisend, we propose two new indices for measuring anger and joy in songs. We suggesta procedure for clustering music streaming data: the DISTATIS procedureand Partitioning Around Medoids (PAM) clustering algorithm are sequentiallyapplied to identify intervals of time sharing similar sentiments. Finally, we employthe proposed procedure to investigate the relationship between the evolutionof the pandemic spread and sentiments extracted from songs. The results show that music streaming data analysis allow identifying fiveclusters of time intervals sharing similar sentiments,

Diagnosis of high‐speed railway ballastless track arching based on unsupervised learning framework

AbstractVehicle‐mounted detection methods have been widely applied in the maintenance of high‐speed railways (HSRs), providing feasibility for diagnosing ballastless track arching. However, applying detection data faces several key limitations: (1) The threshold mostly requires manual setting, making recognition accuracy highly subjective; (2) the extensive workload of manual inspections makes it challenging to label detection data, hindering the application of supervised learning approaches. To address these problems, this paper utilizes the longitudinal level irregularity data obtained from vehicle‐mounted detection, employing the concept of unsupervised learning for dimensionality reduction, combined with clustering algorithms and minimal label fine‐tuning, to design two frameworks: the fully unsupervised framework (FUF) and the few‐shot fine‐tuned framework (FFF). Experiments on dynamic detection data from a Chinese HSR line were conducted, comparing the performance of data dimensionality reduction, clustering, and classification under different strategy combinations. The results show that the improved variational autoencoder significantly enhances the performance of the encoder in dimensionality reduction, facilitating better feature extraction; the FUF achieves effective clustering outcomes without any labeled samples and its adjusted rand index score exceeded 0.8, showcasing its robustness and applicability in scenarios with no prior annotations; the FFF requires only a small number of labeled samples (labeling ratio of 5%) and achieves excellent performance, with metrics such as accuracy exceeding 0.85, thus greatly reducing the reliance on labeled data. This study offers a novel method for solving engineering issues with limited labeled data, providing an efficient solution for identifying track arching defects and advancing railway infrastructure monitoring.

Efficient acceleration of the convergence of the minimum free energy path via a path-planning generated initial guess.

We demonstrate that combining a shifted clustering algorithm with a fast-marching-based algorithm can generate accurate approximations of the minimum energy path (MEP) given a free energy landscape (FEL). Using this approximation as the initial guess for the MEP, followed by further refinement with the string method (referred to as the fast marching tree (FMT)-string combined approach), significantly reduces the number of iterations required for MEP convergence. This approach saves substantial time compared to using linear interpolation (LI) for the initial guess. Our method offers a viable solution for obtaining an effective initial guess of the MEP when an approximate or converged FEL is available. This work highlights the potential of applying FMT-based approaches to extract the MEP in chemical reactions.

Kinematic study of the orion complex: Analysing the young stellar clusters from big and small structures

Abstract In this work, we analysed young stellar clusters with spatial and kinematic coherence in the Orion star-forming complex. For this study, we selected a sample of pre-main sequence candidates using parallaxes, proper motions and positions on the colour-magnitude diagram. After applying a hierarchical clustering algorithm in the 5D parameter space provided by Gaia DR3, we divided the recovered clusters into two regimes: Big Structures and Small Structures, defined by the number of detected stars per cluster. In the first regime, we found 13 stellar groups distributed along the declination axis in the regions where there is a high density of stars. In the second regime, we recovered 34 clusters classified into two types: 14 as small groups completely independent from the larger structures, including four candidates of new clusters, and 12 classified as sub-structures embedded within five larger clusters. Additionally, radial velocity data from APOGEE-2 and GALAH DR3 was included to study the phase space in some regions of the Orion complex. From the Big Structure regime, we found evidence of a general expansion in the Orion OB1 association over a common centre, giving a clue about the dynamical effects the region is undergoing. Likewise, in the Small Structure regime, the projected kinematics shows the ballistic expansion in the λ Orionis association and the detection of likely events of clusters’ close encounters in the OB1 association.

Nighttime large-field video image change detection based on adaptive superpixel reconstruction and multi-scale singular value decomposition fusion

With the development of technology and the needs of social governance, surveillance equipment has been widely used. It is very mature to detect the change of surveillance video images in conventional scenes through video image change detection algorithms. However, in the large field of view environment at night, there are complex random noise and low signal-to-noise ratio in surveillance video images, which makes it difficult for people to find small moving targets. To this end, we propose a new method for nighttime large-field surveillance video image change detection based on adaptive superpixel reconstruction and multi-scale singular value decomposition fusion. The proposed method consists of two parts. On the one hand, an adaptive superpixel reconstruction method is used to reconstruct the two denoised difference images by selecting different segmentation parameters, and the edge information of the two reconstructed difference images is significantly enhanced. On the other hand, a multi-scale singular value decomposition fusion method is used to fuse the two difference images. The multi-scale singular value decomposition fusion obtains a robust difference image by selecting fusion rules at different scales and using the complementary information of different difference images, and the Fuzzy c-means (FCM) clustering algorithm is used to obtain the final changed image. Experimental results on a self-built nighttime large-field video image dataset with two resolutions show that the proposed method is superior to other algorithms in terms of detection accuracy and robustness.

Model‐based clustering in simple hypergraphs through a stochastic blockmodel

AbstractWe propose a model to address the overlooked problem of node clustering in simple hypergraphs. Simple hypergraphs are suitable when a node may not appear multiple times in the same hyperedge, such as in co‐authorship datasets. Our model generalizes the stochastic blockmodel for graphs and assumes the existence of latent node groups and hyperedges are conditionally independent given these groups. We first establish the generic identifiability of the model parameters. We then develop a variational approximation Expectation‐Maximization algorithm for parameter inference and node clustering, and derive a statistical criterion for model selection. To illustrate the performance of our R package HyperSBM, we compare it with other node clustering methods using synthetic data generated from the model, as well as from a line clustering experiment and a co‐authorship dataset.

Model-free detection and quantitative assessment of micro short circuits in lithium-ion battery packs based on incremental capacity and unsupervised clustering

Timely diagnosis of micro short circuit (MSC) faults is crucial for ensuring the safe operation of lithium-ion battery energy storage systems. Existing diagnostic methods face limitations such as high dependency on battery models, difficulty in determining accurate diagnostic thresholds, or low computational efficiency. This work presents a model-free approach for the detection and quantitative assessment of MSCs in lithium-ion battery packs, with incremental capacity (IC) and unsupervised clustering. First, the IC is extracted from charging voltage data to effectively characterize MSC faults in lithium-ion batteries. Next, principal component analysis is used to map the high-dimensional feature space onto a two-dimensional plane to facilitate fault detection and result visualization. Then, an unsupervised clustering algorithm is employed for anomaly detection to identify MSC cells within the battery pack. For the detected MSC cells, a method based on the maximum charging voltage difference between adjacent cycles is designed to estimate the MSC resistance, quantitatively assessing the severity and evolution stage of the MSC. Experimental results show that the accuracy of MSC detection is 99.17 % and the minimum relative error of short-circuit resistance estimation is 1.20 %, which demonstrates the effectiveness and feasibility of the proposed method.

Dynamic region growing approach for leaf-wood separation of individual trees based on geometric features and growing patterns

ABSTRACT The separation of leaf and wood points remains challenging due to the diversity of tree species and structures. We propose an automatic leaf-wood separation method from tree point clouds, leveraging trees’ shape information, growing patterns, and topological information for higher separation accuracy. First, the tree point clouds are roughly classified into initial planar, linear, and scattered points based on the dimensional structure of each point. Then, a slicing strategy combined with the DBSCAN (density-based spatial clustering of application with noise) clustering algorithm is used to exploit the potential wood clusters in each layer. A novel dynamic region growing algorithm based on an energy function is proposed for extracting tree trunk and large branches from initial planar points, incorporating the geometric features and growing patterns of trees. Finally, a novel inner-to-outer region growing method is proposed to extract the tiny branches based on voxel density and the principal direction. Twelve tree samples covering twelve species and locating tropical, temperate, and boreal areas are used to evaluate the method’s performance. The mean separation accuracy and kappa coefficient of the proposed method are 0.942 and 0.805, respectively. Experimental results indicate that the proposed method exhibits a strong ability to distinguish the wood and leaf points for various trees with different species and structures.

An Enhanced K-Means Clustering Algorithm for Phishing Attack Detections

Phishing attacks continue to pose a significant threat to cybersecurity, employing increasingly sophisticated techniques to deceive victims into revealing sensitive information or downloading malware. This paper presents a comprehensive study on the application of Machine Learning (ML) techniques for identifying phishing websites, with a focus on enhancing detection accuracy and efficiency. We propose an approach that integrates the CfsSubsetEval attribute evaluator with the K-Means Clustering algorithm to improve phishing detection capabilities. Our method was evaluated using datasets of varying sizes (2000, 7000, and 10,000 samples) from a publicly available repository. Simulation results demonstrate that our approach achieves an accuracy of 89.2% on the 2000-sample dataset, outperforming the traditional kernel K-Means algorithm, which achieved an accuracy of 51.5%. Further analysis using precision, recall, and F1-score metrics corroborates the effectiveness of our method. We also discuss the scalability and real-world applicability of our approach, addressing limitations and proposing future research directions. This study contributes to the ongoing efforts to develop robust, efficient, and adaptable phishing detection systems in the face of evolving cyber threats.

Development and validation of the Upstream Social Interaction Risk Scale (U-SIRS-13): a scale to assess threats to social connectedness among older adults.

Social interactions are essential to social connectedness among older adults. While many scales have been developed to measure various aspects of social connectedness, most are narrow in scope, which may not be optimally encompassing, practical, or relevant for use with older adults across clinical and community settings. Efforts are needed to create more sensitive scales that can identify "upstream risk," which may facilitate timey referral and/or intervention. The purposes of this study were to: (1) develop and validate a brief scale to measure threats to social connectedness among older adults in the context of their social interactions; and (2) offer practical scoring and implementation recommendations for utilization in research and practice contexts. A sequential process was used to develop the initial instrument used in this study, which was then methodologically reduced to create a brief 13-item scale. Relevant, existing scales and measures were identified and compiled, which were then critically assessed by a combination of research and practice experts to optimize the pool of relevant items that assess threats to social connectedness while reducing potential redundancies. Then, a national sample of 4,082 older adults ages 60 years and older completed a web-based questionnaire containing the initial 36 items about social connection. Several data analysis methods were applied to assess the underlying dimensionality of the data and construct measures of different factors related to risk, including item response theory (IRT) modeling, clustering techniques, and structural equation modeling (SEM). IRT modeling reduced the initial 36 items to create the 13-item Upstream Social Interaction Risk Scale (U-SIRS-13) with strong model fit. The dimensionality assessment using different clustering algorithms supported a 2-factor solution to classify risk. The SEM predicting highest risk items fit exceptionally well (RMSEA = 0.048; CFI = 0.954). For the 13-item scale, theta scores generated from IRT were strongly correlated with the summed count of items binarily identifying risk (r = 0.896, p < 0.001), thus supporting the use of practical scoring techniques for research and practice (Cronbach's alpha = 0.80). The U-SIRS-13 is a multidimensional scale with strong face, content, and construct validity. Findings support its practical utility to identify threats to social connectedness among older adults posed by limited physical opportunities for social interactions and lacking emotional fulfillment from social interactions.

A Toolpath Generator Based on Signed Distance Fields and Clustering Algorithms for Optimized Additive Manufacturing

Additive manufacturing (AM) methods have been gaining momentum because they provide vast design and fabrication possibilities, increasing the accessibility of state-of-the-art hardware through recent developments in user-friendly computer-aided drawing/engineering/manufacturing (CAD/CAE/CAM) tools. However, in comparison to the conventional manufacturing methods, AM processes have some disadvantages, including the machining precision and fabrication process times. The first issue has been mostly resolved through the recent advances in manufacturing hardware, sensors, and controller systems. However, the latter has been widely investigated by researchers with different toolpath planning perspectives. As a contribution to these investigations, the present study proposes a toolpath planning method for AM, which aims to provide highly continuous yet distance-optimized solutions. The approach is based on the utilization of the signed distance field (SDF), clustering, and minimization of toolpath distances among cluster centroids. The method was tested on various geometries with simple closed curves to complex geometries with holes, which provides effective toolpaths, e.g., with relative distance reduction percentages up to 16.5% in comparison to conventional rectilinear infill patterns.

Segmentation of Chinese consumer preference for wine extrinsic attributes based on stratification and weighted clustering algorithm

Chinese consumers are unfamiliar with the sensory attributes of wine and often pay more attention to the extrinsic attributes of wine that can most directly present information. Therefore, it is crucial to study consumer preferences for extrinsic attributes. This paper proposes a consumer segmentation method based on stratification and weighted clustering algorithm, leveraging data from an anonymous online survey (N = 3179). The AFR model is constructed based on the RFM model to segment wine consumers from the perspective of customer value. This model removes Monetary indicator and adds a new indicator Amount to eliminate multicollinearity caused by the Frequency and Monetary indicators of RFM model. In addition, factor analysis is used to assign weights to clustering indicators, addressing the problems of unequal weighting and strong correlation among the indicators. This allows for a simple, efficient, and precise segmentation of wine consumers at different levels. The method proposed in this article segments consumers into two layers and six categories: the potential layer includes product-oriented type, amorphous type, and cheap-fine type, while the mature layer comprises the rational type, reputation-price type and random type. This research will provide wine producers and distributors with a simple and efficient basis for production and marketing decision-making. Additionally, it can serve as a reference for consumer segmentation in food and other fields.

Identification and summarisation of events from Twitter using clustering algorithms and deep neural network

Identification and summarisation of events from Twitter using clustering algorithms and deep neural network

Using Entropy as the Convergence Criteria of Ant Colony Optimization and the Application at Gene Chip Data Analysis.

When Ant Colony Optimization algorithm (ACO) is adept at identifying the shortest path, the temporary solution is uncertain during the iterative process. All temporary solutions form a solution set. Where each solution is random. That is, the solution set has entropy. When the solution tends to be stable, the entropy also converges to a fixed value. Therefore, it was proposed in this paper that apply entropy as a convergence criterion of ACO. The advantage of the proposed criterion is that it approximates the optimal convergence time of the algorithm. In order to prove the superiority of the entropy convergence criterion, it was used to cluster gene chip data, which were sampled from patients of Alzheimer's Disease (AD). The clustering algorithm is compared with six typical clustering algorithms. The comparison shows that the ACO using entropy as a convergence criterion is of good quality. At the same time, applying the presented algorithm, we analyzed the clustering characteristics of genes related to energy metabolism and found that as AD occurs, the entropy of the energy metabolism system decreases; that is, the system disorder decreases significantly.

Integrated machine learning algorithms identify KIF15 as a potential prognostic biomarker and correlated with stemness in triple-negative breast cancer

Cancer stem cells (CSCs) have the potential to self-renew and induce cancer, which may contribute to a poor prognosis by enabling metastasis, recurrence, and therapy resistance. Hence, this study was performed to identify the association between CSC-related genes and triple-negative breast cancer (TNBC) development. Stemness gene sets were downloaded from StemChecker. Based on the online databases, a consensus clustering algorithm was conducted for unsupervised classification of TNBC samples. The variations between subtypes were assessed with regard to prognosis, tumor immune microenvironment (TIME), and chemotherapeutic sensitivity. The stemness-related gene signature was established and random survival forest analysis was employed to identify the core gene for validation experiments and tumor sphere formation assays. 499 patients with TNBC were classified into three subgroups and the Cluster 1 had a better OS than others. After that, WGCNA study was performed to identify genes important for Cluster 1 subtype. Out of all 8 modules, the subtype of Cluster 1 and the yellow module with 103 genes demonstrated the largest positive association. After that, a four-gene stemness-related signature was established. Based on the yellow module, the 39 potential pivotal genes were subjected to the random forest survival analysis to find out the gene that was relatively important for OS. KIF15 was confirmed as the targeted gene by LASSO and random survival forest analyses. In vitro experiments, the downregulation of KIF15 promoted the stemness of TNBC cells. The expression levels of stem cell markers Nanog, SOX2, and OCT4 were found to be elevated in TNBC cell lines after KIF15 inhibition. A stemness-associated risk model was constructed to forecast the clinical outcomes of TNBC patients. The downregulation of KIF15 expression in a subpopulation of TNBC stem cells may promote stemness and possibly TNBC progression.

Machine Learning Clustering Algorithm for Water Environmental Monitoring

Machine Learning Clustering Algorithm for Water Environmental Monitoring

A novel unsupervised adaptive density-based clustering filter for remaining useful life prediction of bearings

Abstract Constructing the health indicator (HI) and predicting the remaining useful life (RUL) are essential steps in bearing health management. Some prediction methods depend on prior information about HIs, especially when these indicators are generated by deep learning models. However, acquiring such prior information can be challenging in practical applications. This paper introduces a novel unsupervised adaptive density-based clustering filter (UADCF) for RUL prediction of bearings, which operates without the need for prior knowledge. Firstly, a post-hoc interpretation HI model (PIHIM) is proposed to characterize the deep learning constructed HIs from the perspective of what the deep learning has done. Then, leveraging the classical density-based clustering algorithm, we introduce the UADCF for unsupervised estimation of model parameters, which can dynamically adjust density parameters based on the current conditions. Finally, we develop a prediction framework combining PIHIM and UADCF, enabling unsupervised RUL prediction of bearings. The experimental studies validate the effectiveness of the proposed method.