Cluster Analysis Algorithm Research Articles

INTELLIGENT EXTRACTION OF COMPLEXITY TYPES IN FRACTAL RESERVOIR AND ITS SIGNIFICANCE TO ESTIMATE TRANSPORT PROPERTY

Fractal pore structure exists widely in natural reservoir and dominates its transport property. For that, more and more effort is devoted to investigate the control mechanism on mass transfer in such a complex and multi-scale system. Apparently, effective characterization of the fractal structure is of fundamental importance. Although the newly emerged concept of complexity assembly clarified the complexity types and their assembly mechanism in a fractal system, equivalent extraction of the complexity types is the key for effective characterization. For these, we proposed a deep learning-based method to extract the original and behavioral complexity assembled in bed-packing fractal porous media for simplification and without loss of generality. In detail, the UNeXt network model was trained to obtain the independent connected regions of scaling objects with different scales, the edge detection and clustering analysis algorithms were employed to extract the number-size relationship between two successive scaling objects, and the unique inversion of fractal behavior was realized by taking the number-size model and fractal topography together. Consequently, an equivalent characterization method for fractal complex pore structure was developed based on the concept of complexity assembly. Our investigation provides a theoretical guidance and method reference for the quantitative characterization of fractal porous media that will guarantee the fundamental requirement for the accurate evaluation of the transport properties of natural reservoir.

A study on the administration of career guidance to college students in higher education based on mental health education assessment data

Abstract Currently, college students are facing severe employment challenges. To address this, this study uses mental health education assessment data to explore how to optimize the employment guidance and management of college students in order to enhance their employability and psychological adaptability. Decision tree algorithm and improved K-means clustering algorithm are used to analyze the mental health assessment data in depth. Data mining techniques were used to identify students’ employment tendencies and psychological characteristics so as to develop personalized employment guidance strategies. It was found that the accuracy and effectiveness of career guidance can be effectively enhanced through a data-driven approach. Specifically, the accuracy of predicting employment tendency using the decision tree model reaches 85%, while the application of the improved K-means algorithm for clustering analysis of students’ psychological characteristics enables more precise customization of employment guidance strategies. Comprehensive data analysis and psychological assessment can significantly improve the quality of employment guidance for college students. Colleges and universities should pay attention to the use of mental health assessment data, combined with data mining technology, to optimize career guidance and management, in order to help students better adapt to the workplace and enhance their employment competitiveness.

The reform and practice path of “curriculum civics” of medical specialties in colleges and universities on the integration of multiple data

Abstract In the context of the new era, reforming “curriculum and political thinking” in the medical specialty of colleges and universities is a key path to realizing the fundamental task of cultivating moral integrity. The study adopts a blended teaching mode, combines online and offline resources, and focuses on analyzing the learning behavior of medical students. The correlation between learning behavior and performance was analyzed by DH-Kmeans cluster analysis algorithm and Pearson’s correlation coefficient. The experimental data came from the online learning behaviors of students in the 2022-2023 academic year of T Medical College, and a total of 2426 data were collected. The results showed that learning behaviors were highly correlated with grades, especially the number of tasks completed, course video progress, and the number of chapter studies. In addition, the comparative analysis of teaching experiments showed that students in the experimental class were better than the control class regarding ideological values, learning attitudes and grades. The conclusion shows that the blended teaching mode effectively improves medical students’ learning effect and the quality of ideological education.

Development Status, Comparison and Inspiration of Integrated Circuit Virtual Simulation Teaching at Home and Abroad

Abstract The cultivation of higher vocational integrated circuit technology professionals requires a complete practical training teaching system and practical training conditions, especially integrated circuit layout design, production process, packaging and testing and other process personnel training needs to be completed in a real work scenario, the virtual simulation training is just for the integrated circuit professional education and teaching to provide support. This paper takes CNKI, SCI and EI databases as the research data source. It uses word frequency analysis and co-word analysis in statistical analysis to quantitatively analyze the development status of virtual simulation teaching of integrated circuits at home and abroad. And combined with the clustering analysis algorithm to explore the integration results of the keywords of integrated circuit virtual simulation teaching at home and overseas, and give the path to improve the high-quality development of integrated circuit virtual simulation teaching. It has been found that the domestic research related to IC virtual simulation teaching has improved by 80 times during 2000–2022, but the foreign research is 1.642 times higher than the domestic one. In addition, domestic and foreign countries are mainly focused on virtual simulation and innovative practice, respectively, and their word frequencies have reached 465 and 596 times respectively. Higher vocational colleges and universities need to optimize the teaching mode of industry-teaching integration, use virtual simulation technology to help students understand the knowledge related to integrated circuits, and provide technical support for improving the quality of talent training.

Psychophysiological state recognition of middle school students based on vibraimage technology and k-means cluster analysis algorithm

Psychophysiological state recognition of middle school students based on vibraimage technology and k-means cluster analysis algorithm

Big data analysis and application of library information resources

Abstract This study explores the application of extensive data analysis to library information resources, focusing on enhancing the efficiency of resource utilization and user satisfaction through personalized recommendation services. We employ cluster analysis algorithms, and least squares support vector machines to model library users’ borrowing behaviors. Additionally, we use the Apriori algorithm and collaborative filtering to recommend books effectively. This study’s experimental outcomes show a notable 11.36% increase in the index of network resource demand satisfaction, indicating a significant enhancement in the library’s ability to meet resource update demands. The adoption of big data analytics has been instrumental in advancing library information management and expanding extensive data services. The findings underscore the pivotal role of big data in enhancing the efficiency of information resource utilization and elevating user satisfaction, mainly through personalized recommendations.

Credit rating algorithm of corporate bonds based on Gaussian process mixture model and improved K-means

The primary challenge in credit analysis revolves around uncovering the correlation between repayment terms and yield to maturity, constituting the interest rate term structure-an essential model for corporate credit term evaluation. Presently, interest rate term structures are predominantly examined through economic theoretical models and quantitative models. However, predicting treasury bond yields remains a challenging task for both approaches. Leveraging the clustering analysis algorithm theory and the attributes of an insurance company’s customer database, this paper enhances the K-means clustering algorithm, specifically addressing the selection of initial cluster centers in extensive sample environments. Utilizing the robust data fitting and analytical capabilities of the Gaussian process mixture model, the study applies this methodology to model and forecast Treasury yields. Additionally, the research incorporates customer credit data from a property insurance company to investigate the application of clustering algorithms in the analysis of insurance customer credit.

Quality development of vocational education in the context of big data

Abstract Taking vocational education as an entry point, this paper utilizes factor analysis to deal with the problem of multicollinearity of vocational education indicators so that the synthesized factors are no longer correlated and lay a good foundation for vocational education cluster analysis. The distance measure and similarity coefficient describe the relationship between vocational education indicators. To increase computational efficiency and handle large and multidimensional data sets more effectively, the advantages of K-mean and grid clustering algorithms are combined to create the GBKM cluster analysis algorithm. Higher education institutions in Province H are chosen as representative samples in order to examine the variables influencing the development of high-quality vocational education, categorize the degree of that development, and forecast the trend of that development. The findings demonstrate that the GBKM cluster analysis algorithm’s accuracy difference between the predicted and actual data on the development trend of vocational education ranges from [0,0.1]. The algorithm’s absolute error value is 0.182, which falls within an acceptable error range and suggests that the algorithm proposed in this paper is capable of more accurately predicting the development trend of vocational education and may have some theoretical and practical implications for fostering high-quality development of vocational education. It has theoretical and practical implications for advancing the development of vocational education to a high standard.

Soft-orthogonal constrained dual-stream encoder with self-supervised clustering network for brain functional connectivity data

In many brain network studies, brain functional connectivity data is extracted from neuroimaging data and then used for disease prediction. For now, brain disease data not only has a small sample but also has the problem of high dimensional and nonlinear. Therefore, deep clustering on brain functional connectivity data is very challenging. To solve these problems, we propose a Soft-orthogonal Constrained Dual-stream Encoder with Self-supervised clustering network (SSCDE), which consists of a pretext task and downstream task, which can fully mine the effective information in brain disease data. In the pretext task, we use two brain disease data under the same category to do cross-domain learning to obtain effective information from the same dataset. In the downstream task, to reduce redundancy and avoid negative coding, we propose a soft-orthogonal constrained dual-stream encoder to encode features separately. At the same time, we use the pseudo labels given by the pretext task as prior information for self-supervised learning. We conduct validation on different brain disease recognition tasks, and the result have proved that the proposed framework has achieved good performance compared with the unsupervised clustering analysis algorithms. To our knowledge, this is the first cross-domain assisted recognition study on brain functional connectivity data. The code is available at https://github.com/hulu88/SSCDE.

Research on Classification of Huizhou Architectural Culture and Extraction of Cultural Characteristics of Villages Based on Cluster Analysis Algorithm

Abstract Based on the cluster analysis algorithm, this paper collects a large amount of sample data from Huizhou buildings and groups these samples using the cluster analysis algorithm so as to identify different categories of architectural culture types. By dividing the group similarity of each category of buildings, the village cultural characteristics related to each category of buildings are extracted, including information on architectural style, structural features, decorative elements and so on. The results show that the automatic cultural classification feature values are 1.2, 2.5, and 2.9, which highlight the unique characteristics of the Huizhou village culture. Especially in Hongcun and Pai Fang Lane buildings, the cultural features are more significant, with matrix classification degrees of 4.7 and 4.022, respectively, fully highlighting the cultural heritage of these buildings. In addition, the clustering analysis algorithm has only a 9.5% error rate, and the classification accuracies all exceed the high level of 0.9, showing its excellent performance in the extraction of various cultural features.

Improved Earthquake Clustering Using a Density-Adaptive DBSCAN Algorithm: An Example from Iran

Abstract DBSCAN is a widely used unsupervised machine learning algorithm for clustering and spatial data analysis. However, the accuracy of the algorithm is highly dependent on the selection of its hyperparameters, minimum samples (Smin), the minimum number of points required to form a cluster, and ϵ, the maximum distance between points. In this study, we propose a modification to the DBSCAN algorithm by introducing an event density map replacing Smin and ε. Through this method, we decrease the number of hyperparameters from two to one, N which represents the number of cells in the event density map, simplifying, and speeding up optimization. As a result, the optimization of the algorithm will be improved as the sole factor to consider is the size of each cell. In addition, the utilization of dynamic Smin will provide more effective clustering because it is better suited to regions that have a variable earthquake density. We used the Iranian earthquake catalog for testing the algorithm, and we compared the outcomes to the Mirzaei et al. (1998) model as a standard for evaluation. Because this algorithm allows for density contrasts between clusters, it can be a good indicator when studying the zonation of a new area. The findings were more consistent than those of other methods and may offer additional insight into the seismotectonic of Iran. Other than earthquake studies, this algorithm can be applied in multiple fields of science and engineering for clustering datasets with variable-density clusters.

Trends and hotspots related to traditional and modern approaches on acupuncture for stroke: A bibliometric and visualization analysis.

Acupuncture role in stroke treatment and post-stroke rehabilitation has garnered significant attention. However, there is a noticeable gap in bibliometric studies on this topic. Additionally, the precision and comprehensive methodology of cluster analysis remain underexplored. This research sought to introduce an innovative cluster analysis technique (called follower-leading clustering algorithm, FLCA) to evaluate global publications and trends related to acupuncture for stroke in the recent decade. Publications pertaining to acupuncture for stroke from 2013 to 2022 were sourced from the Web of Science Core Collection. For the assessment of publication attributes-including contributing countries/regions (e.g., US states, provinces, and major cities in China) in comparison to others, institutions, departments, authors, journals, and keywords-we employed bibliometric visualization tools combined with the FLCA algorithm. The analysis findings, inclusive of present research status, prospective trends, and 3 influential articles, were presented through bibliometrics with visualizations. We identified 1050 publications from 92 countries/regions. An initial gradual rise in publication numbers was observed until 2019, marking a pivotal juncture. Prominent contributors in research, based on criteria such as regions, institutions, departments, and authors, were Beijing (China), Beijing Univ Chinese Med (China), the Department of Rehabilitation Medicine, and Lidian Chen (Fujian). The journal "Evid.-based Complement Altern" emerged as the most productive. The FLCA algorithm was effectively employed for co-word and author collaboration analyses. Furthermore, we detail the prevailing research status, anticipated trends, and 3 standout articles via bibliometrics. Acupuncture for stroke presents a vast research avenue. It is imperative for scholars from various global regions and institutions to transcend academic boundaries to foster dialogue and cooperation. For forthcoming bibliometric investigations, the application of the FLCA algorithm for cluster analysis is advocated.

A study of innovations in legal governance with respect to the safety of artificial intelligence

Abstract This paper aims to promote the safe development of artificial intelligence and improve legal policies. Combined with the cluster analysis algorithm, it analyzes the safety risks as well as legal defects of artificial intelligence. The Laplace matrix is derived using the similarity matrix, and the feature vector space is constructed by analyzing the associated features of artificial intelligence safety. Combining the spectral clustering algorithm, legal assessment indexes for artificial intelligence safety were constructed. The modular metric value method is utilized to assess the clustering effect of laws on the safety of artificial intelligence. Analyzing the security risks of artificial intelligence, improved legal policies are proposed from the perspective of technology and privacy. The results show that the effect of improving privacy protection policy on privacy protection is 0.85, and the effect of clarifying subject rights is 0.9. The introduction of laws should consider social ethics, and the effect degree of ethical principles is 0.75. Clarifying subject rights can help avoid technological risks to a certain extent, and improving privacy protection policies can help protect users’ privacy.

Distributed Power Grid Connected Panoramic Perception Technology Based on Digital Twin Model

Abstract To address the issue that large-scale distributed Proton-exchange membrane fuel cell grid-connected operation status is difficult to effectively monitor, this study carried out clustering screening of Proton-exchange membrane fuel cell grid connected status variables. The digital twin model of the Proton-exchange membrane fuel cell group grid connection is established by using key important variables, and the digital model accurately reflects the real-time operation status of the Proton-exchange membrane fuel cell. Then, it predicts the operation status of the Proton-exchange membrane fuel cell. The experiment showcases that the optimal accuracy of fuzzy C-means clustering algorithm, K-means clustering algorithm and fuzzy C-means clustering algorithm in view of the objective function for clustering screening of grid-connected state quantity of Proton-exchange membrane fuel cell is 0.74, 0.65 and 0.59 respectively; The optimal recall rates are 0.84, 0.76, and 0.68, respectively; The optimal F-measure values are 0.78, 0.70, and 0.64, respectively. Among the three clustering analysis algorithms, the fuzzy C-means clustering algorithm, in view of the objective function, has the shortest running time and the least memory consumption. The monitoring results are basically consistent with the actual situation, indicating that this design method can complete the task of monitoring the operating status of distributed power grid-connected equipment. This study’s proposed method is more accurate than conventional methods and is better suited for monitoring the grid connection status of distributed power systems.

An air combat maneuver pattern extraction based on time series segmentation and clustering analysis

Target maneuver recognition is a prerequisite for air combat situation awareness, trajectory prediction, threat assessment and maneuver decision. To get rid of the dependence of the current target maneuver recognition method on empirical criteria and sample data, and automatically and adaptively complete the task of extracting the target maneuver pattern, in this paper, an air combat maneuver pattern extraction based on time series segmentation and clustering analysis is proposed by combining autoencoder, G-G clustering algorithm and the selective ensemble clustering analysis algorithm. Firstly, the autoencoder is used to extract key features of maneuvering trajectory to remove the impacts of redundant variables and reduce the data dimension; Then, taking the time information into account, the segmentation of Maneuver characteristic time series is realized with the improved FSTS-AEGG algorithm, and a large number of maneuver primitives are extracted; Finally, the maneuver primitives are grouped into some categories by using the selective ensemble multiple time series clustering algorithm, which can prove that each class represents a maneuver action. The maneuver pattern extraction method is applied to small scale air combat trajectory and can recognize and correctly partition at least 71.3% of maneuver actions，indicating that the method is effective and satisfies the requirements for engineering accuracy. In addition, this method can provide data support for various target maneuvering recognition methods proposed in the literature, greatly reduce the workload and improve the recognition accuracy.

Surface analysis insight note: An example of a cluster analysis of spectra from an X‐ray photoelectron spectroscopy image

Identification of similar and dissimilar spectra is an important part of analyzing X‐ray photoelectron spectroscopy (XPS) images. Cluster analysis (CA) is a commonly used exploratory data analysis (EDA) method that groups similar spectra in a data set. CA can be performed in either an agglomerative fashion, for example, using Ward's method, which involves successively linking together/clustering the most similar spectra in a data set, or in a divisive fashion, for example, using the K‐means approach, which involves partitioning all the data into a specified number of clusters. In this note, we show the application of CA to an XPS image dataset. The use of Ward's method identified two major clusters in the image, where one of the clusters appeared as two subclusters. The K‐means image based on two clusters agrees well with previous analyses of the same image. The average spectra corresponding to clusters helped confirm the assignments made by the CA algorithms, as did a multivariate curve resolution (MCR) analysis of the interior region identified in our cluster analysis. “Elbow” plots can help determine the number of clusters to keep in K‐means clustering. The combination of the agglomerative and divisive forms of CA, where the first informs the second, can be effective in revealing the structures of XPS image datasets. The Procrustean bed is a metaphor for overfitting and underfitting in EDA.

Identification of necroptosis-related features in diabetic nephropathy and analysis of their immune microenvironent and inflammatory response.

Background: Diabetic nephropathy (DN) was considered a severe microvascular complication of diabetes, which was recognized as the second leading cause of end-stage renal diseases. Therefore, identifying several effective biomarkers and models to diagnosis and subtype DN is imminent. Necroptosis, a distinct form of programmed cell death, has been established to play a critical role in various inflammatory diseases. Herein, we described the novel landscape of necroptosis in DN and exploit a powerful necroptosis-mediated model for the diagnosis of DN. Methods: We obtained three datasets (GSE96804, GSE30122, and GSE30528) from the Gene Expression Omnibus (GEO) database and necroptosis-related genes (NRGs) from the GeneCards website. Via differential expression analysis and machine learning, significant NRGs were identified. And different necroptosis-related DN subtypes were divided using consensus cluster analysis. The principal component analysis (PCA) algorithm was utilized to calculate the necroptosis score. Finally, the logistic multivariate analysis were performed to construct the necroptosis-mediated diagnostic model for DN. Results: According to several public transcriptomic datasets in GEO, we obtained eight significant necroptosis-related regulators in the occurrence and progress of DN, including CFLAR, FMR1, GSDMD, IKBKB, MAP3K7, NFKBIA, PTGES3, and SFTPA1 via diversified machine learning methods. Subsequently, employing consensus cluster analysis and PCA algorithm, the DN samples in our training set were stratified into two diverse necroptosis-related subtypes based on our eight regulators' expression levels. These subtypes exhibited varying necroptosis scores. Then, we used various functional enrichment analysis and immune infiltration analysis to explore the biological background, immune landscape and inflammatory status of the above subtypes. Finally, a necroptosis-mediated diagnostic model was exploited based on the two subtypes and validated in several external verification datasets. Moreover, the expression level of our eight regulators were verified in the singe-cell level and glomerulus samples. And we further explored the relationship between the expression of eight regulators and the kidney function of DN. Conclusion: In summary, our necroptosis scoring model and necroptosis-mediated diagnostic model fill in the blank of the relationship between necroptosis and DN in the field of bioinformatics, which may provide novel diagnostic insights and therapy strategies for DN.

Retracted: Cluster Analysis Algorithm in the Analysis of College Students’ Mental Health Education

Retracted: Cluster Analysis Algorithm in the Analysis of College Students’ Mental Health Education

Information-based theory of psychological education and the penetration of college Civics courses in student teaching

Abstract This paper first elaborates on the relationship between psychological education and Civics courses and proposes a three-dimensional evaluation system to comprehend the teaching invention of psychological education and Civics classrooms in colleges. Then, based on information theory, the quantitative evaluation model of psychological education and Civics course effectiveness based on a cluster analysis algorithm is proposed. The data of indicators with high correlation are fused according to the cluster analysis algorithm, and the categories of evaluation indicators of sub-series are divided by the essential factors after clustering, while the automatic evaluation model is constructed by using the factor score coefficients under different categories to realize the evaluation of psychological education and Civics course, followed by an application analysis of psychological education and Civics based on information theory. The findings demonstrated that accuracy was higher when conducting course evaluation in the automated assessment model of psychological education and civics according to the cluster analysis algorithm, and time consumption was lower. Legal expertise, moral character, political behavior, view on life, values, and patriotism had substantial negative correlations with sadness and anxiety and significant positive correlations with subjective well-being in the correlation study.

Quantifying the phase assemblage in the hydrated cement paste by an interpretable and automatic EDS image analysis framework

The Energy dispersive X-ray spectroscopy (EDS) data, characterized by high dimensionality, low resolution, and large scale, necessitates a robust characterization method that is both easy to understand and delicate to reveal the underlying information. Here, we present a practical and interpretable framework for quantitative EDS (QEDS) image analysis. To improve the quality of data, we employ sequential processing techniques including guided filter, linear enhancement, and super-pixel segmentation. For phase identification and classification, the dimensionality reduction algorithm Potential of heat-diffusion for affinity-based transition embedding (Phate) was integrated with cluster analysis algorithm Gaussian Mixture Model (GMM). This integration cleanly and clearly reveals typical data patterns such as linear progressions and local clusters, indicating the presence of phase evolution and representative phases. We expect that this QEDS image analysis offers an intuitive and visual way to quantify the phase assemblage in cementitious systems, thereby shifting the quantification process from expert knowledge-dominated “black boxes” into data structure-dominated “glass boxes”.