Cluster Information Research Articles

GRESS: Grouping Belief-Based Deep Contrastive Subspace Clustering.

The self-expressive coefficient plays a crucial role in the self-expressiveness-based subspace clustering method. To enhance the precision of the self-expressive coefficient, we propose a novel deep subspace clustering method, named grouping belief-based deep contrastive subspace clustering (GRESS), which integrates the clustering information and higher-order relationship into the coefficient matrix. Specifically, we develop a deep contrastive subspace clustering module to enhance the learning of both self-expressive coefficients and cluster representations simultaneously. This approach enables the derivation of relatively noiseless self-expressive similarities and cluster-based similarities. To enable interaction between these two types of similarities, we propose a unique grouping belief-based affinity refinement module. This module leverages grouping belief to uncover the higher-order relationships within the similarity matrix, and integrates the well-designed noisy similarity suppression and similarity increment regularization to eliminate redundant connections while complete absent information. Extensive experimental results on four benchmark datasets validate the superiority of our proposed method GRESS over several state-of-the-art methods.

Predicting nuclear power plant operational parameters using clustering and mutual information for feature selection and Transformer neural network optimized by TPE

Predicting nuclear power plant operational parameters using clustering and mutual information for feature selection and Transformer neural network optimized by TPE

Deep Contrastive Survival Analysis with Dual-View Clustering

Survival analysis aims to analyze the relationship between covariates and events of interest, and is widely applied in multiple research fields, especially in clinical fields. Recently, some studies have attempted to discover potential sub-populations in survival data to assist in survival prediction with clustering. However, existing models that combine clustering with survival analysis face multiple challenges: incomplete representation caused by single-path encoders, the incomplete information of pseudo-samples, and misleading effects of boundary samples. To overcome these challenges, in this study, we propose a novel deep contrastive survival analysis model with dual-view clustering. Specifically, we design a Siamese autoencoder to construct latent spaces in two views and conduct dual-view clustering to more comprehensively capture patient representations. Moreover, we consider the dual views as mutual augmentations rather than introducing pseudo-samples and, based on this, triplet contrastive learning is proposed to fully utilize clustering information and dual-view representations to enhance survival prediction. Additionally, we employ a self-paced learning strategy in the dual-view clustering process to ensure the model handles samples from easy to hard in training, thereby avoiding the misleading effects of boundary samples. Our proposal achieves an average C-index and IBS of 0.6653 and 0.1786 on three widely used clinical datasets, both exceeding the existing best methods, which demonstrates its advanced discriminative and calibration performance.

Applications of cluster-based transfer learning in image and localization tasks

Transfer learning can address the issue of insufficient labels in machine learning. Using knowledge in a labeled domain (source domain) can assist in acquiring and learning knowledge in a domain (target domain) that lacks some or all labels. In this paper, we propose a new cluster-based semi-supervised transfer learning (CBSSTL) under a new assumption that samples in the target domain are unlabeled but contain cluster information. Furthermore, we propose a new transfer learning framework and a method for fine-tuning parameters. We tested and compared the proposed method with other unsupervised and semi-supervised transfer learning methods on well-known image datasets. The experimental results demonstrate the effectiveness of the proposed method. Additionally, we created a localization dataset for transfer learning. Finally, we tested and analyzed the proposed method on this dataset. Its particularly challenging nature makes it difficult for our method to work effectively.

R&D of the cluster finding algorithm for CMS iRPC detector

The Compact Muon Solenoid (CMS) experiment will undergo phase-II upgrade to enhance the capacity of detectors in the High-Luminosity Large Hadron Collider era. An important extension involves the installation of the Improved Resistive Plate Chambers (iRPC) in the most forward part of the endcap muon system. The iRPC detector addresses the efficiency drop experienced by the current CMS trigger system for single muon triggers in the high pseudorapidity region. It features a double-ended read-out method, allowing the determination of the hit position along the strip using the time difference between signals from both ends. This feature provides precise spatial information for clustering. To utilize this feature and integrate iRPC cluster information into the CMS trigger system, this paper proposes a 2-Dimensional (2D) cluster-finding algorithm. This algorithm provides the 2D coordinates to CMS trigger system, with each cluster being timestamped to reduce time ambiguity in endcap trajectory reconstruction. The proposed algorithm was implemented in the firmware of the iRPC Back-End Electronics and evaluated using a dedicated cosmic muon setup. The results show a position precision of 2.55 cm and an algorithm efficiency better than 99%, demonstrating the algorithm's potential to improve muon detection and trigger efficiency in the CMS endcap region.

Examining heterogeneity in dementia using data-driven unsupervised clustering of cognitive profiles.

Dementia is characterized by a decline in memory and thinking that is significant enough to impair function in activities of daily living. Patients seen in dementia specialty clinics are highly heterogenous with a variety of different symptoms that progress at different rates. Recent research has focused on finding data-driven subtypes for revealing new insights into dementia's underlying heterogeneity, rather than assuming that the cohort is homogenous. However, current studies on dementia subtyping have the following limitations: (i) focusing on AD-related dementia only and not examining heterogeneity within dementia as a whole, (ii) using only cross-sectional baseline visit information for clustering and (iii) predominantly relying on expensive imaging biomarkers as features for clustering. In this study, we seek to overcome such limitations, using a data-driven unsupervised clustering algorithm named SillyPutty, in combination with hierarchical clustering on cognitive assessment scores to estimate subtypes within a real-world clinical dementia cohort. We use a longitudinal patient data set for our clustering analysis, instead of relying only on baseline visits, allowing us to explore the ongoing temporal relationship between subtypes and disease progression over time. Results showed that subtypes with very mild or mild dementia were more heterogenous in their cognitive profiles and risk of disease progression.

Distance and Angle Insensitive Radar-Based Multi-Human Posture Recognition Using Deep Learning.

Human posture recognition has a wide range of applicability in the detective and preventive healthcare industry. Recognizing posture through frequency-modulated continuous wave (FMCW) radar poses a significant challenge as the human subject is static. Unlike existing radar-based studies, this study proposes a novel framework to extract the postures of two humans in close proximity using FMCW radar point cloud. With radar extracted range, velocity, and angle information, point clouds in the Cartesian domain are retrieved. Afterwards, unsupervised clustering is implemented to segregate the two humans, and finally a deep learning model named DenseNet is applied to classify the postures of both human subjects. Using four base postures (namely, standing, sitting on chair, sitting on floor, and lying down), ten posture combinations for two human scenarios are classified with an average accuracy of 96%. Additionally, using the centroid information of human clusters, an approach to detect and classify overlapping human participants is also introduced. Experiments with five posture combinations of two overlapping humans yielded an accuracy of above 96%. The proposed framework has the potential to offer a privacy-preserving preventive healthcare sensing platform for an elderly couple living alone.

Secondary halo bias through cosmic time II. Reconstructing halo properties using clustering information

When constructing mock galaxy catalogs based on suites of dark matter halo catalogs generated with approximated, calibrated, or machine-learning approaches, assigning intrinsic properties for these tracers is a step of paramount importance, given that they can shape the abundance and spatial distribution of mock galaxies and galaxy clusters. We explore the possibility of assigning properties of dark matter halos within the context of calibrated or learning approaches, explicitly using clustering information. The goal is to retrieve the correct signal of primary and secondary large-scale effective bias as a function of properties reconstructed solely based on phase-space properties of the halo distribution and dark matter density field. The algorithm reconstructs a set of halo properties (such as virial mass, maximum circular velocity, concentration, and spin) constrained to reproduce both primary and secondary (or assembly) bias. The key ingredients of the algorithm are the implementation of individually-assigned large-scale effective bias, a multi-scale approach to account for halo exclusion, and a hierarchical assignment of halo properties. The method facilitates the assignment of halo properties, aiming to replicate the large-scale effective bias, both primary and secondary. This constitutes an improvement over previous methods in the literature, especially for the high-mass end population. We have designed a strategy for reconstructing the main properties of dark matter halos obtained using calibrated or learning algorithms, such that the one- and two-point statistics (on large scales) replicate the signal from detailed $N$-body simulations. We encourage the application of this strategy (or the implementation of our algorithm) for the generation of mock catalogs of dark matter halos based on approximated methods.

Multi-level discriminator based contrastive learning for multiplex networks

Graph embedding is a technique for obtaining low-dimensional representations of nodes across diverse networks, which may then be used for various downstream tasks and applications. When it applies to heterogeneous networks, it is hard to handle heterogeneous networks because they usually contain different types of nodes and edges with more semantic and structural information. Recently, contrastive learning has developed as the preferred strategy for dealing with unsupervised heterogeneous graph embedding to reduce the cost of human label annotation. However, most multi-view contrastive learning approaches calculate the model’s loss only based on the mutual dependence between the node representation and graph representation. These approaches ignore that both node attributes and node clustering contain discriminative content. To solve this issue, we propose a model called Multi-Level Discriminator-based Contrastive Learning for Multiplex Networks (MLDCL). This model adopts a multi-level multi-discriminator-based approach that can simultaneously learn the global-level structural information, node-level attribute information, and local-level clustering information. Moreover, an augmentation strategy in the contrast learning process from the spectral domain is proposed to improve the representation and discriminative ability of MLDCL. Numerous tests with node clustering and classification tasks on widely used datasets demonstrate the efficacy of the proposed approach.

A data-driven regression model for predicting thermal plant performance under load fluctuations

The global energy demand is still primarily reliant on fossil-fueled thermal power plants. With the growing share of renewables, these plants must frequently adjust their loads. Maintaining, or ideally increasing operational efficiency under these conditions is crucial. Increasing the efficiency of such systems directly reduces associated greenhouse gas emissions, but it requires sophisticated models and monitoring systems. Data-driven models have proven their value here, as they can be used for monitoring, operational state estimation, and prediction. However, they are also sensitive to (1) the training approach, (2) the selected feature set, (3) and the algorithm used. Using operational data, we comprehensively investigate these model parameters for performance prediction in a thermal plant for process steam generation. Specifically, four regression algorithms are evaluated for the prediction of the highly fluctuating live steam flow with two training approaches and three feature subsets of the raw dataset. Furthermore, manual and automatic clustering methods are used to identify different states of operation regarding the fuel amounts used in the combustion chamber. Our results show that the live steam flow is predicted with excellent accuracy for a testing period of one month (R2=0.994 and NMAE=0.55%) when using a dynamic training approach and a comprehensive feature set comprised of 48 features representing the combustion process. It is also seen that the statically trained model predicts various load changes with strong accuracy and that the accuracy of the dynamically trained model can be approached by incorporating the cluster information into the static model. These models reflect the plant’s physical intricacies under varying loads, where deviations from the predicted live steam flow indicate unwanted long-term drifts. They can be directly implemented to help operators detect inefficiencies and optimize plant performance.

Effect of second-order network structure on link prediction

Small-degree nodes widely exist in real networks, causing the difficulty in link prediction for them due to the lack of information. The clustering information benefits the link prediction by introducing the network inner structure, however, the commonly discussed first-order clustering information is still insufficient for the link prediction of the small-degree nodes. In this article, we introduce the second-order network structure to complement information for the small-degree nodes. A general link prediction approach is proposed by incorporating the second-order clustering coefficient, and is employed to improve eight baseline algorithms. Experimental results show that all the baseline algorithms are remarkably improved. Compared with three advantageous similarity-based and two learning-based algorithms, an improved common neighbor method also shows an advantage in most cases. Further, an information gain between the first- and the second-order network structure is investigated, and the second-order network structure is found to also contain abundant information, which provides a possible understanding to the proposed approach. Our work may shed a new light on how network structure affects link prediction.

A Review of CiteSpace Visualisation and Analysis of High-Temperature Corrosion Inhibitors for Oil and Gas Fields

With the increasing global energy demand, the exploitation depth of oil and gas fields is gradually increasing. At the same time, importing many high-acid crude oil makes it increasingly heavy and inferior, and its acid value is constantly improving. This change has led to the increasingly severe corrosion problem of oil and gas field equipment, which has become an essential factor affecting the national economy and society's sustainable development. As an economical and practical anticorrosion measure, corrosion inhibitors play a crucial role in the anticorrosion of oil and gas field equipment. Through the research method of biorientation, retrieve the Web of Science database in 2008-2024 about oil and gas field high-temperature corrosion inhibitor research literature information, using CiteSpace measurement analysis software visual analysis in the literature keywords, publications, high citation frequency, cooperation and word clustering information change trend, analyze the research situation of oil and gas field in recent years, summarizes the research hotspot of oil field high-temperature corrosion inhibitor, prominent authors and institutions, reference relationship and development trend. The number of documents on high-temperature corrosion inhibitors in oil and gas fields is smaller, and the authors, institutions, and countries are not closely related. There is less research cooperation on high-temperature corrosion inhibitors in oil and gas fields, and more independent studies exist. China University of Petroleum has the first number of publications, and China is the country with the first number of publications. The study of mass spectrometry for corrosion inhibitors in oil and gas fields is prominent, while the literature on high-temperature corrosion inhibitors is rare.

Cultural heritage sports tourism design opportunities: a bibliometric analysis

The development of cultural heritage sports tourism requires collaboration from the government, communities around cultural heritage, academics, and stakeholders. The implementation of cultural heritage sports tourism has been carried out by many researchers around the world. This research was conducted to provide a review of cultural heritage tourism that has been carried out and to find out future research gaps related to cultural heritage sports tourism. Harzing's publish or perish software, Mendeley Desktop, and VosViewer were used to sort and identify gaps in this research. A total of 1069 articles from 2014 to 2024 from the Scopus, Web of Science, and PubMed databases were reviewed according to a predetermined review. The review included cluster information, impact factors, types of activities, research findings, and gaps for future research. The results showed that there were eight cluster groups in the resulting analysis with seven keywords that had a high impact factor. The keywords that have high impact factors are revisiting intention, digitalization, game-based learning, location-based applications, surveys, circular economy, and immersive technologies. The findings in this study are that the development of cultural heritage attractions needs to consider visitor expectations, the content presented, government involvement, and promotion. The development of cultural heritage sports tourism has great potential. Keywords: bibliometric analysis, sport tourism, cultural heritage, future research

Spatial planning of the Bueno Brandão (MG) municipality with emphasis on hydrographic sub-basins

Territorial planning must be carried out with the objective of organizing human activities so to promote sustainable development, reconciling human well-being with environmental preservation. In this context, this study was developed with an initial proposal for the spatial planning of the municipality of Bueno Brandão (MG), using the hydrographic sub-basins as environmental planning units. For this purpose, the Geographic Information System software QGIS was used to structure a database composed of hydrographic, altimetric information, municipal limits and spatial distribution of rural clusters and the urban area of the municipality. The Digital Elevation Model, obtained from the Shuttle Radar Topography Mission project, was also used. Google Earth images were used to verify that the areas of population concentration coincided with the limits of the sub-basins. The initial proposal for Bueno Brandão spatial planning resulted in the identification of 43 rural clusters and the delimitation of the urban area, distributed in 12 hydrographic sub-basins.

Robust self-supervised learning strategy to tackle the inherent sparsity in single-cell RNA-seq data.

Single-cell RNA sequencing (scRNA-seq) is a powerful tool for elucidating cellular heterogeneity and tissue function in various biological contexts. However, the sparsity in scRNA-seq data limits the accuracy of cell type annotation and transcriptomic analysis due to information loss. To address this limitation, we present scRobust, a robust self-supervised learning strategy to tackle the inherent sparsity of scRNA-seq data. Built upon the Transformer architecture, scRobust employs a novel self-supervised learning strategy comprising contrastive learning and gene expression prediction tasks. We demonstrated the effectiveness of scRobust using nine benchmarks, additional dropout scenarios, and combined datasets. scRobust outperformed recent methods in cell-type annotation tasks and generated cell embeddings that capture multi-faceted clustering information (e.g. cell types and HbA1c levels). In addition, cell embeddings of scRobust were useful for detecting specific marker genes related to drug tolerance stages. Furthermore, when we applied scRobust to scATAC-seq data, high-quality cell embedding vectors were generated. These results demonstrate the representational power of scRobust.

Node-to-node clustering asymptotic synchronized discrete stochastic neural networks in time and space with Bernoulli switching delay

The article proposes a new approach to synchronizing space–time discrete stochastic neural networks with random switching delays. This is achieved by employing a control in the boundary, which is based on node-to-node clustering and controlling theories. The design of the control in the boundary for synchronizing space–time discrete stochastic neural networks in the form of clusters is based on the establishment of several significant sequential inequalities and the creation of cluster information. Also, an executable computer algorithm has been developed to streamline the implementation of the findings presented in this paper. The current study represents a pioneering approach in considering spatial discrete factors, providing a solid foundation for future research and offering theoretical and practical guidance.

Deep time-series clustering via latent representation alignment

In practice, obtaining sufficient label information from a dataset is challenging. Consequently, various clustering methods have been studied to homogeneously group data without label information. Recently, deep clustering approaches that utilize deep neural networks have garnered considerable attention. However, time series data possess unique characteristics, including temporal relationships between observations in a sequence, which can decrease the performance of existing deep clustering methods when applied to time series. Despite this, few studies on deep clustering have addressed the characteristics of time series. Thus, we propose a novel approach for deep time-series clustering using topological information, enabling the capture of underlying temporal patterns to generate cluster-oriented representations. We address the topological information of a time series by introducing a novel loss function based on the eigendecomposition of representations in latent space. Through experiments on various time-series datasets, we demonstrate the efficacy of the proposed method in achieving superior clustering performance compared to state-of-the-art deep clustering methods. To the best of our knowledge, this is the first approach that utilizes topological information for deep time-series clustering.

Generalized load modeling approach considering multiple distributed generation integration

To solve the problem of node characteristic uncertainty caused by the connection of multiple distributed generations to the original load node, a new method for modeling the steady-state characteristics of generalized load nodes based on scene clustering was proposed. Scenario clustering takes into account three factors: wind farm output fluctuation, photovoltaic output fluctuation, and demand-side power load fluctuation, and extracts typical scenarios of generalized load data. According to the uncertainty change of node characteristics in different scenarios, the clustering data is segmented and refined, and its probability distribution is counted. Clustering information, probability information, and maximum value are used as three types of features of generalized load and are custom encoded as 12-dimensional feature vectors as neural network inputs. To improve the identification performance of generalized load features, the back propagation (BP) dichotomy neural network is used to build a unified model of node features. The simulation results show that the proposed method can not only model accurately but also introduce probability information through statistical data samples, which can provide an auxiliary reference for the prediction and regulation of generalized loads.

A survey on personalized document-level sentiment analysis

Personalized document-level sentiment analysis (PDSA) plays an important role in many real-world applications. So far, various deep learning models for PDSA have been proposed. However, there has been no systematic survey in this area. To address this issue, in this paper, we overview the existing methods of PDSA, and propose a novel two-dimensional PDSA taxonomy. Specifically, in the dimension of attribute usage type, PDSA works are divided into two groups: (1) user-based and (2) user and product-based models. In the dimension of attribute processing method, PDSA works are divided into two groups: (1) feature-based and (2) relation-based models. To fill in the research blank indicated by the taxonomy, we further propose an architecture named User Correlation Mining (UCM) for PDSA. Specifically, UCM contains two components, namely Similar User Cluster Module (SUCM) and Triple Attributes BERT Model (TABM). SUCM is responsible for user clustering, and TABM aims to classify the user’s sentiment based on the information of users, products, user clusters and user reviews. To evaluate the performances of the existing works as well as UCM, we conduct extensive experiments on three real-world datasets. The experiment results show that our proposed architecture UCM outperforms the other state-of-the-art methods.

Increasing parameter identifiability through clustered time-varying sensitivity analysis

Hydrological models are becoming progressively complex, leading to unclear internal model behavior, increasing uncertainty, and the risk of equifinality. Accordingly, our study provided a research framework based on global sensitivity analysis, aiming at unraveling the process-level behavior of high-complexity models, teasing out the main information, and ultimately exploiting its usage for model parameterization. The Distributed Hydrology-Soil-Vegetation Model implemented in a mountainous watershed was used. Results indicated that 5 soil parameters and 5 vegetation parameters were most important to control the streamflow responses, while their importance varied greatly throughout the simulation period. Four typical patterns of parameter importance corresponding to different watershed conditions (i.e., flood, short dry-to-wet, fast recession, and continuous dry periods) were successfully distinguished. Using this clustered information, parameters with short dominance times were more identifiable over the clusters (time periods) in which they were most important. The reduced posterior parameter space also slightly improved the model performance.