Joint Clustering Research Articles

Staffing for digitalization processes in agriculture

The legal basis for cooperation between the regions of the Republic of Belarus and the provinces of the People’s Republic of China in the industrial sphere is disclosed. Major projects implemented in the regions and the city of Minsk with the participation of Chinese investors are presented. The branches of industry that have a high potential for the creation of Chinese-Belarusian industries, in the context of regions, have been identified. Prospective forms of interaction between enterprises of both countries are proposed, including industrial cooperation, joint research and development in the field of high technologies, the creation of scientific and technical cooperation centers, and the implementation of joint cluster initiatives.

Development and characterization of a mass cytometry panel for detecting the effect of acute doxorubicin exposure on murine cardiac nonmyocytes.

Childhood cancer survivors (CCSs) face lifelong side effects related to their treatment with chemotherapy. Anthracycline agents, such as doxorubicin (DOX), are important in the treatment of childhood cancers but are associated with cardiotoxicity. Cardiac toxicities represent a significant source of chronic disability that cancer survivors face; despite this, the chronic cardiotoxicity phenotype and how it relates to acute toxicity remains poorly defined. To address this critical knowledge gap, we studied the acute effect of DOX on murine cardiac nonmyocytes in vivo. Determination of the acute cellular effects of DOX on nonmyocytes, a cell pool with finite replicative capacity, provides a basis for understanding the pathogenesis of the chronic heart disease that CCSs face. To investigate the acute cellular effects of DOX, we present single-cell RNA sequencing (scRNAseq) data from homeostatic cardiac nonmyocytes and compare it with preexisting datasets, as well as a novel CyTOF datasets. SCANPY, a python-based single-cell analysis, was used to assess the heterogeneity of cells detected in scRNAseq and CyTOF. To further assist in CyTOF data annotation, joint analyses of scRNAseq and CyTOF data using an artificial neural network known as sparse autoencoder for clustering, imputation, and embedding (SAUCIE) are performed. Lastly, the panel is tested on a mouse model of acute DOX exposure at two time points (24 and 72 h) after the last dose of doxorubicin and examined with joint clustering. In sum, we report the first ever CyTOF study of cardiac nonmyocytes and characterize the effect of acute DOX exposure with scRNAseq and CyTOF.NEW & NOTEWORTHY We describe the first mass cytometry studies of murine cardiac nonmyocytes. The mass cytometry panel is compared with single-cell RNA sequencing data. Homeostatic cardiac nonmyocytes are characterized by mass cytometry to identify and quantify four major cell populations: endothelial cells, fibroblasts, leukocytes, and pericytes. The single-cell acute nonmyocyte response to doxorubicin is studied at 24 and 72 h after doxorubicin exposure given daily for 5 days at a dose of 4 mg/kg/day.

An approach to error label discrimination based on joint clustering

Inaccurate multi-label learning aims at dealing with multi-label data with wrong labels. Error labels in data sets usually result in cognitive bias for objects. To discriminate and correct wrong labels is a significant issue in multi-label learning. In this paper, a joint discrimination model based on fuzzy C-means (FCM) and possible C-means (PCM) is proposed to find wrong labels in data sets. In this model, the connection between samples and their labels is analyzed based on the assumption of consistence between samples and their labels. Samples and labels are clustered by considering this connection in the joint FCM-PCM clustering model. An inconsistence measure between a sample and its label is established to recognize wrong labels. A series of simulated experiments are comparatively implemented on several real multi-label data sets and experimental results show superior performance of the proposed model in comparison with two state of the art methods of mislabeling correction.

Intelligent Reflecting Surface Based Backscatter Communication for Data Offloading

This paper investigates intelligent reflecting surface based backscatter communication (IRS-BackCom), in order to realize computational task offloading of energy-constrained mobile edge computing network in a self-sustainable manner. Specifically, the system operation is divided into two phases. In the first one, the ambient signal energy from a power beacon (PB) either provides the energy supply of local computing and energy harvesting circuits, or flows into the energy storage, when reaching the IRS. In the second one, the stored energy is used to enable IRS-BackCom for partial computational data offloading and energize local computing circuit. Based on this, the maximization problem of sum computational bits is formulated. By jointly optimizing the beamforming vector at the PB, the backscatter matrix at the IRS, the time scheduling of two-phase process, as well as the time of local computing, sum computational bits are maximized. In addition, this paper proposes element clustering to realize BackCom, so as to reduce the control and computation complexity of IRS. According to different operating mechanisms, two cluster operation modes are considered, namely independent cluster operation mode and joint cluster operation mode. Simulation results demonstrate the achievable sum computational bits by the proposed IRS-BackCom schemes.

Joint Clustering and Power Allocation in Coordinated Multipoint Assisted C-NOMA Cellular Networks

We consider a wireless network consisting of two adjacent cells, where the joint transmission (JT) coordinated multipoint (CoMP) is established to assist the user equipments (UEs) located at the edge of each cell. In addition, full-duplex (FD) cooperative non-orthogonal-multiple-access (C-NOMA) is invoked within each cell to improve the data rates of the UEs and to assist those at the cell edge. The UEs are categorized into two groups, namely, cell-center UEs (<inline-formula> <tex-math notation="LaTeX">$CUs$ </tex-math></inline-formula>) and cell-edge UEs (<inline-formula> <tex-math notation="LaTeX">$EUs$ </tex-math></inline-formula>). The <inline-formula> <tex-math notation="LaTeX">$CUs$ </tex-math></inline-formula> are the UEs located around the center of each cell. Meanwhile, the <inline-formula> <tex-math notation="LaTeX">$EUs$ </tex-math></inline-formula> are the UEs located at the edge of each cell, where the JT-CoMP is applied since they have less distinctive received power from two cells. In this paper, a framework to jointly optimize the power control and the UEs clustering of CoMP-assisted FD C-NOMA system is formulated as an optimization problem to maximize the network sum-rate while guaranteeing the required quality-of-service of UEs. The formulated problem is a non-convex mixed-integer non-linear program that cannot be solved in a straightforward manner. To tackle this issue, the formulated problem is decomposed into an inner power allocation problem and an outer UEs clustering problem. For the inner problem, a computational-efficient solution is obtained. Meanwhile, the outer problem is reformulated as a one-to-one three-sided matching game. Then, a low-complexity near-optimal clustering algorithm is proposed. The simulation results demonstrate that 1) the optimality of the power control solution; 2) the CoMP-assisted FD C-NOMA has a superior performance compared to CoMP-assisted half-duplex (HD) C-NOMA and CoMP NOMA schemes for moderate values of self-interference. It has been also shown that the proposed solution achieves around 96.5&#x0025; of the average achievable network sum-rate of the optimal solution.

Single-cell transcriptomics reveals conserved cell identities and fibrogenic phenotypes in zebrafish and human liver.

The mechanisms underlying liver fibrosis are multifaceted and remain elusive with no approved antifibrotic treatments available. The adult zebrafish has been an underutilized tool to study liver fibrosis. We aimed to characterize the single‐cell transcriptome of the adult zebrafish liver to determine its utility as a model for studying liver fibrosis. We used single‐cell RNA sequencing (scRNA‐seq) of adult zebrafish liver to study the molecular and cellular dynamics at a single‐cell level. We performed a comparative analysis to scRNA‐seq of human liver with a focus on hepatic stellate cells (HSCs), the driver cells in liver fibrosis. scRNA‐seq reveals transcriptionally unique populations of hepatic cell types that comprise the zebrafish liver. Joint clustering with human liver scRNA‐seq data demonstrates high conservation of transcriptional profiles and human marker genes in zebrafish. Human and zebrafish HSCs show conservation of transcriptional profiles, and we uncover collectin subfamily member 11 (colec11) as a novel, conserved marker for zebrafish HSCs. To demonstrate the power of scRNA‐seq to study liver fibrosis using zebrafish, we performed scRNA‐seq on our zebrafish model of a pediatric liver disease with mutation in mannose phosphate isomerase (MPI) and characteristic early liver fibrosis. We found fibrosis signaling pathways and upstream regulators conserved across MPI‐depleted zebrafish and human HSCs. CellPhoneDB analysis of zebrafish transcriptome identified neuropilin 1 as a potential driver of liver fibrosis. Conclusion: This study establishes the first scRNA‐seq atlas of the adult zebrafish liver, highlights the high degree of similarity to human liver, and strengthens its value as a model to study liver fibrosis.

Ship images detection and classification based on convolutional neural network with multiple feature regions

In recent years, the maritime industry is developing rapidly, which poses great challenges for intelligent ship navigation systems to achieve accurate ship classification. To cope with this problem, a Recurrent Attention Convolutional Neural Network (RA-CNN) is proposed, which is fused with multiple feature regions for ship classification. The proposed model has three scale layers, each of which contains a classification network VGG-19 and a localisation head Attention Proposal Network (APN). First, the Scale Dependent Pooling algorithm is integrated with VGG-19 to reduce the impact of over-pooling and improve the classification performance of small ships. Second, the APN incorporates the Joint Clustering algorithm to generate multiple independent feature regions; thus, the whole model can make full use of the global information in ship recognition. In the meantime, the Feature Regions Optimisation method is designed to solve the overfitting problem and reduce the overlap rate of multiple feature regions. Finally, a novel loss function is defined to cross-train VGG-19 and APN, which accelerates the convergence process. The experimental results show that the classification accuracy of the authors’ proposed method reaches 90.2%, which has a 6% improvement over the baseline RA-CNN. Both classification accuracy and robustness are improved by a large margin compared to those of other compared models.

Research on Classification of Primary Liver Cancer Syndrome Based on Data Mining Technology.

This study is based on the analysis of the status quo of the research on liver cancer syndromes, starting with the clinical objective and true four-diagnosis information of TCM inpatients with primary liver cancer, using computer data mining technology to analyze and summarize the syndrome rules from the bottom to the top. Let the data itself show the essence of liver cancer syndrome. First, with the help of hierarchical cluster analysis, we can understand the general characteristics through the rough preliminary classification of the four-diagnosis information of liver cancer patients. Then, with the help of the emerging and mature hidden structure model analysis in recent years, through data modeling, the classification of common syndromes of liver cancer and the corresponding relationship with the four-diagnosis information are comprehensively analyzed. Finally, considering the inherent shortcomings of implicit structure and hierarchical clustering based on the assumption that there is a unique one-to-one correspondence between the four diagnostic information factors and the class (or hidden class) when classifying, we plan to use factor analysis and joint cluster analysis, as supplementary means to further explore the classification of liver cancer syndromes and the corresponding relationship with the four-diagnosis information.

Method for Joint Clustering in Graph and Correlation Spaces

Method for Joint Clustering in Graph and Correlation Spaces

Least-squares bilinear clustering of three-way data

A least-squares bilinear clustering framework for modelling three-way data, where each observation consists of an ordinary two-way matrix, is introduced. The method combines bilinear decompositions of the two-way matrices with clustering over observations. Different clusterings are defined for each part of the bilinear decomposition, which decomposes the matrix-valued observations into overall means, row margins, column margins and row–column interactions. Therefore up to four different classifications are defined jointly, one for each type of effect. The computational burden is greatly reduced by the orthogonality of the bilinear model, such that the joint clustering problem reduces to separate problems which can be handled independently. Three of these sub-problems are specific cases of k-means clustering; a special algorithm is formulated for the row–column interactions, which are displayed in clusterwise biplots. The method is illustrated via an empirical example and interpreting the interaction biplots are discussed. Supplemental materials for this paper are available online, which includes the dedicated R package, lsbclust.

Joint Clustering of Single-Cell Sequencing and Fluorescence In Situ Hybridization Data for Reconstructing Clonal Heterogeneity in Cancers.

Aneuploidy and whole genome duplication (WGD) events are common features of cancers associated with poor outcomes, but the ways they influence trajectories of clonal evolution are poorly understood. Phylogenetic methods for reconstructing clonal evolution from genomic data have proven a powerful tool for understanding how clonal evolution occurs in the process of cancer progression, but extant methods so far have limited the ability to resolve tumor evolution via ploidy changes. This limitation exists in part because single-cell DNA-sequencing (scSeq), which has been crucial to developing detailed profiles of clonal evolution, has difficulty in resolving ploidy changes and WGD. Multiplex interphase fluorescence in situ hybridization (miFISH) provides a more unambiguous signal of single-cell ploidy changes but it is limited to profiling small numbers of single markers. Here, we develop a joint clustering method to combine these two data sources with the goal of better resolving ploidy changes in tumor evolution. We develop a probabilistic framework to maximize the probability of latent variables given the pre-clustered datasets, which we optimize via Markov chain Monte Carlo sampling combined with linear regression. We validate the method by using simulated data derived from a glioblastoma (GBM) case profiled by both scSeq and miFISH. We further apply the method to two GBM cases with scSeq and miFISH data by reconstructing a phylogenetic tree from the joint clustering results, demonstrating their synergistic value in understanding how focal copy number changes and WGD events can collectively contribute to tumor progression.

Phylogenetic Relationships in Vendace and Least Cisco, and Their Distribution Areas in Western Eurasia

I conducted a population-genetic study of the Eurasian cisco complex in an area extending from the Baltic Sea to the East-Siberian Sea using 30 enzyme loci. The results indicate that the least cisco (Coregonus sardinella) populations from most rivers of the Kara, Laptev and East-Siberian sea basins are genetically fairly homogeneous, and that the cluster they form is different from the one for the vendace (C. albula) populations from the waterbodies of the Baltic and White seas (Nei's genetic distance (DN) = 0.076). The least cisco and vendace originated from two major phylogenetic lineages of the species occurring as the purest form in the above regions. As a result of the evolution and complex interactions among local populations within the two phylogenetic lineages of cisco at the various stages of Middle and Late Quaternary glaciations, most extant modern populations are hybrid in origin. For example, the Barents Sea populations and the easternmost population from the East-Siberian Sea basin (Kolyma River) emerged as a result of hybridization during the last colonization wave by the least cisco (East Siberian) along the Arctic coast upon cisco's interaction with local ciscoes in the west and east. The White and Kovzhskoye lake populations from the Caspian Sea basin, which form a joint cluster with them, are the hybrids of the local vendace and the descendants of the first wave of least cisco's (West Siberian) expansion to Europe. In this paper, I also discuss the most probable scenarios of cisco's colonization of the study area using paleolimnological reconstructions.

The intersectional impact of sex and social factors on subjective health: analysis of the Canadian longitudinal study on aging (CLSA)

BackgroundSelf-rated health (SRH) is a widely validated measure of the general health of older adults. Our aim was to understand what factors shape individual perceptions of health and, in particular, whether those perceptions vary for men and women and across social locations.MethodsWe used data from the Canadian Longitudinal Study on Aging (CLSA) of community-dwelling adults aged 45 to 85. SRH was measured via a standard single question. Multiple Poisson regression identified individual, behavioural, and social factors related to SRH. Intersections between sex, education, wealth, and rural/urban status, and individual and joint cluster effects on SRH were quantified using multilevel models.ResultsAfter adjustment for relevant confounders, women were 43% less likely to report poor SRH. The strongest cluster effect was for groupings by wealth (21%). When wealth clusters were subdivided by sex or education the overall effect on SRH reduced to 15%. The largest variation in SRH (13.6%) was observed for intersections of sex, wealth, and rural/urban status. In contrast, interactions between sex and social factors were not significant, demonstrating that the complex interplay of sex and social location was only revealed when intersectional methods were employed.ConclusionsSex and social factors affected older adults’ perceptions of health in complex ways that only became apparent when multilevel analyses were carried out. Utilizing intersectionality analysis is a novel and nuanced approach for disentangling explanations for subjective health outcomes.

Sc-compReg enables the comparison of gene regulatory networks between conditions using single-cell data

The comparison of gene regulatory networks between diseased versus healthy individuals or between two different treatments is an important scientific problem. Here, we propose sc-compReg as a method for the comparative analysis of gene expression regulatory networks between two conditions using single cell gene expression (scRNA-seq) and single cell chromatin accessibility data (scATAC-seq). Our software, sc-compReg, can be used as a stand-alone package that provides joint clustering and embedding of the cells from both scRNA-seq and scATAC-seq, and the construction of differential regulatory networks across two conditions. We apply the method to compare the gene regulatory networks of an individual with chronic lymphocytic leukemia (CLL) versus a healthy control. The analysis reveals a tumor-specific B cell subpopulation in the CLL patient and identifies TOX2 as a potential regulator of this subpopulation.

StrokeStrip

When creating freeform drawings, artists routinely employ clusters of overdrawn strokes to convey intended, aggregate curves. The ability to algorithmically fit these intended curves to their corresponding clusters is central to many applications that use artist drawings as inputs. However, while human observers effortlessly envision the intended curves given stroke clusters as input, existing fitting algorithms lack robustness and frequently fail when presented with input stroke clusters with non-trivial geometry or topology. We present StrokeStrip , a new and robust method for fitting intended curves to vector-format stroke clusters. Our method generates fitting outputs consistent with viewer expectations across a vast range of input stroke cluster configurations. We observe that viewers perceive stroke clusters as continuous, varying-width strips whose paths are described by the intended curves. An arc length parameterization of these strips defines a natural mapping from a strip to its path. We recast the curve fitting problem as one of parameterizing the cluster strokes using a joint 1D parameterization that is the restriction of the natural arc length parameterization of this strip to the strokes in the cluster. We simultaneously compute the joint cluster parameterization and implicitly reconstruct the a priori unknown strip geometry by solving a variational problem using a discrete-continuous optimization framework. We use this parameterization to compute parametric aggregate curves whose shape reflects the geometric properties of the cluster strokes at the corresponding isovalues. We demonstrate StrokeStrip outputs to be significantly better aligned with observer preferences compared to those of prior art; in a perceptual study, viewers preferred our fitting outputs by a factor of 12:1 compared to alternatives. We further validate our algorithmic choices via a range of ablation studies; extend our framework to raster data; and illustrate applications that benefit from the parameterizations produced.

DEVELOPMENT OF THE SYSTEM OF RISK CONTROL OF FINANCING OF JOINT CLUSTER PROJECTS

In today's environment, the problem of improving the risk control system for organizations participating in cluster projects remains relevant. This system is multi-layered and complex. There is a need to develop approaches to the development of such a monitoring system for the benefit of stakeholders in a joint cluster project. The authors present methodical approaches to improving control measures to identify and manage specific risks specific to working in a cluster environment, changes in legislation and the current economic situation. The structure of the multi-level system of monitoring cluster projects is presented, individual risks in cooperation and approaches to their evaluation are defined, methodical approaches for assessing counterparties are specified, taking into account the validity of the data, taking into account modern information technologies based on the software "Contour.Focus". The use of new mechanisms and controls reduces the negative impact of the risks of various cluster financing schemes in a remote economy.

Single base station positioning based on multipath parameter clustering in NLOS environment

This paper proposes a scattering area model for processing multipath parameters achieve single base station positioning. First of all, we construct a scattering area model based on the spatial layout of obstacles near the base station and then collect the multipath signals needed for positioning and extract parameters. Second, we use the joint clustering algorithm improved by k-means clustering and mean shift clustering algorithm to process the parameters and extract useful information. Third, the processed information is combined with the spatial layout information of the scattering area model to construct equations, and then the solving problem of equations is converted into a least-squares optimization problem. Finally, the Levenberg-Marquardt (LM) algorithm is used to solve the optimal solution and estimate the mobile target position. The simulation results show that the positioning algorithm in this paper can be used by a single base station to locate the target in an outdoor non-line-of-sight (NLOS) environment, and the accuracy is improved compared with the traditional positioning algorithm.

The cosmology dependence of galaxy clustering and lensing from a hybrid N-body–perturbation theory model

ABSTRACT We implement a model for the two-point statistics of biased tracers that combines dark matter dynamics from N-body simulations with an analytic Lagrangian bias expansion. Using Aemulus, a suite of N-body simulations built for emulation of cosmological observables, we emulate the cosmology dependence of these non-linear spectra from redshifts z = 0 to z = 2. We quantify the accuracy of our emulation procedure, which is sub-per cent at $k=1\, h \,{\rm Mpc}^{-1}$ for the redshifts probed by upcoming surveys and improves at higher redshifts. We demonstrate its ability to describe the statistics of complex tracer samples, including those with assembly bias and baryonic effects, reliably fitting the clustering and lensing statistics of such samples at redshift z ≃ 0.4 to scales of $k_{\rm max} \approx 0.6\, h\,\mathrm{Mpc}^{-1}$. We show that the emulator can be used for unbiased cosmological parameter inference in simulated joint clustering and galaxy–galaxy lensing analyses with data drawn from an independent N-body simulation. These results indicate that our emulator is a promising tool that can be readily applied to the analysis of current and upcoming data sets from galaxy surveys.

Learning deep discriminative representations with pseudo supervision for image clustering

Image clustering is a crucial but challenging task in machine learning and computer vision. Its performance highly depends on the quality of image feature representations. Recently, deep joint clustering which combines representation learning with clustering has presented a promising performance. However, existing joint methods suffer from two severe problems. That is, the learned representations lack discriminability especially for intricate images, and the performance often encounters a bottleneck due to the lack of supervision information. To address these problems, we propose a pseudo-supervised joint method for image clustering, i.e., Discriminative Pseudo Supervision Clustering (DPSC). Our key idea is to discover and utilize the pseudo supervision information to provide supervisory guidance for discriminative representation learning. With the aid of pseudo supervision, the representations can be continuously refined to facilitate inter-cluster separability and intra-cluster compactness, thereby leading to more discriminative representations and correctly separated clusters. To fully benefit from joint learning, we further introduce a self-evolution training algorithm to jointly optimize the DPSC model, in which the learned representations and clustering results boost each other progressively as more reliable pseudo supervision information is discovered during the iteration. Experimental results show that DPSC significantly outperforms state-of-the-art methods on various image datasets. Moreover, the learned feature representations generalize well across various algorithms.

Joint Clustering and Blockchain for Real-Time Information Security Transmission at the Crossroads in C-V2X Networks

The cellular vehicle-to-everything (C-V2X) networks support diverse kinds of services, such as traffic management, road safety, and sharing data. However, the safety issues cannot be ignored in the process of information transmission. In this article, a joint clustering and blockchain scheme is proposed for real-time information security transmission to prevent some vehicles from sending malicious messages to disrupt the traffic order at the crossroads in C-V2X networks. In this scheme, the dynamic stability of the cluster is maintained by updating the trust value of the vehicle nodes, which can improve the real time and accuracy of the information transmission. The modified Webster algorithm is presented to divert the traffic flow so as to reduce the traffic jams at the crossroads. Meanwhile, the blockchain technology is utilized to establish a vehicle trust management mechanism in C-V2X, which can avoid malicious tampering of vehicle information during information sharing and ensure the safety of vehicle information communication. The simulation results of the Veins simulation platform are provided to demonstrate the effectiveness of the proposed algorithm and verify that the proposed scheme can guarantee the security of real-time information transmission.