Hierarchical Clustering Approach Research Articles

VWCluster: Vector-valued optimal transport for network based clustering using multi-omics data in breast cancer.

In this paper, we present a network-based clustering method, called vector Wasserstein clustering (vWCluster), based on the vector-valued Wasserstein distance derived from optimal mass transport (OMT) theory. This approach allows for the natural integration of multi-layer representations of data in a given network from which one derives clusters via a hierarchical clustering approach. In this study, we applied the methodology to multi-omics data from the two largest breast cancer studies. The resultant clusters showed significantly different survival rates in Kaplan-Meier analysis in both datasets. CIBERSORT scores were compared among the identified clusters. Out of the 22 CIBERSORT immune cell types, 9 were commonly significantly different in both datasets, suggesting the difference of tumor immune microenvironment in the clusters. vWCluster can aggregate multi-omics data represented as a vectorial form in a network with multiple layers, taking into account the concordant effect of heterogeneous data, and further identify subgroups of tumors in terms of mortality.

A Novel COVID-19-Related Drug Discovery Approach Based on Non-Equidimensional Data Clustering.

The novel coronavirus disease (COVID-19) caused by severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) has spread all over the world. Since currently no effective antiviral treatment is available and those original inhibitors have no significant effect, the demand for the discovery of potential novel SARS-CoV-2 inhibitors has become more and more urgent. In view of the availability of the inhibitor-bound SARS-CoV-2 Mpro and PLpro crystal structure and a large amount of proteomics knowledge, we attempted using the existing coronavirus inhibitors to synthesize new ones, which combined the advantages of similar effective substructures for COVID-19 treatment. To achieve this, we first formulated this issue as a non-equidimensional inhibitor clustering and a following cluster center generating problem, where three essential challenges were carefully addressed, which are 1) how to define the distance between pairwise inhibitors with non-equidimensional molecular structure; 2) how to group inhibitors into clusters when the dimension is different; 3) how to generate the cluster center under this non-equidimensional condition. To be more specific, a novel matrix Kronecker product (p, m)-norm was first defined to induce the distance D p (A, B) between two inhibitors. Then, the hierarchical clustering approach was conducted to find similar inhibitors, and a novel iterative algorithm–based Kronecker product (p, m)-norm was designed to generate individual cluster centers as the drug candidates. Numerical experiments showed that the proposed methods can find novel drug candidates efficiently for COVID-19, which has provided valuable predictions for further biological evaluations.

Hierarchical autoclassification of cryo-EM samples and macromolecular energy landscape determination

Background and objectiveCryo-electron microscopy using single particle analysis is a powerful technique for obtaining 3D reconstructions of macromolecules in near native conditions. One of its major advances is its capacity to reveal conformations of dynamic molecular complexes. Most popular and successful current approaches to analyzing heterogeneous complexes are founded on Bayesian inference. However, these 3D classification methods require the tuning of specific parameters by the user and the use of complicated 3D re-classification procedures for samples affected by extensive heterogeneity. Thus, the success of these approaches highly depends on the user experience. We introduce a robust approach to identify many different conformations presented in a cryo-EM dataset based on Bayesian inference through Relion classification methods that does not require tuning of parameters and reclassification strategies. MethodsThe algorithm allows both 2D and 3D classification and is based on a hierarchical clustering approach that runs automatically without requiring typical inputs, such as the number of conformations present in the dataset or the required classification iterations. This approach is applied to robustly determine the energy landscapes of macromolecules. ResultsWe tested the performance of the methods proposed here using four different datasets, comprising structurally homogeneous and highly heterogeneous cases. In all cases, the approach provided excellent results. The routines are publicly available as part of the CryoMethods plugin included in the Scipion package. ConclusionsOur results show that the proposed method can be used to align and classify homogeneous and heterogeneous datasets without requiring previous alignment information or any prior knowledge about the number of co-existing conformations. The approach can be used for both 2D and 3D autoclassification and only requires an initial volume. In addition, the approach is robust to the “attractor” problem providing many different conformations/views for samples affected by extensive heterogeneity. The obtained 3D classes can render high resolution 3D structures, while the obtained energy landscapes can be used to determine structural trajectories.

Characterizing metro stations via urban function: Thematic evidence from transit-oriented development (TOD) in Hong Kong

The strategies using transit-oriented development (TOD) to optimize transportation sustainability have been implemented in many metropolitan areas and extended beyond the role of exclusively offering transit services. Research findings from existing literature have largely shown that metro station catchment areas can attract a substantial number of urban functions and human activities that lead metro stations to be vital and vibrant places of urban daily life. In this work, we propose a data-driven semantic framework to characterize metro stations through points of interest (POIs) in Hong Kong. The analytical results reveal four thematic topics of urban functions that are closely related to commercial, residential, tourism, and industrial activities. Given the implementation of a hierarchical clustering approach on these thematic topics, the similarities among different stations are investigated. In particular, metro stations in the same thematic group tend to be spatially concentrated, suggesting an evident geographical proximity relating to similar urban functions. Plus, results from the Multinomial Logit Model (MNLM) confirm that the surrounding built environment of metro stations has close relationships with the heterogeneity of urban functions. Ultimately, this study introduces alternative insights into the urban functional heterogeneity exhibited by metro station areas, and the practical implications for more targeted TOD strategies are discussed.

Picturing of the Lung Tumor Cellular Composition by Multispectral Flow Cytometry.

The lung tumor microenvironment plays a critical role in the tumorigenesis and metastasis of lung cancer, resulting from the crosstalk between cancer cells and microenvironmental cells. Therefore, comprehensive identification and characterization of cell populations in the complex lung structure is crucial for development of novel targeted anti-cancer therapies. Here, a hierarchical clustering approach with multispectral flow cytometry was established to delineate the cellular landscape of murine lungs under steady-state and cancer conditions. Fluorochromes were used multiple times to be able to measure 24 cell surface markers with only 13 detectors, yielding a broad picture for whole-lung phenotyping. Primary and metastatic murine lung tumor models were included to detect major cell populations in the lung, and to identify alterations to the distribution patterns in these models. In the primary tumor models, major altered populations included CD324+ epithelial cells, alveolar macrophages, dendritic cells, and blood and lymph endothelial cells. The number of fibroblasts, vascular smooth muscle cells, monocytes (Ly6C+ and Ly6C–) and neutrophils were elevated in metastatic models of lung cancer. Thus, the proposed clustering approach is a promising method to resolve cell populations from complex organs in detail even with basic flow cytometers.

From networked students centrality to student networks density: What really matters for student performance?

The impact of student networks on academic performance has gained importance as a research subject. In addition to well-known centrality measures (i.e., degree and closeness centralities), this study tests indices that received less attention to predict student performance. This set of measures allows for distinguishing the effects on performance of being connected, being located in advantageous position(s), being connected to central peers and being located within connected neighborhoods. Besides, studies on links between network density and student achievement are rare. This research investigates the combined impacts of student centrality and network density on academic performance. We asked 574 college students about their friendships, and drew the network from the collected information. We used the Exponential Random Graph Models to impute missing friendship ties. Then, we applied a hierarchical clustering approach that identified sub-communities within the student network and we computed the density within each sub-community to study density. Finally, we used hierarchical modeling to predict student performance, i.e., by centrality at the student level and by density at the network level. Results demonstrate a positive impact of the geodesic k-path and of the closeness centralities on GPA, together with a positive impact of cluster’s density on performance, which seems, however, bounded by a ceiling effect.

Data acquisition in large-scale wireless sensor networks using multiple mobile sinks: a hierarchical clustering approach

Data acquisition in large-scale wireless sensor networks using multiple mobile sinks: a hierarchical clustering approach

Theme trends and knowledge structure on health communication: Bibliometric analysis in PubMed database

Health communication is a new field focusing on the “powerful role” of human and media communication in health care services and health promotion. This study intends to explore the intellectual structure of knowledge in health communication literature using the co-word analysis technique. The applied descriptive-analytical method was used in this study to analyze the literature content with a hierarchical clustering approach. For data collection, the descriptors of the keyword “Health Communication” were searched in the medical subject heading (MeSH) in the PubMed database on November 18, 2021, for the period of 1959–2021. Data analysis and clustering were performed using SPSS software (version 20), RavarPremap software, Excell, Ucinet and VosViewer software. Data analysis indicates that scientific articles on communication health have experienced ascending growth pattern. Moreover, the findings on hierarchical clustering led to the formation of six subject clusters with the predominant subjects of " COVID-19 Pandemic, Health Education & Vaccine Hesitancy." The present study revealed a structural relationship among subject concepts in the clusters created with common features within each group. This study provided valuable insights into scientific communication patterns in health communication research produced in the PubMed database.

A Novel Soft Clustering Approach for Gene Expression Data

Gene expression data represents a condition matrix where each row represents the gene and the column shows the condition. Micro array used to detect gene expression in lab for thousands of gene at a time. Genes encode proteins which in turn will dictate the cell function. The production of messenger RNA along with processing the same are the two main stages involved in the process of gene expression. The biological networks complexity added with the volume of data containing imprecision and outliers increases the challenges in dealing with them. Clustering methods are hence essential to identify the patterns present in massive gene data. Many techniques involve hierarchical, partitioning, grid based, density based, model based and soft clustering approaches for dealing with the gene expression data. Understanding the gene regulation and other useful information from this data can be possible only through effective clustering algorithms. Though many methods are discussed in the literature, we concentrate on providing a soft clustering approach for analyzing the gene expression data. The population elements are grouped based on the fuzziness principle and a degree of membership is assigned to all the elements. An improved Fuzzy clustering by Local Approximation of Memberships (FLAME) is proposed in this work which overcomes the limitations of the other approaches while dealing with the non-linear relationships and provide better segregation of biological functions.

Markov random geometric graph, MRGG: A growth model for temporal dynamic networks

We introduce Markov Random Geometric Graphs (MRGGs), a growth model for temporal dynamic networks. It is based on a Markovian latent space dynamic: consecutive latent points are sampled on the Euclidean Sphere using an unknown Markov kernel; and two nodes are connected with a probability depending on a unknown function of their latent geodesic distance. More precisely, at each stamp-time k we add a latent point Xk sampled by jumping from the previous one Xk−1 in a direction chosen uniformly Yk and with a length rk drawn from an unknown distribution called the latitude function. The connection probabilities between each pair of nodes are equal to the envelope function of the distance between these two latent points. We provide theoretical guarantees for the non-parametric estimation of the latitude and the envelope functions. We propose an efficient algorithm that achieves those non-parametric estimation tasks based on an ad-hoc Hierarchical Agglomerative Clustering approach. As a by product, we show how MRGGs can be used to detect dependence structure in growing graphs and to solve link prediction problems.

Impact of COVID-19 on G20 countries: analysis of economic recession using data mining approaches

The G20 countries are the locomotives of economic growth, representing 64% of the global population and including 4.7 billion inhabitants. As a monetary and market value index, real gross domestic product (GDP) is affected by several factors and reflects the economic development of countries. This study aimed to reveal the hidden economic patterns of G20 countries, study the complexity of related economic factors, and analyze the economic reactions taken by policymakers during the coronavirus disease of 2019 (COVID-19) pandemic recession (2019–2020). In this respect, this study employed data-mining techniques of nonparametric classification tree and hierarchical clustering approaches to consider factors such as GDP/capita, industrial production, government spending, COVID-19 cases/population, patient recovery, COVID-19 death cases, number of hospital beds/1000 people, and percentage of the vaccinated population to identify clusters for G20 countries. The clustering approach can help policymakers measure economic indices in terms of the factors considered to identify the specific focus of influences on economic development. The results exhibited significant findings for the economic effects of the COVID-19 pandemic on G20 countries, splitting them into three clusters by sharing different measurements and patterns (harmonies and variances across G20 countries). A comprehensive statistical analysis was performed to analyze endogenous and exogenous factors. Similarly, the classification and regression tree method was applied to predict the associations between the response and independent factors to split the G-20 countries into different groups and analyze the economic recession. Variables such as GDP per capita and patient recovery of COVID-19 cases with values of $12,012 and 82.8%, respectively, were the most significant factors for clustering the G20 countries, with a correlation coefficient (R2) of 91.8%. The results and findings offer some crucial recommendations to handle pandemics in terms of the suggested economic systems by identifying the challenges that the G20 countries have experienced.

A Divisive Hierarchical Clustering Approach to Hyperspectral Band Selection

Band selection, considered as an effective dimensionality reduction technique for hyperspectral imagery (HSI), has become a hot topic for decades. Although various clustering-based methods have been applied to band selection, only a few studies explored the hierarchical structure among different spectral bands. And with regard to conventional hierarchical clustering, implemented in an agglomerative manner, both efficiency and accuracy of band selection still remain to rise. Moreover, the noise sensitivity is a defect inherent in the procedure of clustering. To address these issues, we propose a divisive hierarchical clustering approach (DHCA) to hyperspectral band selection. Inspired by divisive analysis, DHCA is designed to obtain any number of band subsets, which captures the intrinsic hierarchy of hyperspectral bands simultaneously. By introducing the local density into average dissimilarity, it can suppress the outliers clustering separately. Also, given the order of the spectrum, channel interval makes the similarity more rational among bands. Finally, we select a representative band in each cluster from the information viewpoint to ensure the band subset with a high quality. Extensive experiments on three real public HSI datasets fully validate the superiority of the proposed method against state-of-the-art competitors.

A QoS-Aware Machine Learning-Based Framework for AMI Applications in Smart Grids

The Internet of things (IoT) enables a diverse set of applications such as distribution automation, smart cities, wireless sensor networks, and advanced metering infrastructure (AMI). In smart grids (SGs), quality of service (QoS) and AMI traffic management need to be considered in the design of efficient AMI architectures. In this article, we propose a QoS-aware machine-learning-based framework for AMI applications in smart grids. Our proposed framework comprises a three-tier hierarchical architecture for AMI applications, a machine-learning-based hierarchical clustering approach, and a priority-based scheduling technique to ensure QoS in AMI applications in smart grids. We introduce a three-tier hierarchical architecture for AMI applications in smart grids to take advantage of IoT communication technologies and the cloud infrastructure. In this architecture, smart meters are deployed over a georeferenced area where the control center has remote access over the Internet to these network devices. More specifically, these devices can be digitally controlled and monitored using simple web interfaces such as REST APIs. We modify the existing K-means algorithm to construct a hierarchical clustering topology that employs Wi-SUN technology for bi-directional communication between smart meters and data concentrators. Further, we develop a queuing model in which different priorities are assigned to each item of the critical and normal AMI traffic based on its latency and packet size. The critical AMI traffic is scheduled first using priority-based scheduling while the normal traffic is scheduled with a first-in–first-out scheduling scheme to ensure the QoS requirements of both traffic classes in the smart grid network. The numerical results demonstrate that the target coverage and connectivity requirements of all smart meters are fulfilled with the least number of data concentrators in the design. Additionally, the numerical results show that the architectural cost is reduced, and the bottleneck problem of the data concentrator is eliminated. Furthermore, the performance of the proposed framework is evaluated and validated on the CloudSim simulator. The simulation results of our proposed framework show efficient performance in terms of CPU utilization compared to a traditional framework that uses single-hop communication from smart meters to data concentrators with a first-in–first-out scheduling scheme.

Differentiating movement styles in professional tennis: A machine learning and hierarchical clustering approach

ABSTRACT Purpose: Recent explorations of tennis-specific movements have developed contemporary methods for identifying and classifying changes of direction (COD) during match-play. The aim of this research was to employ these new analysis techniques to objectively explore individual nuance and style factors in the execution of COD movements in professional tennis. Methods: Player tracking data from 62 male and 77 female players at the Australian Open Grand Slam were analysed for COD movements using a model algorithm, with a sample of 150,000 direction changes identified. Hierarchical clustering methods were employed on the time-motion and degree characteristics of these direction changes to identify groups of different COD performers. Results: Five unique clusters, labelled “Cutters”, “Gear Changers”, “Lateral Changers”, “Balanced Changers” and “Passive Changers” were identified in accordance with their varying speed, acceleration, degree and directionality of change features. Conclusions: Player COD clustering challenge previously held assumptions regarding on-court movement style, highlighting the complexity and variation in the sport’s locomotion demands. In practice, the speed, acceleration, directionality and degree of change characteristics of each COD style can facilitate athlete profiling and the specificity of training interventions. Highlights We used machine learning techniques and cluster analysis methodology to explore the time motion characteristics of direction change skill in professional tennis. We present five unique types of change of direction style in professional tennis players. These include “Cutters”, “Gear Changers”, “Lateral Changers”, “Balanced Changers” & “Passive Changers”. These style classifications were established in accordance with their varying speed, acceleration, degree and directionality of change features. We show that the application of machine learning techniques to player tracking data can facilitate a more intricate understanding the sport’s physical demands, which can be used to inform training programme design.

Bayesian multistudy factor analysis for high-throughput biological data

This paper analyzes breast cancer gene expression across seven studies to identify genuine and thus replicable gene patterns shared among these studies. Our premise is that genuine biological signal is more likely to be reproducibly present in multiple studies than spurious signal. Our analysis uses a new modeling strategy for the joint analysis of high-throughput biological studies which simultaneously identifies shared as well as study-specific signal. To this end, we generalize the multi-study factor analysis model to handle high-dimensional data and generalize the sparse Bayesian infinite factor model to this context. We provide strategies for the identification of the loading matrices, common and study-specific. Through extensive simulation analysis, we characterize the performance of the proposed approach in various scenarios and show that it outperforms standard factor analysis in identifying replicable signal in all scenarios considered. The analysis of breast cancer gene expression studies identifies clear replicable gene patterns. These patterns are related to well-known biological pathways involved in breast cancer, such as the ER, cell cycle, immune system, collagen, and metabolic pathways. Some of these patterns are also associated with existing breast cancer subtypes, such as LumA, Her2, and basal subtypes, while other patterns identify novel pathways active across subtypes and missed by hierarchical clustering approaches. The R package MSFA implementing the method is available on GitHub.

Functional distributional clustering using spatio-temporal data

This paper presents a new method called the functional distributional clustering algorithm (FDCA) that seeks to identify spatially contiguous clusters and incorporate changes in temporal patterns across overcrowded networks. This method is motivated by a graph-based network composed of sensors arranged over space where recorded observations for each sensor represent a multi-modal distribution. The proposed method is fully non-parametric and generates clusters within an agglomerative hierarchical clustering approach based on a measure of distance that defines a cumulative distribution function over temporal changes for different locations in space. Traditional hierarchical clustering algorithms that are spatially adapted do not typically accommodate the temporal characteristics of the underlying data. The effectiveness of the FDCA is illustrated using an application to both empirical and simulated data from about 400 sensors in a 2.5 square miles network area in downtown San Francisco, California. The results demonstrate the superior ability of the the FDCA in identifying true clusters compared to functional only and distributional only algorithms and similar performance to a model-based clustering algorithm.

Mapping supply chain collaboration research: a machine learning-based literature review

ABSTRACT Supply chain collaboration has been widely discussed in the literature. With this maturity comes a plethora of heterogeneous research that is difficult to manage and navigate. This paper, therefore, applies a novel literature review approach based on text mining analyzing 10,556 articles to provide an overview of previous research themes and future directions of the field. The applied method enables researchers to systematically analyze and structure larger samples of research publications. It allocates articles to thematic clusters using a visual hierarchical clustering approach and subsequently aggregates them into nine overarching themes to determine potential research and insights for practice. Developments regarding research interest and attention within these themes are examined and journals publishing the most impactful articles are identified. The paper thus contributes to the field of Supply Chain Collaboration research by mapping its evolvement over the last five years and by deriving a research agenda for the next decade.

HydroBlocks v0.2: enabling a field-scale two-way coupling between the land surface and river networks in Earth system models

Abstract. Over the past decade, there has been appreciable progress towards modeling the water, energy, and carbon cycles at field scales (10–100 m) over continental to global extents in Earth system models (ESMs). One such approach, named HydroBlocks, accomplishes this task while maintaining computational efficiency via Hydrologic Response Units (HRUs), more commonly known as “tiles” in ESMs. In HydroBlocks, these HRUs are learned via a hierarchical clustering approach from available global high-resolution environmental data. However, until now there has yet to be a river routing approach that is able to leverage HydroBlocks' approach to modeling field-scale heterogeneity; bridging this gap will make it possible to more formally include riparian zone dynamics, irrigation from surface water, and interactive floodplains in the model. This paper introduces a novel dynamic river routing scheme in HydroBlocks that is intertwined with the modeled field-scale land surface heterogeneity. Each macroscale polygon (a generalization of the concept of macroscale grid cell) is assigned its own fine-scale river network that is derived from very high resolution (∼ 30 m) digital elevation models (DEMs); the inlet–outlet reaches of a domain's macroscale polygons are then linked to assemble a full domain's river network. The river dynamics are solved at the reach-level via the kinematic wave assumption of the Saint-Venant equations. Finally, a two-way coupling between each HRU and its corresponding fine-scale river reaches is established. To implement and test the novel approach, a 1.0∘ bounding box surrounding the Atmospheric Radiation and Measurement (ARM) Southern Great Plains (SGP) site in northern Oklahoma (United States) is used. The results show (1) the implementation of the two-way coupling between the land surface and the river network leads to appreciable differences in the simulated spatial heterogeneity of the surface energy balance, (2) a limited number of HRUs (∼ 300 per 0.25∘ cell) are required to approximate the fully distributed simulation adequately, and (3) the surface energy balance partitioning is sensitive to the river routing model parameters. The resulting routing scheme provides an effective and efficient path forward to enable a two-way coupling between the high-resolution river networks and state-of-the-art tiling schemes in ESMs.

Adaptive time window convolutional neural networks concerning multiple operation modes with applications in energy efficiency predictions

Energy efficiency prediction models promote the efficient uses of energy and low consumptions of raw materials. The Convolutional neural network (CNN) is one of the most effective deep learning networks for complex process modeling. However, when applied to real industrial processes, the performance of the CNN would be restricted by the change of operating conditions, such as swings in feedstock qualities, different manufacturing strategies and variations in product specifications. A globally invariant model is unable to adapt the time-varying conditions. Therefore, we proposed a multiple operation modes adaptive time window convolutional neural network (MOM-ATWCNN). Here, a hierarchical clustering approach is suggested to determine the numbers and locations of the modes. Then, an optimal length of time window is selected to match with each mode accordingly. Lastly, the improved deep learning model is used to extract the varying features hidden in different modes. To verify the effectiveness, the proposed method is compared to several typical deep learning models by the data collected from a real industrial atmospheric and vacuum distillation process. The results show that the energy prediction accuracy of the MOM-ATWCNN is 6.5%, 2.9% and 10.2% higher than those of the traditional CNN, LSTM, BPNN, respectively. Furthermore, the proposed method exhibit its superiority regarding various performance indexes. The improvement of the algorithm is beneficial to the reduction of energy consumptions thus achieving economic goals.

Automatic Segmentation to Cluster Patterns of Breathing in Sleep Apnea.

Annotation of polysomnography (PSG) recordings for diagnosis of obstructive sleep apnea (OSA) is a standard procedure but an expensive and time-consuming process for clinicians. To aid clinicians in this process we present a data driven unsupervised hierarchical clustering approach for detection and visual presentation of breathing patterns in PSG recordings. The aim was to develop a model independent of manual annotations to detect and visualize respiratory events related to OSA. 10 recordings from the Sleep Heart Health Study database were used, and the proposed algorithm was evaluated based on the manually annotated events for each recording. The algorithm reached an F1-score of 0.58 across the 10 recordings when detecting the presence of an event vs. no event and a 100% correct diagnosis prediction of OSA when predicting if apnea-hypopnea index (AHI) ≥ 15, which is a clinically meaningful cut-off. The F1-score may be due to imprecise placement of events, difficulty distinguishing between hypopneas and stable breathing, and variations in scoring. In conclusion the performance can be improved despite the strong agreement in diagnostics. The method is a proof of concept that a clustering method can detect and visualize breathing patterns related to OSA while maintaining a correct diagnosis.