Explore the vast range of titles available.

Spatial cluster analysis is a uniquely interdisciplinary endeavour, and so it is important to communicate and disseminate ideas, innovations, best practices and challenges across practitioners, applied epidemiology researchers and spatial statisticians. In this research we conducted a scoping review to systematically search peer-reviewed journal databases for research that has employed spatial cluster analysis methods on individual-level, address location, or x and y coordinate derived data. To illustrate the thematic issues raised by our results, methods were tested using a dataset where known clusters existed. Point pattern methods, spatial clustering and cluster detection tests, and a locally weighted spatial regression model were most commonly used for individual-level, address location data (n = 29). The spatial scan statistic was the most popular method for address location data (n = 19). Six themes were identified relating to the application of spatial cluster analysis methods and subsequent analyses, which we recommend researchers to consider; exploratory analysis, visualization, spatial resolution, aetiology, scale and spatial weights. It is our intention that researchers seeking direction for using spatial cluster analysis methods, consider the caveats and strengths of each approach, but also explore the numerous other methods available for this type of analysis. Applied spatial epidemiology researchers and practitioners should give special consideration to applying multiple tests to a dataset. Future research should focus on developing frameworks for selecting appropriate methods and the corresponding spatial weighting schemes.

This paper introduces a novel clustering approach that enhances the traditional Density‐Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm by integrating a grid search method and Nash Equilibrium principles and addresses the limitations of DBSCAN parameterization, particularly its inefficiency with big data. The use of Nash equilibrium allows the identification of clusters with different densities and the determination of DBSCAN parameters and the selection of cells from the network, and significantly improves the efficiency and accuracy of the clustering process. The proposed method divides data into grid cells, applies DBSCAN to each cell, and then merges smaller clusters, capitalizing on dynamic parameter calculation and reduced computational complexity. The performance of the proposed method was assessed over 3 big‐size and 11 middle‐size datasets. The achieved results implied the superiority of the proposed method to DBSCAN, ST‐DBSCAN, P‐DBSCAN, GCBD, and CAGS methods in terms of clustering accuracy (purity) and processing time. It proposes an enhanced method combining the density‐based spatial clustering of applications with noise (DBSCAN) with a dynamic approach and Nash equilibrium to improve efficiency and accuracy.

Semantic segmentation of large unstructured 3D point clouds is important problem for 3D object recognition which in turn is essential to solving more complex tasks such as scene understanding. The problem is highly challenging owing to large scale of data, varying point density and localization errors of 3D points. Nevertheless, with recent successes of deep neural network architectures to solve complex 2D perceptual problems, several researchers have shown interest to translate the developed 2D networks to 3D point cloud segmentation by a prior voxelization step for an explicit neighborhood representation. However, such a 3D grid representation loses the fine details and inherent structure due to quantization artifacts. For this purpose, this paper proposes an approach to performing semantic segmentation of 3D point clouds by exploiting the idea of super-point based graph construction. The proposed architecture is composed of two cascaded modules including a light-weight representation learning module which uses unsupervised geometric grouping to partition the large-scale unstructured 3D point cloud and a deep context aware sequential network based on long short memory units and graph convolutions with embedding residual learning for semantic segmentation. The proposed model is evaluated on two standard benchmark datasets and achieves competitive performance with the existing state-of-the-art datasets. The code and the obtained results have been made public at https://github.com/saba155/DCARN .

The network real-time kinematic (RTK) technique can provide centimeter-level real time positioning solutions and play a key role in geo-spatial infrastructure. With ever-increasing popularity, network RTK systems will face issues in the support of large numbers of concurrent users. In the past, high-precision positioning services were oriented towards professionals and only supported a few concurrent users. Currently, precise positioning provides a spatial foundation for artificial intelligence (AI), and countless smart devices (autonomous cars, unmanned aerial-vehicles (UAVs), robotic equipment, etc.) require precise positioning services. Therefore, the development of approaches to support large-scale network RTK systems is urgent. In this study, we proposed a self-organizing spatial clustering (SOSC) approach which automatically clusters online users to reduce the computational load on the network RTK system server side. The experimental results indicate that both the SOSC algorithm and the grid algorithm can reduce the computational load efficiently, while the SOSC algorithm gives a more elastic and adaptive clustering solution with different datasets. The SOSC algorithm determines the cluster number and the mean distance to cluster center (MDTCC) according to the data set, while the grid approaches are all predefined. The side-effects of clustering algorithms on the user side are analyzed with real global navigation satellite system (GNSS) data sets. The experimental results indicate that 10 km can be safely used as the cluster radius threshold for the SOSC algorithm without significantly reducing the positioning precision and reliability on the user side.

Background & objectives: Malaria infects around 216 million people annually with estimated 445,000 deaths globally. Anopheles culicifacies is the vector of malaria in Sri Lanka, a complex of five morphologically identical sibling species of which precise identification using DNA-based methods is still under experimentation. This study was carried out in Sri Lanka to observe the utility of BCE-PCR assay based on mitochondrial Cytochrome Oxidase II (COII) developed in India, in sibling species B and E identification in Sri Lanka, to characterize nucleotide and corresponding amino acid sequences of COII region in major vector sibling species E in Sri Lanka and to analyze the spatial distribution pattern of sibling species E in Sri Lanka using microsatellite markers. Methods: BCE-PCR was carried out for the samples to identify their sibling status. Sequencing of COII region was then carried out to investigate the genetic diversity of Sri Lankan sibling species E, sequences were aligned and compared; microsatellite genotyping was carried out and the spatial clustering pattern was analyzed. Results: Identification of sibling species B and E using BCE-PCR was confusing due to the heterogeneity in the COII region of sibling species in Sri Lanka. Non-synonymous substitutions were detected in COII gene amongst sibling species E. Spatial distributed two clusters were detected in the studied population. Interpretation & conclusion: Existence of genetic variants among sibling species is suggested in Sri Lanka. Further, the pattern of sibling species identification in BCE-PCR was reflected in the spatial clustering of sibling E in Sri Lanka.

Optimal integration of transcriptomics data and associated spatial information is essential towards fully exploiting spatial transcriptomics to dissect tissue heterogeneity and map out inter-cellular communications. We present SEDR, which uses a deep autoencoder coupled with a masked self-supervised learning mechanism to construct a low-dimensional latent representation of gene expression, which is then simultaneously embedded with the corresponding spatial information through a variational graph autoencoder. SEDR achieved higher clustering performance on manually annotated 10 × Visium datasets and better scalability on high-resolution spatial transcriptomics datasets than existing methods. Additionally, we show SEDR’s ability to impute and denoise gene expression (URL: https://github.com/JinmiaoChenLab/SEDR/ ).

Monitoring the structure of forest stands is of high importance for forest managers to help them in maintaining ecosystem services. For that purpose, Unmanned Aerial Vehicles (UAVs) open new prospects, especially in combination with Light Detection and Ranging (LiDAR) technology. Indeed, the shorter distance from the Earth’s surface significantly increases the point density beneath the canopy, thus offering new possibilities for the extraction of the underlying semantics. For example, tree stems can now be captured with sufficient detail, which is a gateway to accurately locating trees and directly retrieving metrics—e.g., the Diameter at Breast Height (DBH). Current practices usually require numerous site-specific parameters, which may preclude their use when applied beyond their initial application context. To overcome this shortcoming, the machine learning Hierarchical Density-Based Spatial Clustering of Application of Noise (HDBSCAN) clustering algorithm was further improved and implemented to segment tree stems. Afterwards, Principal Component Analysis (PCA) was applied to extract tree stem orientation for subsequent DBH estimation. This workflow was then validated using LiDAR point clouds collected in a temperate deciduous closed-canopy forest stand during the leaf-on and leaf-off seasons, along with multiple scanning angle ranges. The results show that the proposed methodology can correctly detect up to 82% of tree stems (with a precision of 98%) during the leaf-off season and have a Maximum Scanning Angle Range (MSAR) of 75 degrees, without having to set up any site-specific parameters for the segmentation procedure. In the future, our method could then minimize the omission and commission errors when initially detecting trees, along with assisting further tree metrics retrieval. Finally, this research shows that, under the study conditions, the point density within an approximately 1.3-meter height above the ground remains low within closed-canopy forest stands even during the leaf-off season, thus restricting the accurate estimation of the DBH. As a result, autonomous UAVs that can both fly above and under the canopy provide a clear opportunity to achieve this purpose.

Clustering can identify the natural structure that is inherent to measured data. For single-cell omics, clustering finds cells with similar molecular phenotype after which cell types are annotated. Leiden clustering is one of the algorithms of choice in the single-cell community. In the field of spatial omics, Leiden is often categorized as a “non-spatial” clustering method. However, we show that by integrating spatial information at various steps Leiden clustering is rendered into a computationally highly performant, spatially aware clustering method that compares well with state-of-the art spatial clustering algorithms.

The need for a multidimensional measure of population health that accounts for its distribution remains a central problem to guide the allocation of limited resources. Absolute proxy measures, like the infant mortality rate (IMR), are limited because they ignore inequality and spatial clustering. We propose a novel, three-part, multidimensional mortality indicator that can be used as the first step to differentiate interventions in a region or country. The three-part indicator (MortalityABC index) combines absolute mortality rate, the Theil Index to calculate mortality inequality and the Getis-Ord G statistic to determine the degree of spatial clustering. The analysis utilises global sub-national IMR data to empirically illustrate the proposed indicator. The three-part indicator is mapped globally to display regional/country variation and further highlight its potential application. Developing countries (e.g. in sub-Saharan Africa) display high levels of absolute mortality as well as variable mortality inequality with evidence of spatial clustering within certain sub-national units (\"hotspots\"). Although greater inequality is observed outside developed regions, high mortality inequality and spatial clustering are common in both developed and developing countries. Significant positive correlation was observed between the degree of spatial clustering and absolute mortality. The proposed multidimensional indicator should prove useful for spatial allocation of healthcare resources within a country, because it can prompt a wide range of policy options and prioritise high-risk areas. The new indicator demonstrates the inadequacy of IMR as a single measure of population health, and it can also be adapted to lower administrative levels within a country and other population health measures.

Using topology in data analysis is a promising new field, and recently, it has attracted numerous researchers and played a vital role in both research and application. This study explores the burgeoning field of topology-based data analysis, mainly focusing on its application in clustering algorithms within data mining. Our research addresses the critical challenges of reducing execution time and enhancing clustering quality, which includes decreasing the dependency on input parameters - a notable limitation in current methods. We propose five innovative strategies to optimize clustering algorithms that utilize topological relationships by combining solutions of expanding points fewer times, merging clusters, and using a jump to increase the radius value according to the nearest neighbor distance array index. These strategies aim to refine clustering performance by improving algorithmic efficiency and the quality of clustering outcomes. This approach elevates the standard of cluster analysis and contributes significantly to the evolving landscape of data mining and analysis.