Representation Of Spatial Data Research Articles

VSPACE: exploring virtual spatial representation of articular chondrocytes at the single-cell level.

vSPACE is a web-based application presenting a spatial representation of scRNAseq data obtained from human articular cartilage by emulating the concept of spatial transcriptomics technology, but virtually. This virtual 2D plot presentation of human articular cartage cells generates several zonal distribution patterns, for one or multiple genes at a time, revealing patterns that scientists can appreciate as imputed spatial distribution patterns along the zonal axis. vSPACE is implemented in Python Dash as a web-based toolbox designed for data visualization of zonal gene expression patterns in articular cartilage chondrocytes. This tool is freely accessible at: https://vspace.cse.uconn.edu/The source code and extra materials for this service can be downloaded from: https://github.com/zhacheny/vSPACE.

GEUKE: A geographic entities uniformly explicit knowledge embedding model

AbstractKnowledge embedding for geographic knowledge graphs can effectively improve computational efficiency and provide support for knowledge reasoning, knowledge answering and other applications of knowledge graphs. To maintain a more comprehensive understanding of spatial features through knowledge embedding, it is crucial to integrate the representation and computation of various entity types, encompassing points, lines, and polygons. This article proposes a geographic entities uniformly explicit knowledge embedding model (GEUKE). In GEUKE, spatial data of point, line, and polygon‐type geographic entities are expressed in the form of subgraphs, and space embedding is generated using a SubGNN‐based uniform spatial feature encoder. GEUKE improves the energy function in TransE to train spatial feature‐based embedding and structural‐based embedding of geographic entities into a unified vector space. Experimental results show that GEUKE has higher performance than TransE, TransH, TransD, and TransE‐GDR on link prediction and triple classification task. Within the spatial feature embedding process, GEUKE effectively preserves the inherent features of entities, encompassing location, neighborhood, and structural attributes, while simultaneously ensuring a coherent spatial data representation across all three entity types: points, lines, and polygons. By maintaining the spatial features of geographic entities and their interrelations, this capability unleashes the full potential of applications such as knowledge reasoning and geospatial question answering in a manner that is conducive to diverse geospatial scenarios.

Concept of Processing and Interpretation of Spatiotemporal Vector Data

The purpose of this work is to develop an approach to complex processing and interpretation of spatio-temporal vector data. In this regard, it is necessary to analyze existing methods for visualizing vector and tensor fields and organizing a database for their storage and develop a concept which contains the main advantages of these methods and allows one to interpret spatial data represented as a tensor. The developed concept proposes an approach to field visualization based on drawing superellipse glyphs at each point in space. Axes of glyphs correspond to the rank of the visualized tensor, and attribute values are expressed by varying the color gradient in its monochrome representation. The architecture of a web-based application, which implements the storage of spatial data in a hybrid DBMS, and interpretation of the necessary data upon request is also proposed. For the physical storage of tensor information, a hybrid relational-hierarchical model is proposed, in which the representation of direct spatial data and the corresponding metadata, including those characterizing the source of information, are separated. It is advisable to present the final result and intermediate data in GeoJSON format. This format is actually currently the standard for presenting geospatial data and is supported by almost all software platforms and libraries aimed at solving problems of this kind.

«Цифровой двойник» населения Арктики в демографических исследованиях и управлении развитием территорий

The article considers “digital twins” of the population as a tool for socio-demographic research and territorial management. The experience of creating digital twins of the population and interactive web-sites devoted to demographic issues is systematized. A methodology for creating a digital twin of the Arctic population is proposed, based on three methodological principles: consideration of the hierarchy of territories, spatial representation of data, and combining demographic statistics with new digital data sources. The author has developed the Digital twin of the Arctic population — an interactive website (dashboard) containing detailed data on the Arctic population, including municipal and settlement levels. It includes demographic statistics, census results and data from digital platforms. The Digital twin of the Arctic population covers such issues as the size, dynamics and composition of the population, resettlement, natural and migration movement, labor and employment, transport movements, science and education, and the impact of the pandemic on demographic processes. Tools of ranking, multivariate analysis, clustering and forecasting of indicator values are implemented for researchers. From the viewpoint of state and municipal management, the main interest is the demographic profiles of regions and territories, reflecting up-to-date information about the demographic situation. Using the Digital twin of the Arctic population, the author draws conclusions about the spatial patterns of the demographic development of the Russian Arctic.

Internet in the Middle of Nowhere: Performance of Geoportals in Rural Areas According to Core Web Vitals

The spatial planning system in Poland is undergoing a fundamental reform. It emphasises the digital representation of spatial data. Low performance of geoportals, no Internet access, or poor connectivity can contribute to the exclusion from the spatial planning process, and consequently to the exclusion from a specific part of public life. Considering these developments, the present study seems relevant by pointing out the issue with geoportal performance and availability of quality Internet in rural areas. The primary contribution of the article is (1) results of performance measurements for selected geoportals; (2) presentation of measuring tools and performance indices combined with methods for ad-hoc performance measuring; and (3) presentation of potential actions to improve geoportal performance on the device with which it is used. The article offers case studies where the performance of selected geoportals was tested in rural mountainous areas with limited Internet access. Five geoportals were tested with PageSpeed Insights (PSI), WebPageTest, GTmetrix, Pingdom, and GiftOfSpeed. Core Web Vitals indices were analysed: Largest Contentful Paint (LCP), First Input Delay (FID), Cumulative Layout Shift (CLS), and First Contentful Paint (FCP). The author verified values of the Speed Index and Fully Loaded Time along with other performance indices, like GTmetrix Structure. The study failed to provide unambiguous evidence that radio link users in rural areas could experience problems with geoportal performance, although the results seem to suggest it indirectly. PSI Lab Data and Field Data tests revealed a relatively low performance of the geoportals. The Performance index remained below 50 in most cases, which is ‘Poor’ according to the PSI scale. The fully loaded time exceeded 10 s for all the geoportals and 20 s in some cases (Lab Data). It means that the perceived performance of the tested geoportals on a radio link in rural areas is most probably even lower. The case studies demonstrated further that the user has limited possibilities to speed up map applications. It is possible to slightly improve the geoportal experience through the optimisation of the device locally, but the responsibility to ensure geoportal performance is mainly the publisher’s.

Spatial transformation of multi-omics data unlocks novel insights into cancer biology.

The application of next-generation sequencing (NGS) has transformed cancer research. As costs have decreased, NGS has increasingly been applied to generate multiple layers of molecular data from the same samples, covering genomics, transcriptomics, and methylomics. Integrating these types of multi-omics data in a combined analysis is now becoming a common issue with no obvious solution, often handled on an ad hoc basis, with multi-omics data arriving in a tabular format and analyzed using computationally intensive statistical methods. These methods particularly ignore the spatial orientation of the genome and often apply stringent p-value corrections that likely result in the loss of true positive associations. Here, we present GENIUS (GEnome traNsformatIon and spatial representation of mUltiomicS data), a framework for integrating multi-omics data using deep learning models developed for advanced image analysis. The GENIUS framework is able to transform multi-omics data into images with genes displayed as spatially connected pixels and successfully extract relevant information with respect to the desired output. We demonstrate the utility of GENIUS by applying the framework to multi-omics datasets from the Cancer Genome Atlas. Our results are focused on predicting the development of metastatic cancer from primary tumors, and demonstrate how through model inference, we are able to extract the genes which are driving the model prediction and are likely associated with metastatic disease progression. We anticipate our framework to be a starting point and strong proof of concept for multi-omics data transformation and analysis without the need for statistical correction.

Spatial transformation of multi-omics data unlocks novel insights into cancer biology

The application of next-generation sequencing (NGS) has transformed cancer research. As costs have decreased, NGS has increasingly been applied to generate multiple layers of molecular data from the same samples, covering genomics, transcriptomics, and methylomics. Integrating these types of multi-omics data in a combined analysis is now becoming a common issue with no obvious solution, often handled on an ad hoc basis, with multi-omics data arriving in a tabular format and analyzed using computationally intensive statistical methods. These methods particularly ignore the spatial orientation of the genome and often apply stringent p-value corrections that likely result in the loss of true positive associations. Here, we present GENIUS (GEnome traNsformatIon and spatial representation of mUltiomicS data), a framework for integrating multi-omics data using deep learning models developed for advanced image analysis. The GENIUS framework is able to transform multi-omics data into images with genes displayed as spatially connected pixels and successfully extract relevant information with respect to the desired output. We demonstrate the utility of GENIUS by applying the framework to multi-omics datasets from the Cancer Genome Atlas. Our results are focused on predicting the development of metastatic cancer from primary tumors, and demonstrate how through model inference, we are able to extract the genes which are driving the model prediction and are likely associated with metastatic disease progression. We anticipate our framework to be a starting point and strong proof of concept for multi-omics data transformation and analysis without the need for statistical correction.

A study of crude oil futures price volatility based on multi-dimensional data from event-driven and deep learning perspectives

There are two unique challenges in current research of price volatility studies in the crude oil futures market, which is how to capture the impact of interactivity between data as much as possible when multi-dimensional data are fused, and how to solve the problem of temporal heterogeneity of research samples existing in multi-dimensional data. We proposed a tensor-based event-driven gated recurrent unit (Event-GRU) deep learning model that helps to solve the above dilemmas. Our model can effectively prevent the loss of interaction relationship of multi-dimensional data by taking the advantage of spatial data representation of tensor, as well as using news occurrence as a trigger to construct the event-driven mechanism based on GRU model, in order to overcome the feature space distortion between discrete news data and continuous trading fundamentals data due to the uneven sample time matching. Regarding the current insufficient research of crude oil prices in China, we addressed the crude oil futures trading data from the Shanghai Futures Exchange and 31,422 news data of the crude oil futures market from April 2018 to August 2020. We used the XGBoost algorithm (eXtreme Gradient Boosting) to evaluate and filter. Besides, we built a tensor-based event-GRU deep learning model to finally analyze the closing price on the day after. This research contributes to improving the accuracy of crude oil futures price analysis compared with using benchmark models such as DT, SVM, BP, LSTM, and GRU, and laying the foundation for the subsequent opening of corresponding quantitative investment strategies.

The S-BAN: Insights into the Perception of Shape-Changing Haptic Interfaces via Virtual Pedestrian Navigation

Screen-based pedestrian navigation assistance can be distracting or inaccessible to users. Shape-changing haptic interfaces can overcome these concerns. The S-BAN is a new handheld haptic interface that utilizes a parallel kinematic structure to deliver 2-DOF spatial information over a continuous workspace, with a form factor suited to integration with other travel aids. The ability to pivot, extend and retract its body opens possibilities and questions around spatial data representation. We present a static study to understand user perception of absolute pose and relative motion for two spatial mappings, showing the highest sensitivity to relative motions in the cardinal directions. We then present an embodied navigation experiment in virtual reality (VR). User motion efficiency when guided by the S-BAN was statistically equivalent to using a vision-based tool (a smartphone proxy). Although haptic trials were slower than visual trials, participants’ heads were more elevated with the S-BAN, allowing greater visual focus on the environment.

Seismic Facies Visualization Analysis Method of SOM Corrected by Uniform Manifold Approximation and Projection

<italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">As a common seismic facies visualization analysis method, SOM projects the waveform or seismic attribute vectors into a two-dimensional topological plane in a nonlinear way, which can effectively and efficiently discover the topological structure of a dataset. SOM does not need to set the number of classes in prior, and has friendly visualization characteristics and excellent generalization, which are conducive to seismic facies interpretation using unlabeled data. However, due to the competitive learning used in SOM and the imbalance of data distribution in real world, the samples from majority classes are expanded on the topological plane and the minority classes are compressed. As a result, the plane cannot accurately describe the global structure of data distribution. To improve the visualization precision by modifying the topological relationship of the prototype vectors of SOM, we utilize UMAP (Uniform Manifold Approximation and Projection), a novel manifold learning technique for dimension reduction, to correct the prototype vectors generated by SOM. By combing the advantages of SOM and UMAP in the representation of data topological structure, the global relationship between seismic data samples can be properly established, and the internal relative spatial structure of majority class samples can be retained as much as possible, resulting in a more reliable classification. Meanwhile, the framework maintains the advantages of SOM in visualization. In the modeling tests and real data experiments, we have demonstrated the effectiveness and rationality of UMAP-SOM on the spatial structure representation of three-dimensional seismic data</i> .

An Extension of Multiquadric Method Based on Trend Analysis for Surface Construction

The representation of spatial discrete data is crucial for the data analysis of meteorology, agriculture, geological exploration and other fields. Among various methods for scattered data interpolation, the multiquadric (MQ) method is the most favorable in the field of surface construction. However, the classical MQ method has accuracy concern on the boundary and is time consuming for large data set. This study proposes an algorithm by integrating the MQ method with trend surface analysis. In which, the low-order polynomial trend surface equation is firstly used to model the overall trend. Then, the MQ equation is applied to fit the residual surface after removal the trend from the data. Our implementation can eliminate the distortion in data missing areas by the classical MQ method, and the modeling efficiency can be improved significantly since the local MQ method divide the residual surface into a group of subsurfaces. The accuracy and efficiency of the proposed algorithm are validated on a synthetic model. The performance of the developed algorithm is further examined on the elevation data collected in Tibet and the seabed of a strait in Norway. The results show that with an equivalent resolution, the developed algorithm can be much more efficient than the classical MQ method and well-developed Kriging method.

Cell2Grid: an efficient, spatial, and convolutional neural network-ready representation of cell segmentation data.

Cell segmentation algorithms are commonly used to analyze large histologic images as they facilitate interpretation, but on the other hand they complicate hypothesis-free spatial analysis. Therefore, many applications train convolutional neural networks (CNNs) on high-resolution images that resolve individual cells instead, but their practical application is severely limited by computational resources. In this work, we propose and investigate an alternative spatial data representation based on cell segmentation data for direct training of CNNs. We introduce and analyze the properties of Cell2Grid, an algorithm that generates compact images from cell segmentation data by placing individual cells into a low-resolution grid and resolves possible cell conflicts. For evaluation, we present a case study on colorectal cancer relapse prediction using fluorescent multiplex immunohistochemistry images. We could generate Cell2Grid images at resolution that were 100 times smaller than the original ones. Cell features, such as phenotype counts and nearest-neighbor cell distances, remain similar to those of original cell segmentation tables ( ). These images could be directly fed to a CNN for predicting colon cancer relapse. Our experiments showed that test set error rate was reduced by 25% compared with CNNs trained on images rescaled to with bilinear interpolation. Compared with images at resolution (bilinear rescaling), our method reduced CNN training time by 85%. Cell2Grid is an efficient spatial data representation algorithm that enables the use of conventional CNNs on cell segmentation data. Its cell-based representation additionally opens a door for simplified model interpretation and synthetic image generation.

Classifying ASD based on time-series fMRI using spatial–temporal transformer

As the prevalence of autism spectrum disorder (ASD) increases globally, more and more patients need to receive timely diagnosis and treatment to alleviate their suffering. However, the current diagnosis method of ASD still adopts the subjective symptom-based criteria through clinical observation, which is time-consuming and costly. In recent years, functional magnetic resonance imaging (fMRI) neuroimaging techniques have emerged to facilitate the identification of potential biomarkers for diagnosing ASD. In this study, we developed a deep learning framework named spatial–temporal Transformer (ST-Transformer) to distinguish ASD subjects from typical controls based on fMRI data. Specifically, a linear spatial–temporal multi-headed attention unit is proposed to obtain the spatial and temporal representation of fMRI data. Moreover, a Gaussian GAN-based data balancing method is introduced to solve the data unbalance problem in real-world ASD datasets for subtype ASD diagnosis. Our proposed ST-Transformer is evaluated on a large cohort of subjects from two independent datasets (ABIDE I and ABIDE II) and achieves robust accuracies of 71.0% and 70.6%, respectively. Compared with state-of-the-art methods, our results demonstrate competitive performance in ASD diagnosis.

ScFeatures: multi-view representations of single-cell and spatial data for disease outcome prediction.

MotivationWith the recent surge of large-cohort scale single cell research, it is of critical importance that analytical methods can fully utilize the comprehensive characterization of cellular systems that single cell technologies produce to provide insights into samples from individuals. Currently, there is little consensus on the best ways to compress information from the complex data structures of these technologies to summary statistics that represent each sample (e.g. individuals).ResultsHere, we present scFeatures, an approach that creates interpretable cellular and molecular representations of single-cell and spatial data at the sample level. We demonstrate that summarizing a broad collection of features at the sample level is both important for understanding underlying disease mechanisms in different experimental studies and for accurately classifying disease status of individuals.Availability and implementationscFeatures is publicly available as an R package at https://github.com/SydneyBioX/scFeatures. All data used in this study are publicly available with accession ID reported in the Section 2.Supplementary information Supplementary data are available at Bioinformatics online.

A unified representation method for interdisciplinary spatial earth data

ABSTRACT Unified representation of spatial earth data is an essential scientific issue. The analysis and mining of interdisciplinary spatial earth data resources can help discover hidden scientific knowledge, and even reveal the intrinsic relationship among different disciplines. However, the different description methods and inner structures among interdisciplinary spatial earth data bring significant challenges to unified data management and collaborative analysis in earth environment research. To address this issue, this paper proposes a unified representation method for interdisciplinary spatial earth data. First, this paper establishes a general metadata model and realizes the unified description of interdisciplinary data. Second, an entity data organization model is presented, which can realize the unified organization of entity data with different inner structures. Finally, we introduce the Spatial Earth Data Format (SEDF), a data format based on HDF5 for implementing the data organization model of interdisciplinary spatial earth data. Data representation experiments and validation are conducted to verify the availability and practicability of the proposed data representation method. The results suggest the powerful ability to represent spatial earth data efficiently and ensure data integrity, which is convenient for data management and application.

Estimation and Mapping of the Received Power Level of Digital Signals TV Using Spatial Interpolation Methods

The signal digitization process of the open television system is still in progress, therefore, the study of the digital signal propagation has great importance so that broadcasters can develop and improve the transmission service. The field measurement of digital signal parameters is one of the most reliable means to analyze the signal propagation in a given area. In this work, received power measurements of a TV station digital signal in the city of Mossoró, Rio Grande do Norte, Brazil were performed. The objective is to implement interpolation methods and identify which is the most suitable for the spatial representation of power data in this region through the Mean Error (ME) and Root Mean Squared Error (RMSE) evaluation metrics. A good representation of the received power level contributes to the mapping of greater and lesser intensity of the digital signal in the region. The implementation of the interpolation methods was performed in Surfer® software (Golden Software, LLC), which provides the cross-validation report with the ME and RMSE values associated with each method. The Ordinary Kriging method with exponential variogram model obtained the lowest RMSE value (7.6083) and, therefore, the most adequate estimates.

Mapping of the cost of atmospheric corrosion of zinc and galvanised steel due to the effect of atmospheric pollution in the Mexico City Metropolitan area

ABSTRACT The deterioration of materials due to the effect of atmospheric pollution generates a cost to society because the maintenance and replacement of degraded materials. Galvanised steel is used in electrical industry to build electrical transmission towers (ETT). The objective of the study was to estimate the annual maintenance cost of galvanised steel used in the construction of ETT. The maintenance cost for galvanised steel was estimated considering the cost of the material surface area and the difference between the maintenance interval of clean and contaminated areas. Maps of intervals and maintenance costs were obtained for galvanised steel (85 and 100 µm), which are the thicknesses regulated in Mexico for ETT. In addition, an ArcGis geographic information system was used for a spatial representation of data from the anthropogenic environment. The mapping of areas at risk of corrosion shows that in the northwest zone, ETT presents the highest maintenance costs for the year 2019. For galvanised steel thicknesses of 85 and 100 µm, there are annual costs of, respectively, 8.68 and 10.16 USD/m2.

INFORMATION SUPPORT FOR MANAGING THE COMPUTER INFRASTRUCTURE OF COMPLEX DISTRIBUTED SYSTEMS

Management of complex distributed systems, at present, is carried out using information technologies designed to collect and manage a large amount of heterogeneous information of an organization or institution. The computer infrastructure of such systems is also a complex distributed system, and information about the location and mutual arrangement of its individual components, as well as the location of the associated infrastructure and main users, is essential for its high-quality functioning. This paper proposes a method for mining spatial data to formalize the process of creating specialized databases for the implementation (creation) of individual subsystems as part of complex distributed information systems. The results of the application of this method for the construction of one of the subsystems, namely, the subsystem of information support for the management of computer infrastructure, as part of a complex distributed information system, are presented on the example of the geoinformation system of the Ufa State Aviation Technical University. The proposed approach to intelligent analysis and representation of spatial data can be used to build complex information systems in significantly distributed organizational and infrastructural systems.

STRATA OBJECTS BASED ON MALAYSIAN LADM COUNTRY PROFILE VIA WEB 3D VISUALIZATION

Abstract. Three-dimensional visualization of 3D parcels have been investigated in many viewpoints in order to fulfil the demands of expanding cities and the increasing complexity of building design. In Malaysia, with the growing strata developed area, particularly residential buildings (i.e., apartments), land administration agencies will need to improve their application in sharing and disseminating cadastral data. Hence, web-based solutions have been recognized as an important visualization requirement among end-users. It acts as a distributed information platform that allows 3D data sharing with the minimal architecture of client-server connects by the internet. There are two key topics addressed in this paper, which is the depiction of 3D strata objects on the web and the linkage to their legal data. This paper also describes the implementation of conceptual model of strata object based on Malaysian Land Administration Domain Model (LADM) Country Profile for the representation of spatial and non-spatial data. Tools such as PostgreSQL with PostGIS extension is used for storing data, CesiumJS was used to handle and visualise 3D strata objects in a 3D browser that was customised as a web application. The results demonstrate a viewer of a multi-storey buildings using web visualization to display both physical and legal information of 3D Strata objects based on LADM country profile (Malaysia). This particular paper also attempts to address 3D visualization of spatial and non-spatial data query using a web application, which also suggests further directions for 3D cadastral visualization development.

S²ENet: Spatial–Spectral Cross-Modal Enhancement Network for Classification of Hyperspectral and LiDAR Data

The effective utilization of multimodal data (e.g., hyperspectral and light detection and ranging (LiDAR) data) has profound implications for further development of the remote sensing (RS) field. Many studies have explored how to effectively fuse features from multiple modalities; however, few of them focus on information interactions that can effectively promote the complementary semantic content of multisource data before fusion. In this letter, we propose a spatial–spectral enhancement module (S <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> EM) for cross-modal information interaction in deep neural networks. Specifically, S <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> EM consists of SpAtial Enhancement Module (SAEM) for enhancing spatial representation of hyperspectral data by LiDAR features and SpEctral Enhancement Module (SEEM) for enhancing spectral representation of LiDAR data by hyperspectral features. A series of experiments and ablation studies on the Houston2013 dataset show that S <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> EM can effectively facilitate the interaction and understanding between multimodal data. Our source code is available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/likyoo/Multimodal-Remote-Sensing-Toolkit</uri> , contributing to the RS community.