Filters








5,605 Hits in 8.0 sec

SAMCNet for Spatial-configuration-based Classification: A Summary of Results [article]

Majid Farhadloo, Carl Molnar, Gaoxiang Luo, Yan Li, Shashi Shekhar, Rachel L. Maus, Svetomir N. Markovic, Raymond Moore, Alexey Leontovich
2022 arXiv   pre-print
In addition, the related deep neural networks are limited to category pairs and do not explore larger subsets of point categories.  ...  To overcome these limitations, we propose a Spatial-interaction Aware Multi-Category deep neural Network (SAMCNet) architecture and contribute novel local reference frame characterization and point pair  ...  We also thank Kim Koffolt and the Spatial Computing Research Group for valuable comments and refinements.  ... 
arXiv:2112.12219v2 fatcat:ti6yt5qhfrgephaz7bknpco6dm

What We Know About the Brain Structure–Function Relationship

Karla Batista-García-Ramó, Caridad Fernández-Verdecia
2018 Behavioral Sciences  
to elucidate multi-scale relationships and to infer disorder mechanisms.  ...  The main hypothesis is that the anatomic architecture conditions, but does not determine, the neural network dynamic.  ...  The FC is dealt with as a purely spatial measure and this static description is a moot point given that the non-stationary of resting-state connectivity turns around the way that functional interactions  ... 
doi:10.3390/bs8040039 pmid:29670045 pmcid:PMC5946098 fatcat:nahupzt2enfarcaa5ju3qrbbwm

Research topic trend prediction of scientific papers based on spatial enhancement and dynamic graph convolution network [article]

Changwei Zheng and Zhe Xue and Meiyu Liang and Feifei Kou
2022 arXiv   pre-print
Our model combines a graph convolutional neural network (GCN) and Temporal Convolutional Network (TCN), specifically, GCNs are used to learn the spatial dependencies of research topics a and use space  ...  To simultaneously capture the spatial dependencies and temporal changes between research topics, we propose a deep neural network-based research topic hotness prediction algorithm, a spatiotemporal convolutional  ...  For example, with the rise of graph neural networks, The transportation network begins to use the graph neural network [5] [6] to capture the spatial features, and the research on intelligent transportation  ... 
arXiv:2203.16256v1 fatcat:lyowmrwct5ggtpnro5nt7e6zvy

Learning cell communication from spatial graphs of cells [article]

David Sebastian Fischer, Anna Christina Schaar, Fabian J Theis
2021 bioRxiv   pre-print
We address these limitations using spatial molecular profiling data with node-centric expression modeling (NCEM), a computational method based on graph neural networks which reconciles variance attribution  ...  These events cannot be directly observed in molecular profiling assays of single cells and have to be inferred.  ...  of the Bavarian Research Association "ForInter" (Interaction of human brain cells), by the Wellcome Trust Grant 108413/A/15/D and by the Helmholtz Association's Initiative and Networking Fund through Helmholtz  ... 
doi:10.1101/2021.07.11.451750 fatcat:k3efxkguhncxhj3e3ihrgsbr7u

Attentive Gated Graph Neural Network for Image Scene Graph Generation

Shuohao Li, Min Tang, Jun Zhang, Lincheng Jiang
2020 Symmetry  
In this work, we translate the scene graph into an Attentive Gated Graph Neural Network which can propagate a message by visual relationship embedding.  ...  Image scene graph is a semantic structural representation which can not only show what objects are in the image, but also infer the relationships and interactions among them.  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/sym12040511 fatcat:5v57eu723bglpm44pib6xj2fje

Leveraging Spatio-Temporal Graphs and Knowledge Graphs: Perspectives in the Field of Maritime Transportation

Géraldine Del Mondo, Peng Peng, Jérôme Gensel, Christophe Claramunt, Feng Lu
2021 ISPRS International Journal of Geo-Information  
While the integration of time within GIS has long been a domain of major interest, alternative modelling and data manipulation approaches derived from graph and knowledge-based principles provide many  ...  This paper introduces a prospective study of the potential of spatio-temporal graphs (ST-graphs) and knowledge graphs (K-graphs) for the modelling of geographical phenomena.  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/ijgi10080541 fatcat:xardl3g6qrcmxeq2mauoyk7wjy

Positional Encoder Graph Neural Networks for Geographic Data [article]

Konstantin Klemmer, Nathan Safir, Daniel B Neill
2022 arXiv   pre-print
Graph neural networks (GNNs) provide a powerful and scalable solution for modeling continuous spatial data.  ...  spatial autocorrelation in the data in parallel with the main task.  ...  Specific GNN architectures including Graph Convolutional Networks [20] , Graph Attention Networks [31] and GraphSAGE [12] are powerful methods for inference and representation learning with spatial  ... 
arXiv:2111.10144v2 fatcat:7kfyjso6hjebros6j7jjqeeenu

Multi-Resolution Graph Neural Network for Large-Scale Pointcloud Segmentation [article]

Liuyue Xie, Tomotake Furuhata, Kenji Shimada
2020 arXiv   pre-print
We reduce the computation demand by utilizing a graph neural network on the preformed pointcloud graphs and retain the precision of the segmentation with a bidirectional network that fuses feature embedding  ...  We present MuGNet, a memory-efficient, end-to-end graph neural network framework to perform semantic segmentation on large-scale pointclouds.  ...  All of the frameworks sequentially infer the graph embeddings with only forward network paths.  ... 
arXiv:2009.08924v1 fatcat:6sczmd7lzvd3rjh6eevjvlhoza

Survey of Knowledge Graph Approaches and Applications

Hangjun Zhou, Tingting Shen, Xinglian Liu, Yurong Zhang, Peng Guo, Jianjun Zhang
2020 Journal on Artificial Intelligence  
On the basis of comprehensively expounding the definition and architecture of knowledge graph, this paper reviews the key technologies of knowledge graph construction, including the research progress of  ...  With the advent of the era of big data, knowledge engineering has received extensive attention. How to extract useful knowledge from massive data is the key to big data analysis.  ...  on spatial distribution); b) reasoning based on neural network; c) mixed reasoning (mixed rules and distributed representation reasoning, mixed neural network and distributed representation reasoning)  ... 
doi:10.32604/jai.2020.09968 fatcat:yvggvqhexze43jyomytsf7kfr4

Multi-Robot Collaborative Perception with Graph Neural Networks [article]

Yang Zhou, Jiuhong Xiao, Yue Zhou, Giuseppe Loianno
2022 arXiv   pre-print
In this paper, we propose a general-purpose Graph Neural Network (GNN) with the main goal to increase, in multi-robot perception tasks, single robots' inference perception accuracy as well as resilience  ...  Several experiments both using photo-realistic and real data gathered from multiple aerial robots' viewpoints show the effectiveness of the proposed approach in challenging inference conditions including  ...  This paper was recommended for publication by Editor Cesar Cadena upon evaluation of the Associate Editor and Reviewers' comments.  ... 
arXiv:2201.01760v1 fatcat:tx3w52t5crdidiaf7s5hwepiom

Incorporating biological structure into machine learning models in biomedicine

Jake Crawford, Casey S Greene
2020 Current Opinion in Biotechnology  
Examples of such data include DNA or RNA sequences, gene sets or pathways, gene interaction or coexpression networks, ontologies, and phylogenetic trees.  ...  The area of research would benefit from performant open source implementations and independent benchmarking efforts.  ...  Acknowledgement The authors would like to thank Daniel Himmelstein for a critical reading of the manuscript and helpful discussion.  ... 
doi:10.1016/j.copbio.2019.12.021 pmid:31962244 pmcid:PMC7308204 fatcat:dldjmhskujb4nhg5v7h2vw3fxa

Advantages of using graph databases to explore chromatin conformation capture experiments

Daniele D'Agostino, Pietro Liò, Marco Aldinucci, Ivan Merelli
2021 BMC Bioinformatics  
The use of graph databases, instead, supports both the analysis and the visualisation of the spatial pattern present in Hi-C data, in particular for comparing different experiments or for re-mapping omics  ...  These concepts have been implemented in NeoHiC, an open-source and user-friendly web application for the progressive visualisation and analysis of Hi-C networks based on the use of the Neo4j graph database  ...  The full contents of the supplement are available at https ://bmcbi oinfo rmati cs.biome dcent ral.com/artic les/suppl ement s/volum e-22-suppl ement -2.  ... 
doi:10.1186/s12859-020-03937-0 pmid:33902433 fatcat:hmiaaz7tgza4hc74cflhovjva4

Semantic Enhancement of Human Urban Activity Chain Construction Using Mobile Phone Signaling Data

Shaojun Liu, Yi Long, Ling Zhang, Hao Liu
2021 ISPRS International Journal of Geo-Information  
However, the spatial and temporal uncertainty of the ubiquitous mobile sensing data brings a huge challenge for modeling and analyzing human activities.  ...  Semantic activity chain modeling with activity purpose provides scientific methodological support for the analysis and decision-making of human behavior, urban planning, traffic management, green sustainable  ...  (1) Graph construction In graph neural networks, the graph connection of common social networks and paper citation networks can be directly built based on the data's subscription and citation relationships  ... 
doi:10.3390/ijgi10080545 fatcat:5bkfpitm3nhxhipjrbpe6wat5y

Spatial Commonsense Graph for Object Localisation in Partial Scenes [article]

Francesco Giuliari and Geri Skenderi and Marco Cristani and Yiming Wang and Alessio Del Bue
2022 arXiv   pre-print
The SCG is used to estimate the unknown position of the target object in two steps: first, we feed the SCG into a novel Proximity Prediction Network, a graph neural network that uses attention to perform  ...  The proposed solution is based on a novel scene graph model, the Spatial Commonsense Graph (SCG), where objects are the nodes and edges define pairwise distances between them, enriched by concept nodes  ...  First, we construct a spatial commonsense graph (SCG) from the known scene by enriching the scene graph with concept relationships, resulting in edges of three types: UsedFor (orange edges), AtLocation  ... 
arXiv:2203.05380v2 fatcat:wxvwmthcz5aktgvtnmloy2dmre

Spatio-Temporal Features in Action Recognition Using 3D Skeletal Joints

Mihai Trăscău, Mihai Nan, Adina Florea
2019 Sensors  
This paper explores different interpretations of both the spatial and the temporal dimensions of a sequence of frames describing an action.  ...  Using 3D skeleton joints extracted from depth images taken with time-of-flight (ToF) cameras has been a popular solution for accomplishing these tasks.  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/s19020423 fatcat:fwdwbvh7x5bxzoje6iceelpnui
« Previous Showing results 1 — 15 out of 5,605 results