2,368 Hits in 4.8 sec

Spatial Structured Prediction Models: Applications, Challenges, and Techniques

Zhe Jiang
2020 IEEE Access  
topology based models learn spatial structures on a topological surface (e.g., 3D terrain map) beyond the common Euclidean space (e.g., raster image or video).  ...  We now introduce several categories of techniques based on the type of spatial structural constraints being incorporated, including spatial neighborhood graph, spatial distance kernel, and geometric topology  ... 
doi:10.1109/access.2020.2975584 fatcat:oeseqyr3dbhx3hznh6omk2c7mm

Short-Term Electricity Price Forecasting based on Graph Convolution Network and Attention Mechanism [article]

Yuyun Yang, Zhenfei Tan, Haitao Yang, Guangchun Ruan, Haiwang Zhong
2021 arXiv   pre-print
Case studies based on the IEEE-118 test system and real-world data from the PJM validate that the proposed model outperforms existing forecasting models in accuracy, and maintains a robust performance  ...  Such kind of network can extract the spatial-temporal features of LMPs, and provide fast and high-quality predictions for all nodes simultaneously.  ...  Reference [13] formulated some general seasonal periodic regression models for daily LMPs with the auto-regressive integrated moving average (ARIMA), auto-regressive fractionally integrated moving average  ... 
arXiv:2107.12794v1 fatcat:ignstbcarbdsdf4vm5gyabgpam

Transdisciplinary Foundations of Geospatial Data Science

Yiqun Xie, Emre Eftelioglu, Reem Ali, Xun Tang, Yan Li, Ruhi Doshi, Shashi Shekhar
2017 ISPRS International Journal of Geo-Information  
Based on the analysis, specific algorithm design paradigms can be explored for algorithm acceleration.  ...  Prediction aims to predict values for unlabeled locations in a geographic domain using classification or regression models learned from training datasets (e.g., land use classification, crop yield prediction  ...  We may also consider some constraints on the size of the hotspot based on domain knowledge.  ... 
doi:10.3390/ijgi6120395 fatcat:w3uibnadrneqrctxgaw5dxfkqm

Probabilistic Feature Extraction from Multivariate Time Series Using Spatio-Temporal Constraints [chapter]

Michał Lewandowski, Dimitrios Makris, Jean-Christophe Nebel
2011 Lecture Notes in Computer Science  
In addition we provide quantitative results on a classification application, i.e. view-invariant action recognition, where imposing spatiotemporal constraints is essential.  ...  GPDM [22] , augments GPLVM with a nonlinear dynamical mapping on the latent space based on the auto-regressive model to take advantage of temporal information provided with time series data.  ...  Preservation of observed space topology was supported by imposing high dimensional constraints on the latent space [12, 21] .  ... 
doi:10.1007/978-3-642-20847-8_15 fatcat:ru35l7fm4vd2vc4hialscntkl4

Disentangled Spatiotemporal Graph Generative Models [article]

Yuanqi Du and Xiaojie Guo and Hengning Cao and Yanfang Ye and Liang Zhao
2022 arXiv   pre-print
for interpretability.  ...  Although disentangling and understanding the correlations among spatial, temporal, and graph aspects have been a long-standing key topic in network science, they typically rely on network processing hypothesized  ...  Thus it is calculated based on the learn latent variables and the input graphs in the testing sets.  ... 
arXiv:2203.00411v1 fatcat:wzkmje7u65dxzlstk2wt6glklu

Bridging the Gap between Brain Activity and Cognition: Beyond the Different Tales of fMRI Data Analysis

Maria G. Di Bono, Konstantinos Priftis, Carlo Umiltà
2017 Frontiers in Neuroscience  
Instead, the very notion of network phenomena requires understanding spatiotemporal dynamics, which, in turn, depends on the way fMRI data are analyzed.  ...  The challenging question is: what is the learning mechanism, which, within spatial/anatomical constraints, has shaped the flexible representational code of the brain?  ...  Indeed, analysis of fMRI data has been mainly based on univariate methods (i.e., the General Linear Model-GLM), which impose a series of critical assumptions and constraints.  ... 
doi:10.3389/fnins.2017.00031 pmid:28197069 pmcid:PMC5281568 fatcat:gn2lwlchdbhufpbrozqw6xrkgi

Modeling Global Spatial–Temporal Graph Attention Network for Traffic Prediction

Bin Sun, Duan Zhao, Xinguo Shi, Yongxin He
2021 IEEE Access  
Due to the complex dynamic spatial-temporal dependence between traffic networks, traffic prediction is extremely challenging.  ...  Then, each node computes the influence of traffic global interaction on a single node in parallel, and the spatial-temporal interaction information is adaptive fused by gating fusion mechanism.  ...  SVR: The regression prediction method based on machine learning can adapt to non-linear traffic data. Factor: Single node timing.  ... 
doi:10.1109/access.2021.3049556 fatcat:wdlfpkr67bgmhm2ofmkodjf72q

A Statistical Toolbox For Mining And Modeling Spatial Data

Gérard D'Aubigny
2016 Comparative Economic Research  
, based on the Moran's and the Geary's coefficients, the adequacy of which is rarely challenged, despite the fact that when reporting on their properties, many users seem likely to make mistakes and to  ...  Most data mining projects in spatial economics start with an evaluation of a set of attribute variables on a sample of spatial entities, looking for the existence and strength of spatial autocorrelation  ...  Observe too that one well known specification of models of spatial regression, that takes into account spatial auto-correlation is where as said above, .  ... 
doi:10.1515/cer-2016-0035 fatcat:d4a3gnwfffax3jja6pscjjbwym

Mining Model Trees from Spatial Data [chapter]

Donato Malerba, Michelangelo Ceci, Annalisa Appice
2005 Lecture Notes in Computer Science  
Mining regression models from spatial data is a fundamental task in Spatial Data Mining.  ...  We propose a method, namely Mrs-SMOTI, that takes advantage from a tight-integration with spatial databases and mines regression models in form of trees in order to partition the sample space.  ...  The auto-correlation on the spatially-lagged response attribute can be similarly exploited during the mining process.  ... 
doi:10.1007/11564126_20 fatcat:w7ogbh4rovgijecwsb5dpc54fu

Integrating GIS and FEATHERS: A Conceptual Design

Sungjin Cho, Tom Bellemans, Davy Janssens, Geert Wets
2014 Procedia Computer Science  
GIS provides geodatabase for effectively storing and edit (non-)spatial data, useful functions of spatial analysis for defining spatial interactions between phenomena simulated by the modeling system,  ...  Thus, this study mainly focuses on three topics: i) why FEATHERS needs a GIS module, ii) how the GIS module is designed, and iii) what functions can be supported by the GIS module in the FEATHERS system  ...  Lastly, the spatial regression captures spatial dependency that measures as the existence of statistical dependence in a collection of random variables or a collection of random variables in regression  ... 
doi:10.1016/j.procs.2014.05.441 fatcat:mdv42mwecrhynj5oabgzody6ca

DeepTransport: Learning Spatial-Temporal Dependency for Traffic Condition Forecasting [article]

Xingyi Cheng, Ruiqing Zhang, Jie Zhou, Wei Xu
2022 arXiv   pre-print
Our experiments on this dataset demonstrate our method captures the complex relationship in temporal and spatial domain.  ...  topology.  ...  We proposed a novel deep learning model (Deep-Transport) to learn the spatial-temporal dependency.  ... 
arXiv:1709.09585v3 fatcat:xmfqvbzhvjabdkkswdmwpyr25e

DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation

Jeong Joon Park, Peter Florence, Julian Straub, Richard Newcombe, Steven Lovegrove
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
Above images are raycast renderings of DeepSDF interpolating between two shapes in the learned shape latent space. Best viewed digitally.  ...  Furthermore, we show stateof-the-art performance for learned 3D shape representation and completion while reducing the model size by an order of magnitude compared with previous work.  ...  on learned priors.  ... 
doi:10.1109/cvpr.2019.00025 dblp:conf/cvpr/ParkFSNL19 fatcat:6wnfa36lqvbxdbnrc3het6mfbe

STConvS2S: Spatiotemporal Convolutional Sequence to Sequence Network for Weather Forecasting [article]

Rafaela C. Nascimento, Yania M. Souto, Eduardo Ogasawara, Fabio Porto, Eduardo Bezerra
2019 arXiv   pre-print
In this work, we propose STConvS2S (short for Spatiotemporal Convolutional Sequence to Sequence Network), a new deep learning architecture built for learning both spatial and temporal data dependencies  ...  Applying machine learning models to meteorological data brings many opportunities to the Geosciences field, such as predicting future weather conditions more accurately.  ...  Auto-regressive integrated moving average (ARIMA) are traditional statistical methods for times series analysis [Babu and Reddy, 2012] .  ... 
arXiv:1912.00134v3 fatcat:ply2wsyozbagtbq6ebyvu34hai

Measuring the Biases and Effectiveness of Content-Style Disentanglement [article]

Xiao Liu, Spyridon Thermos, Gabriele Valvano, Agisilaos Chartsias, Alison O'Neil, Sotirios A. Tsaftaris
2021 arXiv   pre-print
In particular, we consider the setting where we: (i) identify key design choices and learning constraints for three popular content-style disentanglement models; (ii) relax or remove such constraints in  ...  While considerable effort has been made to measure disentanglement in vector representations, and assess its impact on task performance, such analysis for (spatial) content - style disentanglement is lacking  ...  Removing the C constraints from SDNet and PANet spreads the spatial information across all channels, decreasing interpretability.  ... 
arXiv:2008.12378v4 fatcat:mqo5s4gf2jbgrbt55vkqniujpa

Quantification of uncertainty in 3-D seismic interpretation: implications for deterministic and stochastic geomodelling and machine learning

Alexander Schaaf, Clare E. Bond
2019 Solid Earth Discussions  
in fault network topology.  ...  Our work provides a first quantification of fault and horizon uncertainties in 3-D seismic interpretation, providing valuable insights into the influence of seismic image quality on 3-D interpretation,  ...  We would like to acknowledge the help of David Iacopini for providing access to the interpretation projects.  ... 
doi:10.5194/se-2019-54 fatcat:ewegi7fg4zck7okejghynj25zq
« Previous Showing results 1 — 15 out of 2,368 results