FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3119490841> ?p ?o ?g. }

• W3119490841 abstract "Data-driven methods open up unprecedented possibilities for maritime surveillance using Automatic Identification System (AIS) data. In this work, we explore deep learning strategies using historical AIS observations to address the problem of predicting future vessel trajectories with a prediction horizon of several hours. We propose novel sequence-to-sequence vessel trajectory prediction models based on encoder-decoder recurrent neural networks (RNNs) that are trained on historical trajectory data to predict future trajectory samples given previous observations. The proposed architecture combines Long Short-Term Memory (LSTM) RNNs for sequence modeling to encode the observed data and generate future predictions with different intermediate aggregation layers to capture space-time dependencies in sequential data. Experimental results on vessel trajectories from an AIS dataset made freely available by the Danish Maritime Authority show the effectiveness of deep-learning methods for trajectory prediction based on sequence-to-sequence neural networks, which achieve better performance than baseline approaches based on linear regression or on the Multi-Layer Perceptron (MLP) architecture. The comparative evaluation of results shows: i) the superiority of attention pooling over static pooling for the specific application, and ii) the remarkable performance improvement that can be obtained with labeled trajectories, i.e., when predictions are conditioned on a low-level context representation encoded from the sequence of past observations, as well as on additional inputs (e.g., port of departure or arrival) about the vessel's high-level intention, which may be available from AIS." @default.
• W3119490841 created "2021-01-18" @default.
• W3119490841 creator A5019392883 @default.
• W3119490841 creator A5021918420 @default.
• W3119490841 creator A5042374975 @default.
• W3119490841 creator A5048276519 @default.
• W3119490841 creator A5049659813 @default.
• W3119490841 date "2021-01-07" @default.
• W3119490841 modified "2023-09-27" @default.
• W3119490841 title "Deep Learning Methods for Vessel Trajectory Prediction based on Recurrent Neural Networks" @default.
• W3119490841 cites W1480376833 @default.
• W3119490841 cites W1492815834 @default.
• W3119490841 cites W1514535095 @default.
• W3119490841 cites W1533861849 @default.
• W3119490841 cites W1544827683 @default.
• W3119490841 cites W1554663460 @default.
• W3119490841 cites W1589221530 @default.
• W3119490841 cites W1677182931 @default.
• W3119490841 cites W2064675550 @default.
• W3119490841 cites W2107878631 @default.
• W3119490841 cites W2130494750 @default.
• W3119490841 cites W2130942839 @default.
• W3119490841 cites W2131774270 @default.
• W3119490841 cites W2136848157 @default.
• W3119490841 cites W2140242774 @default.
• W3119490841 cites W2143612262 @default.
• W3119490841 cites W2156387975 @default.
• W3119490841 cites W2157331557 @default.
• W3119490841 cites W2162931300 @default.
• W3119490841 cites W2215617441 @default.
• W3119490841 cites W2520171618 @default.
• W3119490841 cites W2532516272 @default.
• W3119490841 cites W2572270144 @default.
• W3119490841 cites W2743711613 @default.
• W3119490841 cites W2753820606 @default.
• W3119490841 cites W2760327630 @default.
• W3119490841 cites W2790115023 @default.
• W3119490841 cites W2809127489 @default.
• W3119490841 cites W2902297500 @default.
• W3119490841 cites W2937593748 @default.
• W3119490841 cites W2939984110 @default.
• W3119490841 cites W2944791333 @default.
• W3119490841 cites W2944924828 @default.
• W3119490841 cites W2950178297 @default.
• W3119490841 cites W2950768109 @default.
• W3119490841 cites W2962824709 @default.
• W3119490841 cites W2962965405 @default.
• W3119490841 cites W2963755273 @default.
• W3119490841 cites W2964121744 @default.
• W3119490841 cites W2964304579 @default.
• W3119490841 cites W2964308564 @default.
• W3119490841 cites W2979995175 @default.
• W3119490841 cites W2997958396 @default.
• W3119490841 cites W3012815794 @default.
• W3119490841 cites W3015961574 @default.
• W3119490841 cites W3020873385 @default.
• W3119490841 cites W3023092994 @default.
• W3119490841 cites W3026482450 @default.
• W3119490841 cites W3034826969 @default.
• W3119490841 cites W3085973453 @default.
• W3119490841 cites W3102144021 @default.
• W3119490841 cites W581956982 @default.
• W3119490841 cites W650350307 @default.
• W3119490841 cites W3023071679 @default.
• W3119490841 hasPublicationYear "2021" @default.
• W3119490841 type Work @default.
• W3119490841 sameAs 3119490841 @default.
• W3119490841 citedByCount "3" @default.
• W3119490841 countsByYear W31194908412021 @default.
• W3119490841 crossrefType "posted-content" @default.
• W3119490841 hasAuthorship W3119490841A5019392883 @default.
• W3119490841 hasAuthorship W3119490841A5021918420 @default.
• W3119490841 hasAuthorship W3119490841A5042374975 @default.
• W3119490841 hasAuthorship W3119490841A5048276519 @default.
• W3119490841 hasAuthorship W3119490841A5049659813 @default.
• W3119490841 hasConcept C108583219 @default.
• W3119490841 hasConcept C111919701 @default.
• W3119490841 hasConcept C118505674 @default.
• W3119490841 hasConcept C119857082 @default.
• W3119490841 hasConcept C121332964 @default.
• W3119490841 hasConcept C1276947 @default.
• W3119490841 hasConcept C13662910 @default.
• W3119490841 hasConcept C147168706 @default.
• W3119490841 hasConcept C151730666 @default.
• W3119490841 hasConcept C154945302 @default.
• W3119490841 hasConcept C2778112365 @default.
• W3119490841 hasConcept C2779343474 @default.
• W3119490841 hasConcept C40506919 @default.
• W3119490841 hasConcept C41008148 @default.
• W3119490841 hasConcept C50644808 @default.
• W3119490841 hasConcept C54355233 @default.
• W3119490841 hasConcept C70437156 @default.
• W3119490841 hasConcept C86803240 @default.
• W3119490841 hasConceptScore W3119490841C108583219 @default.
• W3119490841 hasConceptScore W3119490841C111919701 @default.
• W3119490841 hasConceptScore W3119490841C118505674 @default.
• W3119490841 hasConceptScore W3119490841C119857082 @default.
• W3119490841 hasConceptScore W3119490841C121332964 @default.
• W3119490841 hasConceptScore W3119490841C1276947 @default.
• W3119490841 hasConceptScore W3119490841C13662910 @default.

• next