FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3090334975> ?p ?o ?g. }

• W3090334975 endingPage "102787" @default.
• W3090334975 startingPage "102787" @default.
• W3090334975 abstract "Population synthesis is concerned with the generation of agents for agent-based modelling in many fields, such as economics, transportation, ecology and epidemiology. When the number of attributes describing the agents and/or their level of detail becomes large, survey data cannot densely support the joint distribution of the attributes in the population due to the curse of dimensionality. It leads to a situation where many attribute combinations are missing from the sample data while such combinations exist in the real population. In this case, it becomes essential to consider methods that are able to impute such missing information effectively. In this paper, we propose to use deep generative latent models. These models are able to learn a compressed representation of the data space, which when projected back to the original space, leads to an effective way of imputing information in the observed data space. Specifically, we employ the Wasserstein Generative Adversarial Network (WGAN) and the Variational Autoencoder (VAE) for a large-scale population synthesis application. The models are applied to a Danish travel survey with a feature-space of more than 60 variables and trained and tested using cross-validation. A new metric that applies to the evaluation of generative models in an unsupervised setting is proposed. It is based on the ability to generate diverse yet valid synthetic attribute combinations by comparing if the models can recover missing combinations (sampling zeros) while keeping truly impossible combinations (structural zeros) models at a minimum. For a low-dimensional experiment, the VAE, the marginal sampler and the fully random sampler generate 5%, 21% and 26% more structural zeros per sampling zero when compared to the WGAN. For a high dimensional case, these figures increase to 44%, 2217% and 170440% respectively. This research directly supports the development of agent-based systems and in particular cases where detailed socio-economic or geographical representations are required." @default.
• W3090334975 created "2020-10-08" @default.
• W3090334975 creator A5001424439 @default.
• W3090334975 creator A5031495928 @default.
• W3090334975 creator A5057934865 @default.
• W3090334975 date "2020-11-01" @default.
• W3090334975 modified "2023-09-30" @default.
• W3090334975 title "Prediction of rare feature combinations in population synthesis: Application of deep generative modelling" @default.
• W3090334975 cites W1498436455 @default.
• W3090334975 cites W1540435109 @default.
• W3090334975 cites W1988115241 @default.
• W3090334975 cites W2021887957 @default.
• W3090334975 cites W2029420412 @default.
• W3090334975 cites W2042492924 @default.
• W3090334975 cites W2045634204 @default.
• W3090334975 cites W2077860232 @default.
• W3090334975 cites W2103496339 @default.
• W3090334975 cites W2110555120 @default.
• W3090334975 cites W2119747081 @default.
• W3090334975 cites W2121097743 @default.
• W3090334975 cites W2144832675 @default.
• W3090334975 cites W2151233483 @default.
• W3090334975 cites W2155319430 @default.
• W3090334975 cites W2307838076 @default.
• W3090334975 cites W2345208044 @default.
• W3090334975 cites W2467664696 @default.
• W3090334975 cites W2563209634 @default.
• W3090334975 cites W2808127757 @default.
• W3090334975 cites W2894584319 @default.
• W3090334975 cites W2906813057 @default.
• W3090334975 cites W2958110591 @default.
• W3090334975 cites W2963565783 @default.
• W3090334975 cites W4206566734 @default.
• W3090334975 cites W4244837574 @default.
• W3090334975 doi "https://doi.org/10.1016/j.trc.2020.102787" @default.
• W3090334975 hasPublicationYear "2020" @default.
• W3090334975 type Work @default.
• W3090334975 sameAs 3090334975 @default.
• W3090334975 citedByCount "10" @default.
• W3090334975 countsByYear W30903349752020 @default.
• W3090334975 countsByYear W30903349752021 @default.
• W3090334975 countsByYear W30903349752022 @default.
• W3090334975 countsByYear W30903349752023 @default.
• W3090334975 crossrefType "journal-article" @default.
• W3090334975 hasAuthorship W3090334975A5001424439 @default.
• W3090334975 hasAuthorship W3090334975A5031495928 @default.
• W3090334975 hasAuthorship W3090334975A5057934865 @default.
• W3090334975 hasBestOaLocation W30903349752 @default.
• W3090334975 hasConcept C101738243 @default.
• W3090334975 hasConcept C103278499 @default.
• W3090334975 hasConcept C111030470 @default.
• W3090334975 hasConcept C115961682 @default.
• W3090334975 hasConcept C119857082 @default.
• W3090334975 hasConcept C124101348 @default.
• W3090334975 hasConcept C138885662 @default.
• W3090334975 hasConcept C144024400 @default.
• W3090334975 hasConcept C149923435 @default.
• W3090334975 hasConcept C154945302 @default.
• W3090334975 hasConcept C162324750 @default.
• W3090334975 hasConcept C167966045 @default.
• W3090334975 hasConcept C176217482 @default.
• W3090334975 hasConcept C17744445 @default.
• W3090334975 hasConcept C199539241 @default.
• W3090334975 hasConcept C21547014 @default.
• W3090334975 hasConcept C2776359362 @default.
• W3090334975 hasConcept C2776401178 @default.
• W3090334975 hasConcept C2908647359 @default.
• W3090334975 hasConcept C39890363 @default.
• W3090334975 hasConcept C41008148 @default.
• W3090334975 hasConcept C41895202 @default.
• W3090334975 hasConcept C50644808 @default.
• W3090334975 hasConcept C83665646 @default.
• W3090334975 hasConcept C9357733 @default.
• W3090334975 hasConcept C94625758 @default.
• W3090334975 hasConceptScore W3090334975C101738243 @default.
• W3090334975 hasConceptScore W3090334975C103278499 @default.
• W3090334975 hasConceptScore W3090334975C111030470 @default.
• W3090334975 hasConceptScore W3090334975C115961682 @default.
• W3090334975 hasConceptScore W3090334975C119857082 @default.
• W3090334975 hasConceptScore W3090334975C124101348 @default.
• W3090334975 hasConceptScore W3090334975C138885662 @default.
• W3090334975 hasConceptScore W3090334975C144024400 @default.
• W3090334975 hasConceptScore W3090334975C149923435 @default.
• W3090334975 hasConceptScore W3090334975C154945302 @default.
• W3090334975 hasConceptScore W3090334975C162324750 @default.
• W3090334975 hasConceptScore W3090334975C167966045 @default.
• W3090334975 hasConceptScore W3090334975C176217482 @default.
• W3090334975 hasConceptScore W3090334975C17744445 @default.
• W3090334975 hasConceptScore W3090334975C199539241 @default.
• W3090334975 hasConceptScore W3090334975C21547014 @default.
• W3090334975 hasConceptScore W3090334975C2776359362 @default.
• W3090334975 hasConceptScore W3090334975C2776401178 @default.
• W3090334975 hasConceptScore W3090334975C2908647359 @default.
• W3090334975 hasConceptScore W3090334975C39890363 @default.
• W3090334975 hasConceptScore W3090334975C41008148 @default.
• W3090334975 hasConceptScore W3090334975C41895202 @default.
• W3090334975 hasConceptScore W3090334975C50644808 @default.
• W3090334975 hasConceptScore W3090334975C83665646 @default.

• next