Matches in SemOpenAlex for { <https://semopenalex.org/work/W3013674851> ?p ?o ?g. }
Showing items 1 to 47 of
47
with 100 items per page.
- W3013674851 abstract "We focus in this work on predicting the next location of mobile users by analyzing large data sets of the history of their movements. We make use of past location sequences to train a classification model that will be used to predict future locations. Contrary to traditional mobility prediction techniques based on Markovian models, we investigate the use of modern deep learning techniques such as the use of Convolutional Neural Networks (CNNs). Inspired by the word2vec embedding technique used for the next word prediction, we present a new method called loc2vec in which each location is encoded as a vector whereby the more often two locations cooccur in the location sequences, the closer their vectors will be. Using the vector representation, we divide long mobility sequences into several sub-sequences and use them to form Mobility Subsequence Matrices on which we run CNN classification which will be used later for the prediction. We run extensive testing and experimentation on a subset of a large real mobility trace database made publicly available through the CRAWDAD project. Our results show that loc2vec embedding and CNN-based prediction provide significant improvement in the next location prediction accuracy compared to state-of-the-art methods. We also show that transfer learning on existing pretrained CNN models provides further improvement over CNN models build from scratch on mobility data. We also show that our loc2vec-CNN model enhanced with transfer learning achieves better results than other variants including our other proposal onehot-CNN and existing Markovian models." @default.
- W3013674851 created "2020-04-03" @default.
- W3013674851 creator A5033148767 @default.
- W3013674851 creator A5044156309 @default.
- W3013674851 creator A5044514578 @default.
- W3013674851 creator A5087889937 @default.
- W3013674851 date "2019-10-14" @default.
- W3013674851 modified "2023-09-27" @default.
- W3013674851 title "Location Embedding and Deep Convolutional Neural Networks for Next Location Prediction" @default.
- W3013674851 hasPublicationYear "2019" @default.
- W3013674851 type Work @default.
- W3013674851 sameAs 3013674851 @default.
- W3013674851 citedByCount "0" @default.
- W3013674851 crossrefType "proceedings-article" @default.
- W3013674851 hasAuthorship W3013674851A5033148767 @default.
- W3013674851 hasAuthorship W3013674851A5044156309 @default.
- W3013674851 hasAuthorship W3013674851A5044514578 @default.
- W3013674851 hasAuthorship W3013674851A5087889937 @default.
- W3013674851 hasBestOaLocation W30136748511 @default.
- W3013674851 hasConcept C108583219 @default.
- W3013674851 hasConcept C154945302 @default.
- W3013674851 hasConcept C41008148 @default.
- W3013674851 hasConcept C41608201 @default.
- W3013674851 hasConcept C81363708 @default.
- W3013674851 hasConceptScore W3013674851C108583219 @default.
- W3013674851 hasConceptScore W3013674851C154945302 @default.
- W3013674851 hasConceptScore W3013674851C41008148 @default.
- W3013674851 hasConceptScore W3013674851C41608201 @default.
- W3013674851 hasConceptScore W3013674851C81363708 @default.
- W3013674851 hasLocation W30136748511 @default.
- W3013674851 hasLocation W30136748512 @default.
- W3013674851 hasOpenAccess W3013674851 @default.
- W3013674851 hasPrimaryLocation W30136748511 @default.
- W3013674851 hasRelatedWork W2557924869 @default.
- W3013674851 hasRelatedWork W2731899572 @default.
- W3013674851 hasRelatedWork W2763109982 @default.
- W3013674851 hasRelatedWork W2999805992 @default.
- W3013674851 hasRelatedWork W3116150086 @default.
- W3013674851 hasRelatedWork W3133861977 @default.
- W3013674851 hasRelatedWork W3184130799 @default.
- W3013674851 hasRelatedWork W3192840557 @default.
- W3013674851 hasRelatedWork W4200173597 @default.
- W3013674851 hasRelatedWork W4220996320 @default.
- W3013674851 isParatext "false" @default.
- W3013674851 isRetracted "false" @default.
- W3013674851 magId "3013674851" @default.
- W3013674851 workType "article" @default.