Matches in SemOpenAlex for { <https://semopenalex.org/work/W3117201166> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W3117201166 abstract "Intelligent transportation management requires not only statistical information on users' mobility patterns, but also knowledge of their selected transportation modes. The latter can be inferred from users' GPS records, as captured by smartphone or vehicle sensors. The recently demonstrated prevalence of deep neural networks in learning from data makes them a promising candidate for transportation mode identification. However, the massive geospatial data produced by GPS sensors are typically unlabeled. To address this problem, we propose an unsupervised learning approach for transportation mode identification. Specifically, we first pretrain a deep Convolutional AutoEncoder (CAE) using unlabeled fixed-size trajectory segments. Then, we attach a clustering layer to the CAE's embedding layer, the former maintaining cluster centroids as trainable weights. Finally, we retrain the composite clustering model, encouraging the encoder's learned representation of the input data to be clustering-friendly by striking a balance between the model's reconstruction and clustering losses. By further incorporating features computed over each segment, we achieve a clustering accuracy of 80.5% on the Geolife dataset without using any labels. To the best of our knowledge, this is the first work to leverage unsupervised deep learning for clustering of GPS trajectory data by transportation mode." @default.
- W3117201166 created "2021-01-05" @default.
- W3117201166 creator A5076130415 @default.
- W3117201166 creator A5077589061 @default.
- W3117201166 date "2020-09-20" @default.
- W3117201166 modified "2023-09-25" @default.
- W3117201166 title "Unsupervised Deep Learning for GPS-Based Transportation Mode Identification" @default.
- W3117201166 cites W1967807710 @default.
- W3117201166 cites W2020642377 @default.
- W3117201166 cites W2100495367 @default.
- W3117201166 cites W2136317921 @default.
- W3117201166 cites W2143394441 @default.
- W3117201166 cites W2222512263 @default.
- W3117201166 cites W2535078255 @default.
- W3117201166 cites W2603986758 @default.
- W3117201166 cites W2609649633 @default.
- W3117201166 cites W2797767624 @default.
- W3117201166 cites W2883725317 @default.
- W3117201166 cites W2906257585 @default.
- W3117201166 cites W2911968972 @default.
- W3117201166 cites W2956324374 @default.
- W3117201166 cites W2962852342 @default.
- W3117201166 cites W616026467 @default.
- W3117201166 doi "https://doi.org/10.1109/itsc45102.2020.9294673" @default.
- W3117201166 hasPublicationYear "2020" @default.
- W3117201166 type Work @default.
- W3117201166 sameAs 3117201166 @default.
- W3117201166 citedByCount "3" @default.
- W3117201166 countsByYear W31172011662021 @default.
- W3117201166 countsByYear W31172011662022 @default.
- W3117201166 crossrefType "proceedings-article" @default.
- W3117201166 hasAuthorship W3117201166A5076130415 @default.
- W3117201166 hasAuthorship W3117201166A5077589061 @default.
- W3117201166 hasConcept C101738243 @default.
- W3117201166 hasConcept C108583219 @default.
- W3117201166 hasConcept C116834253 @default.
- W3117201166 hasConcept C119857082 @default.
- W3117201166 hasConcept C124101348 @default.
- W3117201166 hasConcept C127413603 @default.
- W3117201166 hasConcept C147176958 @default.
- W3117201166 hasConcept C153083717 @default.
- W3117201166 hasConcept C153180895 @default.
- W3117201166 hasConcept C154945302 @default.
- W3117201166 hasConcept C41008148 @default.
- W3117201166 hasConcept C47796450 @default.
- W3117201166 hasConcept C59404180 @default.
- W3117201166 hasConcept C59822182 @default.
- W3117201166 hasConcept C60229501 @default.
- W3117201166 hasConcept C73555534 @default.
- W3117201166 hasConcept C76155785 @default.
- W3117201166 hasConcept C8038995 @default.
- W3117201166 hasConcept C81363708 @default.
- W3117201166 hasConcept C86803240 @default.
- W3117201166 hasConceptScore W3117201166C101738243 @default.
- W3117201166 hasConceptScore W3117201166C108583219 @default.
- W3117201166 hasConceptScore W3117201166C116834253 @default.
- W3117201166 hasConceptScore W3117201166C119857082 @default.
- W3117201166 hasConceptScore W3117201166C124101348 @default.
- W3117201166 hasConceptScore W3117201166C127413603 @default.
- W3117201166 hasConceptScore W3117201166C147176958 @default.
- W3117201166 hasConceptScore W3117201166C153083717 @default.
- W3117201166 hasConceptScore W3117201166C153180895 @default.
- W3117201166 hasConceptScore W3117201166C154945302 @default.
- W3117201166 hasConceptScore W3117201166C41008148 @default.
- W3117201166 hasConceptScore W3117201166C47796450 @default.
- W3117201166 hasConceptScore W3117201166C59404180 @default.
- W3117201166 hasConceptScore W3117201166C59822182 @default.
- W3117201166 hasConceptScore W3117201166C60229501 @default.
- W3117201166 hasConceptScore W3117201166C73555534 @default.
- W3117201166 hasConceptScore W3117201166C76155785 @default.
- W3117201166 hasConceptScore W3117201166C8038995 @default.
- W3117201166 hasConceptScore W3117201166C81363708 @default.
- W3117201166 hasConceptScore W3117201166C86803240 @default.
- W3117201166 hasLocation W31172011661 @default.
- W3117201166 hasOpenAccess W3117201166 @default.
- W3117201166 hasPrimaryLocation W31172011661 @default.
- W3117201166 hasRelatedWork W2592385986 @default.
- W3117201166 hasRelatedWork W2775464024 @default.
- W3117201166 hasRelatedWork W2784313445 @default.
- W3117201166 hasRelatedWork W2908875379 @default.
- W3117201166 hasRelatedWork W3044458868 @default.
- W3117201166 hasRelatedWork W4213225422 @default.
- W3117201166 hasRelatedWork W4221136938 @default.
- W3117201166 hasRelatedWork W4306194456 @default.
- W3117201166 hasRelatedWork W4367623604 @default.
- W3117201166 hasRelatedWork W564581980 @default.
- W3117201166 isParatext "false" @default.
- W3117201166 isRetracted "false" @default.
- W3117201166 magId "3117201166" @default.
- W3117201166 workType "article" @default.