Spatiotemporal sequence prediction with point processes and self-organizing decision trees

buir.contributor.authorKaraahmetoğlu, Oğuzhan
buir.contributor.authorSerdar Kozat, Süleyman
buir.contributor.orcidKaraahmetoğlu, Oğuzhan|0000-0002-0131-6782
buir.contributor.orcidSerdar Kozat, Süleyman|0000-0002-6488-3848
dc.citation.epage3110en_US
dc.citation.issueNumber6
dc.citation.spage3097 en_US
dc.citation.volumeNumber34
dc.contributor.authorKaraahmetoğlu, Oğuzhan
dc.contributor.authorSerdar Kozat, Süleymanen_US
dc.date.accessioned2022-03-04T13:19:24Z
dc.date.available2022-03-04T13:19:24Z
dc.date.issued2021-09-22
dc.departmentDepartment of Electrical and Electronics Engineeringen_US
dc.description.abstractWe study the spatiotemporal prediction problem and introduce a novel point-process-based prediction algorithm. Spatiotemporal prediction is extensively studied in machine learning literature due to its critical real-life applications, such as crime, earthquake, and social event prediction. Despite these thorough studies, specific problems inherent to the application domain are not yet fully explored. Here, we address the nonstationary spatiotemporal prediction problem on both densely and sparsely distributed sequences. We introduce a probabilistic approach that partitions the spatial domain into subregions and models the event arrivals in each region with interacting point processes. Our algorithm can jointly learn the spatial partitioning and the interaction between these regions through a gradient-based optimization procedure. Finally, we demonstrate the performance of our algorithm on both simulated data and two real-life datasets. We compare our approach with baseline and state-of-the-art deep learning-based approaches, where we achieve significant performance improvements. Moreover, we also show the effect of using different parameters on the overall performance through empirical results and explain the procedure for choosing the parameters.en_US
dc.description.provenanceSubmitted by Dilan Ayverdi (dilan.ayverdi@bilkent.edu.tr) on 2022-03-04T13:19:24Z No. of bitstreams: 1 Spatiotemporal_sequence_prediction_with_point_processes_and_self-organizing_decision_trees.pdf: 1744467 bytes, checksum: 3a6c435c3910332234f64deffb61d9e8 (MD5)en
dc.description.provenanceMade available in DSpace on 2022-03-04T13:19:24Z (GMT). No. of bitstreams: 1 Spatiotemporal_sequence_prediction_with_point_processes_and_self-organizing_decision_trees.pdf: 1744467 bytes, checksum: 3a6c435c3910332234f64deffb61d9e8 (MD5) Previous issue date: 2021-09-22en
dc.identifier.doi10.1109/TNNLS.2021.3111817en_US
dc.identifier.eissn2162-2388
dc.identifier.issn2162-237X
dc.identifier.urihttp://hdl.handle.net/11693/77686
dc.language.isoEnglishen_US
dc.publisherInstitute of Electrical and Electronics Engineersen_US
dc.relation.isversionofhttps://doi.org/10.1109/TNNLS.2021.3111817en_US
dc.source.titleIEEE Transactions on Neural Networks and Learning Systemsen_US
dc.subjectAdaptive decision treesen_US
dc.subjectCrime predictionen_US
dc.subjectEarthquake predictionen_US
dc.subjectHawkes processen_US
dc.subjectNonstationary time-series dataen_US
dc.subjectOnline learningen_US
dc.subjectSpatiotemporal point processen_US
dc.titleSpatiotemporal sequence prediction with point processes and self-organizing decision treesen_US
dc.typeArticleen_US

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Spatiotemporal_sequence_prediction_with_point_processes_and_self-organizing_decision_trees.pdf
Size:
1.64 MB
Format:
Adobe Portable Document Format