Ensemble methods for spatial data stream classification with application to emergency services

Simple item page
dc.contributor.authorBhattacharjee, Prasanta
dc.contributor.authorUniversity of Lethbridge. Faculty of Arts and Science
dc.contributor.supervisorOsborn, Wendy
dc.date.accessioned2024-12-05T20:34:57Z
dc.date.available2024-12-05T20:34:57Z
dc.date.issued2024
dc.degree.levelMasters
dc.description.abstractOur research investigates the application of ensemble methods for spatial data stream classification within emergency services, specifically severe weather events. Emergencies demand swift, accurate decisions to mitigate impacts and protect lives. Ensemble methods improve the accuracy of predictions by combining outputs from multiple neural networks, each trained on diverse aspects of the data, including geographic coordinates, weather data, spatial data, and logistical factors. These models collectively contribute to more precise decision-making, particularly in assessing evacuation priorities. We collected and generated relevant data for affected regions and evacuation centres pertinent to severe weather events. For class labeling data, we employed K-means and DBSCAN clustering techniques. Our findings show that the ensemble of neural networks significantly improves the classification accuracy of spatial data stream data, potentially leading to more effective emergency responses. Comprehensive experiments with streams containing both spatial and non-spatial data show the accuracy, precision, and recall of our proposed approach.
dc.embargoNo
dc.identifier.urihttps://hdl.handle.net/10133/6961
dc.language.isoen
dc.publisherLethbridge, Alta. : University of Lethbridge, Dept. of Mathematics and Computer Science
dc.publisher.departmentDepartment of Mathematics and Computer Science
dc.publisher.facultyArts and Science
dc.relation.ispartofseriesThesis (University of Lethbridge. Faculty of Arts and Science)
dc.subjectensemble methods
dc.subjectspatial data stream classification
dc.subjectemergency services
dc.subjectpredicting severe weather events
dc.subjectneural network ensembles
dc.subject.lcshDissertations, Academic
dc.subject.lcshEnsemble learning (Machine learning)
dc.subject.lcshSpatial data mining
dc.subject.lcshData mining
dc.subject.lcshEmergency management--Data processing
dc.subject.lcshEmergency communication systems--Technological innovations--Research
dc.subject.lcshNatural disaster warming systems--Technological innovations--Research
dc.subject.lcshNeural networks (Computer science)
dc.subject.lcshSevere storms--Forecasting--Research
dc.titleEnsemble methods for spatial data stream classification with application to emergency services
dc.typeThesis
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
BHATTACHARJEE_PRASANTA_MSC_2024.pdf
Size:
596.37 KB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
3.33 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Arts and Science, Faculty of
University of Lethbridge Theses