A Data Mining Approach to Predict urban Fires in Lisbon using H2o.ai python Library

Bibliographic Details
Main Author: Quinta, Luís António Hill
Publication Date: 2022
Format: Master thesis
Language: eng
Source: Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
Download full: http://hdl.handle.net/10362/134984
Summary: Project Work presented as the partial requirement for obtaining a Master's degree in Information Management, specialization in Knowledge Management and Business Intelligence
id RCAP_e6b8f101f1efaac044344fcfb37eb649
oai_identifier_str oai:run.unl.pt:10362/134984
network_acronym_str RCAP
network_name_str Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
repository_id_str https://opendoar.ac.uk/repository/7160
spelling A Data Mining Approach to Predict urban Fires in Lisbon using H2o.ai python LibraryLisbonEmergency Incident PredictionUrban FiresPredictive ModellingH2oaiSDG 11 - Sustainable cities and communities. Target - 11.5 - By 2030, significantly reduce the number of deaths and the number of people affected and substantially decrease the direct economic lossesProject Work presented as the partial requirement for obtaining a Master's degree in Information Management, specialization in Knowledge Management and Business IntelligenceTechnologies have enabled societies to socially and economically prosper and to be more interconnected. With the decreasing cost of data storage and processing, cities are now trying to extract actionable information from the available data to improve and optimize their resource allocation and planning. This thesis aims to develop a data-mining approach to predicting urban fires in Lisbon, leveraging both climate, building, and population data available to predict where a fire will happen in the future within a particular period. To aid RSB in reducing their overall response time to fires by predicting probable positive emergency event areas and understand the driving factors that lead to these events in Lisbon. This supervised learning task developed using the CRISP-DM methodology makes use of standard machine learning estimators using the h2o.ai python module to incorporate parallel distributed computing combined with an AutoML package, evaluated using cross-validation, PR-AUC and F-0.5 score. The main conclusion from this paper is that applying predictive methods of data mining in the prediction of emergency events has a large potential to aid in resource allocation and understanding of drivers to combat emergency events, however requires large amounts of data to for algorithms to learn and extract actionable insights from their predictions.Neto, Miguel de Castro Simões FerreiraRUNQuinta, Luís António Hill2022-03-22T15:14:34Z2022-02-032022-02-03T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/10362/134984TID:202969576enginfo:eu-repo/semantics/openAccessreponame:Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)instname:FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologiainstacron:RCAAP2024-05-22T18:00:25Zoai:run.unl.pt:10362/134984Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireinfo@rcaap.ptopendoar:https://opendoar.ac.uk/repository/71602025-05-28T17:31:37.301809Repositórios Científicos de Acesso Aberto de Portugal (RCAAP) - FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologiafalse
dc.title.none.fl_str_mv A Data Mining Approach to Predict urban Fires in Lisbon using H2o.ai python Library
title A Data Mining Approach to Predict urban Fires in Lisbon using H2o.ai python Library
spellingShingle A Data Mining Approach to Predict urban Fires in Lisbon using H2o.ai python Library
Quinta, Luís António Hill
Lisbon
Emergency Incident Prediction
Urban Fires
Predictive Modelling
H2oai
SDG 11 - Sustainable cities and communities. Target - 11.5 - By 2030, significantly reduce the number of deaths and the number of people affected and substantially decrease the direct economic losses
title_short A Data Mining Approach to Predict urban Fires in Lisbon using H2o.ai python Library
title_full A Data Mining Approach to Predict urban Fires in Lisbon using H2o.ai python Library
title_fullStr A Data Mining Approach to Predict urban Fires in Lisbon using H2o.ai python Library
title_full_unstemmed A Data Mining Approach to Predict urban Fires in Lisbon using H2o.ai python Library
title_sort A Data Mining Approach to Predict urban Fires in Lisbon using H2o.ai python Library
author Quinta, Luís António Hill
author_facet Quinta, Luís António Hill
author_role author
dc.contributor.none.fl_str_mv Neto, Miguel de Castro Simões Ferreira
RUN
dc.contributor.author.fl_str_mv Quinta, Luís António Hill
dc.subject.por.fl_str_mv Lisbon
Emergency Incident Prediction
Urban Fires
Predictive Modelling
H2oai
SDG 11 - Sustainable cities and communities. Target - 11.5 - By 2030, significantly reduce the number of deaths and the number of people affected and substantially decrease the direct economic losses
topic Lisbon
Emergency Incident Prediction
Urban Fires
Predictive Modelling
H2oai
SDG 11 - Sustainable cities and communities. Target - 11.5 - By 2030, significantly reduce the number of deaths and the number of people affected and substantially decrease the direct economic losses
description Project Work presented as the partial requirement for obtaining a Master's degree in Information Management, specialization in Knowledge Management and Business Intelligence
publishDate 2022
dc.date.none.fl_str_mv 2022-03-22T15:14:34Z
2022-02-03
2022-02-03T00:00:00Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/masterThesis
format masterThesis
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://hdl.handle.net/10362/134984
TID:202969576
url http://hdl.handle.net/10362/134984
identifier_str_mv TID:202969576
dc.language.iso.fl_str_mv eng
language eng
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv reponame:Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
instname:FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologia
instacron:RCAAP
instname_str FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologia
instacron_str RCAAP
institution RCAAP
reponame_str Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
collection Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
repository.name.fl_str_mv Repositórios Científicos de Acesso Aberto de Portugal (RCAAP) - FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologia
repository.mail.fl_str_mv info@rcaap.pt
_version_ 1833596755967475712

Similar Items