Machine Learning for pattern detection and prediction of criminal occurrences

Detalhes bibliográficos
Autor(a) principal: Fonseca, Luís Miguel Marques
Data de Publicação: 2020
Tipo de documento: Dissertação
Idioma: eng
Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
Texto Completo: http://hdl.handle.net/10773/29209
Resumo: The increase of the world population, especially in large urban centers, has resulted in new challenges such as the management of natural resources and infrastructures as well as the optimization of services to promote the quality of citizens’ life. One of the biggest and most important challenges is the management of public safety, since, in addition to being a factor of interest to both the general population and the authorities, it is also an area that influences other essential indicators in a city such as tourism and employment. Public Safety has impact on the economic growth and social development of a community. This dissertation proposes a solution for the prediction of criminal occurrences in a city based on historical data of incidents and demographic data. The entire life cycle of the model’s learning process will be presented to provide an organization with predictive capability: start with the data collection from its original source, the treatment and transformations applied to them, the choice and the evaluation and implementation of the Machine Learning model up to the application layer. Classification models will be implemented to predict criminal risk for a given time interval and location, as well as regression models to predict the number of crimes. Machine Learning algorithms, such as Random Forest, Neural Networks, K-Nearest Neighbors and Logistic Regression will be used to predict occurrences, and their performance will be compared according to the data processing and transformation used. The results of the chosen model show that the use of Machine Learning techniques helps to anticipate criminal occurrences, which contributed to the reinforcement of public security. Finally, the models will be implemented on a platform that provides an API to enable other entities to request for predictions in real-time. An application will also be presented where it is possible to show criminal occurrences predictions visually.
id RCAP_f89ae9198970601c755a9eeddb7f6971
oai_identifier_str oai:ria.ua.pt:10773/29209
network_acronym_str RCAP
network_name_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository_id_str 7160
spelling Machine Learning for pattern detection and prediction of criminal occurrencesMachine learningCrime predictionSmart citiesBig dataThe increase of the world population, especially in large urban centers, has resulted in new challenges such as the management of natural resources and infrastructures as well as the optimization of services to promote the quality of citizens’ life. One of the biggest and most important challenges is the management of public safety, since, in addition to being a factor of interest to both the general population and the authorities, it is also an area that influences other essential indicators in a city such as tourism and employment. Public Safety has impact on the economic growth and social development of a community. This dissertation proposes a solution for the prediction of criminal occurrences in a city based on historical data of incidents and demographic data. The entire life cycle of the model’s learning process will be presented to provide an organization with predictive capability: start with the data collection from its original source, the treatment and transformations applied to them, the choice and the evaluation and implementation of the Machine Learning model up to the application layer. Classification models will be implemented to predict criminal risk for a given time interval and location, as well as regression models to predict the number of crimes. Machine Learning algorithms, such as Random Forest, Neural Networks, K-Nearest Neighbors and Logistic Regression will be used to predict occurrences, and their performance will be compared according to the data processing and transformation used. The results of the chosen model show that the use of Machine Learning techniques helps to anticipate criminal occurrences, which contributed to the reinforcement of public security. Finally, the models will be implemented on a platform that provides an API to enable other entities to request for predictions in real-time. An application will also be presented where it is possible to show criminal occurrences predictions visually.O aumento da população mundial, especialmente nos grandes centros urbanos, tem resultado em novos desafios tais como a gestão de recursos naturais, gestão de infraestruturas, bem como a otimização dos serviços para promover a qualidade de vida dos cidadãos. Um dos maiores e mais importantes desafios é a gestão da segurança pública. Para além de ser um fator de interesse quer da população em geral quer das autoridades, também é um domínio que influencia outros indicadores essenciais numa cidade como o turismo e o emprego. A segurança pública reflete-se no crescimento económico e no desenvolvimento social de uma comunidade. Nesta dissertação é proposta uma solução para previsão de ocorrências criminais numa cidade baseada em dados de histórico de incidentes e dados demográficos. Será apresentado todo o ciclo de vida do processo de aprendizagem do modelo para dotar uma organização da capacidade preditiva: desde a recolha dos dados da sua fonte de origem, o tratamento e transformações aplicadas aos mesmos, escolha, avaliação e implementação do modelo de Machine Learning até à camada de aplicação. Serão implementados modelos de classificação para previsão do risco criminal para um dado intervalo temporal e localização, e modelos de regressão para previsão do número de crimes. Irão ser utilizados algoritmos de Machine Learning como Random Forest, Redes Neuronais, K-Nearest Neighbors e Regressão Logística para a aprendizagem do modelo de previsão de ocorrências onde serão comparados os seus desempenhos de acordo com o tratamento e transformação dos dados utilizados. Os resultados do modelo escolhido evidenciam que a utilização de técnicas de Machine Learning auxiliam a antecipação de ocorrências criminais, o que contribuiu para o reforço da segurança pública. Por fim, irá ser procedida a implementação dos modelos numa plataforma que fornece uma API para que entidades externas possam solicitar previsões em tempo real. Será também apresentada a aplicação onde é possível mostrar visualmente as previsões de ocorrências criminais.2021-07-20T00:00:00Z2020-07-20T00:00:00Z2020-07-20info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/10773/29209engFonseca, Luís Miguel Marquesinfo:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2024-02-22T11:56:31Zoai:ria.ua.pt:10773/29209Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-20T03:01:36.329167Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse
dc.title.none.fl_str_mv Machine Learning for pattern detection and prediction of criminal occurrences
title Machine Learning for pattern detection and prediction of criminal occurrences
spellingShingle Machine Learning for pattern detection and prediction of criminal occurrences
Fonseca, Luís Miguel Marques
Machine learning
Crime prediction
Smart cities
Big data
title_short Machine Learning for pattern detection and prediction of criminal occurrences
title_full Machine Learning for pattern detection and prediction of criminal occurrences
title_fullStr Machine Learning for pattern detection and prediction of criminal occurrences
title_full_unstemmed Machine Learning for pattern detection and prediction of criminal occurrences
title_sort Machine Learning for pattern detection and prediction of criminal occurrences
author Fonseca, Luís Miguel Marques
author_facet Fonseca, Luís Miguel Marques
author_role author
dc.contributor.author.fl_str_mv Fonseca, Luís Miguel Marques
dc.subject.por.fl_str_mv Machine learning
Crime prediction
Smart cities
Big data
topic Machine learning
Crime prediction
Smart cities
Big data
description The increase of the world population, especially in large urban centers, has resulted in new challenges such as the management of natural resources and infrastructures as well as the optimization of services to promote the quality of citizens’ life. One of the biggest and most important challenges is the management of public safety, since, in addition to being a factor of interest to both the general population and the authorities, it is also an area that influences other essential indicators in a city such as tourism and employment. Public Safety has impact on the economic growth and social development of a community. This dissertation proposes a solution for the prediction of criminal occurrences in a city based on historical data of incidents and demographic data. The entire life cycle of the model’s learning process will be presented to provide an organization with predictive capability: start with the data collection from its original source, the treatment and transformations applied to them, the choice and the evaluation and implementation of the Machine Learning model up to the application layer. Classification models will be implemented to predict criminal risk for a given time interval and location, as well as regression models to predict the number of crimes. Machine Learning algorithms, such as Random Forest, Neural Networks, K-Nearest Neighbors and Logistic Regression will be used to predict occurrences, and their performance will be compared according to the data processing and transformation used. The results of the chosen model show that the use of Machine Learning techniques helps to anticipate criminal occurrences, which contributed to the reinforcement of public security. Finally, the models will be implemented on a platform that provides an API to enable other entities to request for predictions in real-time. An application will also be presented where it is possible to show criminal occurrences predictions visually.
publishDate 2020
dc.date.none.fl_str_mv 2020-07-20T00:00:00Z
2020-07-20
2021-07-20T00:00:00Z
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/10773/29209
url http://hdl.handle.net/10773/29209
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:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron:RCAAP
instname_str Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron_str RCAAP
institution RCAAP
reponame_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
collection Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository.name.fl_str_mv Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
repository.mail.fl_str_mv
_version_ 1799137671805665280