It is estimated that the Legal Amazon covers about 60% of the Brazilian territory and is home to 21 million inhabitants, 12% of the total population, of which 70% live in cities and towns, where high rates of deforestation are found in the northeast of the state. from Pará. This study presents a classification algorithm for degraded images using an image database provided by the State Secretariat for the Environment and Sustainability (SEMAS) to justify the objective of favorable conditions in the provision of environmental services in deforested areas using the computational implementation of learning machine in order to promote technological advancement through remote sensing.
Crime is a common social problem faced around the world, and it can affect a nation's quality of life, economic growth, and reputation. Thus, law enforcement officials need to take preventive measures and one of the methods that have been gaining ground in crime analysis is data mining. With this, the purpose of this paper is to apply data analysis and data mining techniques in public security databases in the city of Belém of Pará, in order to discover hidden patterns and assist security managers in developing new public policies to try to reduce crime rates, through data from police reports in the city of Belém of Pará, Brazil in the years 2019, 2020 and 2021. To guide this study, the CRISP-DM methodology was used, where it was possible through these techniques to extract knowledge to understand and analyze the crime scene in the municipality of Belém, such as the fact that a certain crime occurs at night implies that its nature is robbery in order to assist the responsible bodies in investigations and strategies for a more effective fight against crime.
To evaluate students in the area of computing, technological and computational resources are sought in order to analyze behavior, performance and difficulties of the students during their academic life. Thus, this study aims to analyze and explore POSCOMP microdata from 2016 to 2019 editions with data mining techniques, following the steps of KDD process, in order to extract useful information and non-trivial knowledge, with the aim of make the results available to managers, teachers and educational institutions, elucidating the performance and characteristics of students from computing courses in the state of Pará on the exam. The results show that the average scores of the applicants that dwell in the state of Pará remain lower or equal to the nacional ones throughout the period, either with respect to the overall grades and in regards to grades per subject, except for two subjects, it was also verified that the number of absentees in Pará has presented a drop since the 2017 edition, and the number of women enrolled in the exam on the state presented a rise since 2018, being different trends from the national ones.
This paper describes the development of a supervised classifier constructed upon knowledge extracted from police report public databases, in the years between 2019 and 2021 in the state of Pará, Brazil. The classifier achieved an accuracy of approximately 78% for the prediction of 463 unique labels related to public safety. The resulting model can be used to improve the statistical processes of criminal analysts, both in quantitative and qualitative terms.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.