TCC - Bacharelado em Ciência da Computação (Sede)
URI permanente para esta coleçãohttps://arandu.ufrpe.br/handle/123456789/415
Navegar
87 resultados
Resultados da Pesquisa
Item An AMR-based extractive summarization method for cohesive summaries(2021) Silva, Pedro Assis Xavier; Lima, Rinaldo José de; Espinasse, Bernard; http://lattes.cnpq.br/7645118086647340; http://lattes.cnpq.br/0509757461700562The main goal of automatic text summarization is condensing the original text into a shorter version, preserving the information content and general meaning. The extractive summarization, one of the main approaches for automatic text summarization, consists to select the most relevant sentences of a document, and generate a summary. This paper proposes a new mono-document extractive summarization method using a semantic representation of the sentence of a document expressed in AMR (Abstract Meaning Representation). In this method, AMR semantic representation is used to capture the most important concepts of each sentence (in core semantic terms), and a concept-based Integer Linear Programming (ILP) approach to select the most informative sentences improving both relevance and text cohesion of the summary. Two datasets proposed by DUC (2001 and 2002) were used to evaluate the effectiveness of our method on extrative summarirazion and commparing it with other state-of-the-art summary systems.Item Smart Tour PE: um aplicativo android para monitoramento remoto de pontos turísticos no estado Pernambuco(2021-07-13) Fonsêca, Eder Lucena Andrade da; Araújo, Danilo Ricardo Barbosa de; http://lattes.cnpq.br/2708354422178489; http://lattes.cnpq.br/9564226085565142The tourism sector has been growing sustainably since the 90s, and not even the period of economic downturn at the time was able to stop it. In recent years, around 2018 and 2019, the sector was breaking new records of international arrivals, with the COVID19 pandemic being the only “disaster” capable of stopping this success streak. More than a year after the beginning of the pandemic, thanks to the medical advances allowing the creation of effective vaccines and viable means to return to normality, it is expected that the search for tourist destinations will grow again very soon, with ecotourism being pointed out as the most likely niche to be sought after. Therefore, it is important that technological solutions are made available to support tourism, especially ecotourism. This undergraduate thesis is the idealization of a tool to help tourists dynamically choose their next travel destination based on the location’s real time weather. Accurate information about the climate will ensure that tourists make the most of their leisure time, being able to visit a place that most suits them, from beaches to tree lined hiking trails in preservation areas, based on climate reports. The real time weather reports from tourist attractions will be displayed through an application idealized in this undergraduate thesis, designed to work on mobile devices with internet access. This application will use information from weather stations installed in tourist attractions in the state of Pernambuco during the execution of the research project related to this undergraduate thesis, also offering the user geolocation data, video streaming from local cameras, routes to access the desired location, as well as additional information about utility telephones and a panic buttons for emergencies. According to usability tests carried out with the target audience, only 3% of them considered the application difficult to use and 97% considered it easy or extremely easy to use. In addition, the application scored 75 points in the Net Promoter Score indicator, with the average for the tourism sector in Brazil being 70 points, additionally to several other positive indicators to be explained later.Item Formação de grupos de alunos baseada em múltiplos critérios(2021-05-27) Fiorentino Neto, Giuseppe; Miranda, Péricles Barbosa Cunha de; http://lattes.cnpq.br/8649204954287770; http://lattes.cnpq.br/6288849609186849Group formation is one of the main steps of the collaborative learning. This paper proposes an intelligent method to optimize the group formation process considering multiple criteria: inter-homogeneity, intra-heterogeneity and empathy. The method was evaluated regarding the performance, being compared to the exhaustive and random approaches; And regarding the pedagogical aspect, being compared with random and self-selected methods. The results showed the potential of the proposed method from the computational point of view as well as the pedagogical point of view.Item Semantic segmentation for people detection on beach images(2021-03-01) Monte, Leonardo de Araujo; Macário Filho, Valmir; http://lattes.cnpq.br/4346898674852080; http://lattes.cnpq.br/0547792731866043Cameras monitoring are increasingly aided by computer vision systems that identify risk situations. This work is part of an automatic track system to monitor beaches in the metropolitan area of Recife in order to prevent bathers to trespass the boundaries of the safe region for swimming. Semantic segmentation has gained strength in several computer vision tasks. Usually, the metaarchitecture of a semantic segmentation network consists of two modules: encoder (backbone) and decoder. This work does a study combining a set of semantic segmentation networks, Unet, Xnet, LinkNet and Unet++ with the pretrained backbones VGG16 and VGG19, to detect swimmners in beach images. We have used our own dataset, made by several images taken at the Boa Viagem beach, RecifeBrazil. The algorithms are evaluated with MIoU metric regarding the entire image scene and just in the water area. The best MIoU regarding all image was 80.87best MIoU in detecting swimmers at the beach was 85.56obtained by the LinkNet algorithm with both VGG16 and VGG19 backbones.Item Development of machine learning models for the prediction of dissolved oxygen in aquaculture 4.0(2021-02-24) Freitas, Fábio Alves de; Nóbrega, Obionor de Oliveira; Lins, Fernando Antonio Aires; http://lattes.cnpq.br/2475965771605110; http://lattes.cnpq.br/8576087238071129; http://lattes.cnpq.br/5725435192607619The world faces the problem of feeding a growing population, which will reach more than 9 billion people by 2050. Thus, there is a need to develop activities that promote food production, within the dimensions of sustainability (social, technicaleconomic, and environmental). In this context, IoT systems focused on aquaculture 4.0 stand out, which allows the cultivation of high productions per unit of volume, with low environmental impact. However, these systems need to be extremely controlled, requiring sensors to perform realtime readings of water metrics, with emphasis on the dissolved oxygen (DO) sensor, which plays an essential role in determining the quality and quantity of available habitat for the organisms present in the system. Even with this importance, this sensor is often not used, due to its high associated cost. As an alternative solution to this problem, machine learning models have been proposed to predict DO, using temperature and pH readings as inputs. Experiments were carried out comparing different data scaling techniques and the prediction performance in different seasons of the year and regression metrics were used to evaluate the implemented models. The results showed that the proposed LSTM model is capable of making OD predictions and being applied in IoT and aquaculture 4.0 systems.Item Security evaluation of operating systems considering compliance policies(2021-03-01) Teixeira, Vanessa Bandeira Lins; Lins, Fernando Antonio Aires; Nóbrega, Obionor de Oliveira; http://lattes.cnpq.br/8576087238071129; http://lattes.cnpq.br/2475965771605110; http://lattes.cnpq.br/9351392044969981Currently, to search, mitigate and solve security vulnerabilities is considered a relevant and complex task. New software are being developed everyday, and each one of them may bring its own vulnerabilities. In addition, the configurations of these applications can also increase these vulnerabilities. In this context, there is a lack of securityoriented configurations in a significant part of the current operating systems. These assets, which are usually not properly configured considering security requirements, become easy targets for a considered number of security attacks. The application of compliance policies in an operating system helps to preserve the environment from malicious exploitation. The main objective of this work is to evaluate the use of compliance policies to assess and improve the security level of operating systems. To achieve this, a methodology is proposed and described. This methodology is also applied to a case study with server operating systems. For this purpose, faults in the factory configuration of the operating systems were considered, which were identified using the Center for Internet Security (CIS) compliance policies. Thus, it became possible to evaluate the system security level and to classify the main recommendations for prioritizing the corrections that users can follow. Such recommendations aim to reduce the attacks surface on systems and increase the security level by mitigating the vulnerabilities to which the systems are exposed.Item Utilização de processamento de linguagem natural para identificação do domínio da escrita formal em redações da língua portuguesa(2020-12-07) Araujo, Viviane Barbosa de; Mello, Rafael Ferreira Leite de; http://lattes.cnpq.br/6190254569597745; http://lattes.cnpq.br/5293423783550464In Brazil, the main means of entering a public or private university is through the National High School Exam, ENEM. This exam requires that the candidate has the ability to write a good dissertation-argumentative text according to the formal norm of the Portuguese language, and can be eliminated from the exam if he does not fulfill this requirement. In order to help the candidate to identify his mistakes and help in the process of writing a good essay, this article proposes the implementation of a tool capable of identifying the spelling and grammatical errors of a text using techniques of Natural Language Processing (PLN). The analysis of the tools showed that the results obtained by the research are promising, mainly in relation to the identification of grammatical errors.Item Uma revisão sistemática sobre avaliação do consumo de energia em nuvem das coisas(2021-12-10) Ferreira, Emerson Severino de Oliveira Ramos; Sousa, Erica Teixeira Gomes de; http://lattes.cnpq.br/9899077867723655; http://lattes.cnpq.br/9000455288391839IoT devices are used in many types of vertical industries and consumer markets. In 2020 there were around 8 billion devices connected around the world, and the forecast for 2030 is to have more than 25 billion devices connected. Furthermore, the world market for IoT devices in the government area alone will transact around $21 billion in 2022, where more than 50% of that amount will be for external surveillance equipment. Which represents a 36% increase in comparison with 2020. Nowadays, research is heading towards the integration of Cloud Computing and the Internet of Things (IoT), thus creating the concept of Cloud of Things (CoT). CoT aims to offer computational resources in a pervasive and ubiquitous way, in which IoT characteristics are available as services through Cloud Computing. In CoT, Cloud acts as a middleware that makes the interaction between objects (Things) and users/applications in a transparent way, eliminating the complexity which facilitates the development of applications that interact with smart objects, which facilitate their utilization in areas as Healthcare, Smart Cities, Smart Home, Video Surveillance, Smart Mobility, Smart Energy and others.In CoT environments, a large amount of communication and data transmission affected by IoT devices degrade the energy efficiency of these environments, affecting the quality of services. In this way, this work describes a systematic review the strategies for evaluating the energy consumption in Cloud of Things. This systematic review aims to bring together published studies related to energy consumption assessment in IoT and Cloud of Things, for an analysis of the methodologies employed in these works and proposition of future work, about cloud of things energy consumption assessment.Item Virtualização de jogos tradicionais para aprendizagem de matemática: uma avaliação do jogo Cubra Doze em versão digital(2019-01-18) Silva, Ana Carolina Santos; Falcão, Taciana Pontual da Rocha; http://lattes.cnpq.br/5706959249737319; http://lattes.cnpq.br/0794195512627295The current research is guided by the growing use of games in education, as a teaching methodology that joins fun, logical reasoning, strategic planning, among other aspects. Prior to the Digital Era, physical games were already used in Math teaching, helping to develop students’ skills. With the increasing ubiquity of technological devices in people’s daily lives, especially the new generations, using digital technology in education is an inevitable trend. Therefore, in order to approximate the positive results of traditional games in teaching and the growing demand and interest of children and young people for digital games, this research aims to analyze the contributions of a digital game about the four Mathematics basic operations. In order to do this, the game called Cubra Doze was transformed into a digital version and an analysis was made considering the engagement and impact of the Human-Computer Interaction aspects in the user experience. After the game virtualization process, a case study was conducted with 32 students in the 1st year of High School to gauge the motivation and interaction with it. Notes registered while students were playing and an educational games evaluation questionnaire were used as instruments. The game was also evaluated based on 25 usability heuristics by 11 experts. The results revealed there are possibilities for improvements in the game’s usability, therefore it was verified there were positive outcomes related to the engagement in learning through a digital game as well as the collaboration and educational content attached to it, demonstrating how games are good educational tools to support learning.Item Como a (in)felicidade impacta nos engenheiros de software em ambientes ágeis?(2019-12-04) Amorim, Luís Felipe Cavalcanti de; Marinho, Marcelo Luiz Monteiro; http://lattes.cnpq.br/3362360567612060; http://lattes.cnpq.br/6498416955849459Given a scenario where IT organizations are increasing the use of agile practices, which is based on a people-centered culture along software development process, it is important to understand the social and human factors linked to those individuals, such as happiness and unhappiness and how these factors impact on this kind of environment. Therefore, 5 case-studies were developed inside agile projects, in a company that values innovation, aiming to identify how (un)happiness impacts on software engineers in agile environments. According to the answers gathered from 67 participants through a survey and using a cross-analysis, (un)happiness characteristics were identified as anxiety and frustration on younger respondents and unhappy ones, and high satisfaction and collaboration on happier ones.