TCC - Bacharelado em Ciência da Computação (Sede)
URI permanente para esta coleçãohttps://arandu.ufrpe.br/handle/123456789/415
Navegar
Item Abordagem híbrida e independente de domínio para extração de aspectos na análise de sentimentos(2018) Lins, André Lucas Machado; Lima, Rinaldo José de; http://lattes.cnpq.br/7645118086647340; http://lattes.cnpq.br/3233947254235611Opinions are central in most of the human activities and are keys of influence to our behaviors. Our beliefs, perception of reality and our choices are in a considerable degree, influenced by how people see and evaluate the world. In view of this statement theSentimentAnalysis(SA)hasbeengrowingconstantly,thepossibilityofunderstand people’sfeelingsandopinionsaboutcertainsubjectsgetseveryoneexcited.Sentiment Analysisisthecomputationalstudyofpeople’sopinions,attitudesandemotionsabout some entity. The literature about Sentiment Analysis is pretty wide, having too many ways of execute such tasks. A variation of SA called Aspect based Sentiment Analysis (ABSA) has been receiving researchers attention. In this approach feelings are identified in relation to sentence aspects, in order to discern those that are treated in eachsentenceordocument.ABSAisdividedinthreemajortaskswhicharetheextraction,classificationandaggregationoftheaspect,havingaspectextractionasthemost complextask.There’sseveralapproachestosolvetheaspectextractiontask,although manyoftheseapproachesaredomaindependent,makingdifficulttoreplicatetheseapproaches to domains that does not have the same features. Therefore, this work aims topurposeadomainindependenthybridmethodtoaspectsextraction,thatconsistsin fourmajorsteps.Thefirstoneidentifyallthepossibleaspectsoutofsemanticrulesfor eachsentence.Afterthisstep,willbegeneratedalexicalofallthesentenceshavingthe aspectsandmostrelevantfeelings.Inthefollowstepismadethepruningofpossibleaspectsusingsemanticrulesthroughthelexicalofaspectsandfeelingsmadepreviously. Lastly,ismadeaselectionamongtheremainingaspectsbyadynamicthreshold.This purpose was evaluated in the Semeval’s dataset, containing opinions about several aspects related to restaurants and laptops, using the most adopted evaluation metrics in literature. The experimental results imply that the proposed method is competitive when it’s compared to many other methods dependents and independents of state of art domain.Item Uma abordagem para tradução de uma linguagem de programação de robôs para um modelo formal(2018) Pereira, Iverson Luís; Nogueira, Sidney de Carvalho; http://lattes.cnpq.br/9171224058305522; http://lattes.cnpq.br/1186672408246777There is an increasing interest in virtual robot programming environments for educational purposes in recent years. These environments are an alternative to the use of real robots, which have a high acquisition value. Automatic verification of robot programs is a demand of students and teachers that expect to have fast and automatic feed back about the correctness of robot programs.However,no free software provides an automatic verification of virtual robot programs. This work proposes an approach for the automatic verification of virtual robot programs authored in the educational language called ROBO. We propose a compiler that reads programs written in ROBO and translates its source code into a formal notation called CSP (Communicating Sequential Processes), which is the input to a model checking tool called FDR (FailuresDivergences Refinement). The compiler was implemented using the facilities of the Spoofax framework, which is used to define a parser for the ROBO language and a set of translation rules from ROBO to CSP. This work removes a limitation of our previous verification approach that does not perform the verification of ROBO programs containing variables and procedures. A significant contribution is the extension of the verification approach to allow the automatic analysis of ROBO programs with variables and procedures.The extension consists of the modification of the compiler Grammar by the inclusion of variables and procedures and the inclusion of translation rules that define the formal semantics for the elements added into the grammar.Moreover, the work proposes a tool that makes transparent the translation process from ROBO to CSP and the automatic verification using FDR.We validate the approach using the proposed tool to verify the behavior of a ROBO program with variables and procedures.Item Aligning expectations about the adoption of learning analytics in a brazilian higher education institution(2021-03-01) Garcia, Samantha Millena Costa; Falcão, Taciana Pontual da Rocha; http://lattes.cnpq.br/5706959249737319; http://lattes.cnpq.br/7221410090403436Learning Analytics (LA) consists of using educational data to inform teaching strategies and management decisions, aiming to improve students’ learning. The successful implementation of LA in Higher Education Institutions (HEI) involves technical aspects and infrastructure and, but also, and very importantly, stakeholders’ acceptance. The SHEILA framework proposes instruments for diagnosis of HEI for LA adoption, including stakeholders’ views. In this paper, we present the results of the application of SHEILA’s surveys adapted to the Brazilian context, to identify the most and least important aspects in the views of students and instructors, and compare their ideal and realistic expectations about the adoption of LA. Results confirm the high interest in using LA for improving the learning experience, but with ideal expectations higher than realistic expectations, and point out key challenges and opportunities for Latin American researchers to join efforts towards building solid evidence that can inform educational policymakers and managers, and support the development of strategies for LA services in the region.Item Alocação dinâmica de recursos para URLLC em redes 5G NFV-MEC(2020-11-03) Souza, Caio Bruno Bezerra de; Araújo, Danilo Ricardo Barbosa de; Balieiro, Andson Marreiros; http://lattes.cnpq.br/9825617657358787; http://lattes.cnpq.br/2708354422178489; http://lattes.cnpq.br/5915479506163386The Fifth Generation of mobile networks (5G) seeks to support a diversity of applications categorized into three types: enhanced Mobile Broadband (eMBB), massive Machine Type Communications (mMTC) and Ultra Reliable Low Latency Communications (URLLC), where the latter is perhaps the most challenging due to its endtoend latency restrictions (few milliseconds), low probability of packet loss and high network availability, which are not reachable in today’s mobile networks. As in previous generations, much of the research effort has focused on the Radio Access Network (RAN), with the 5G core often assumed to be similar in operation to that of common data centers, although it is clear that they may not be able to handle the requirements of URLLC services. Support for URLLC applications in MultiAccess Edge Computing (MEC) environments using Network Functions Virtualization (NFV) brings challenges, in which different aspects must be considered. This work seeks to analyze the provisioning of resources for URLLC services in 5G networks based on MECNFV, considering the time of configuration / initialization of the Virtualized Network Function (VNF), the possibility of failure during service, associated with the preinitialization technique resources, determining the limits of how minimally performance the URLLC resource provisioning should be. For this purpose, an analytical model based on queue theory and validated via a simulator developed in a Colored Petri Net was proposed in this monograph and the average response time, the probability of blocking and the average number of active resources are analyzed under different service arrival rates, resource startup rates, maximum system capacity, number of resources (containers) and number of preinitialized containers. From this it was observed that the effect of the lower setup rate can be mitigated by the preinitialization of containers, reducing the waiting time for service delivery.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 Analisando a presença feminina no Ensino Superior em Tecnologia no Brasil ao longo dos anos de 2013 a 2022(2024-03-07) Ramos, Giuliane Benjamim de Oliveira; Alencar, Andrêza Leite de; Furtado, Ana Paula Carvalho Cavalcanti; http://lattes.cnpq.br/5862330768739698; http://lattes.cnpq.br/6060587704569605; http://lattes.cnpq.br/6421196285147828Masculine stigma, low family encouragement, and lack of representation are the main factors that justify the underrepresentation of women in the technology field. Therefore, this paper aims to highlight the current female landscape in Information Technology (IT) higher education courses in Brazil. To achieve this purpose, a literature review and analysis of microdata from the Higher Education Census from 2013 to 2022, provided by the National Institute for Educational Studies and Research An´ısio Teixeira (INEP), were conducted. The analysis shows significantly low female representation in higher education technology courses over the analyzed period - female enrollments do not exceed 17%, the completion rate averages 15%, and the Southeast region has the highest number of female representatives in IT courses, with São Paulo standing out. However, a trend of increase can be observed in the last two years.Item Análise da acessibilidade para pessoas com deficiência visual e auditiva em redes sociais(2024-10-01) Lima, Thiago Ferreira de; Falcão, Taciana Pontual da Rocha; http://lattes.cnpq.br/5706959249737319; http://lattes.cnpq.br/5181649435278623Item Análise da evasão no ensino superior: predição e prevenção por meio da mineração de dados educacionais(2024-03-05) Ferreira, Rodolfo André Barbosa; Mello, Rafael Ferreira Leite de; http://lattes.cnpq.br/6190254569597745; http://lattes.cnpq.br/2982020271806247Considering that dropout occurs due to abandonment, transfer, or withdrawal from the course; when the student disengages from the institution they are enrolled in or when the student definitively abandons or does not complete higher education, this article seeks to identify methods and automated techniques to assist managers in preventing dropout cases through predictions. To conduct the study, Educational Data Mining (EDM) was used, which applies data mining techniques such as database, statistics, and machine learning in education. Data from 5144 students with characteristics related to course, semester, and demographics were used from the database provided by the Academic Information and Management System (SIGA) of the Federal Rural University of Pernambuco (UFRPE) for the courses of Animal Science, Fisheries Engineering, and Agronomy. The data, except for those containing personal, restricted, and sensitive information, were separated into Academic Characteristics per Semester, General Academic Characteristics, Course-related, Demographic, and Target Characteristics. The study employs the LSTM machine learning algorithm and the SGD and Adam optimizers, exploring different values for the parameters of learning rate, momentum, batch size, and number of epochs.Item Análise de dados de coinfecção tuberculose/HIV disponíveis no SINAN utilizando o banco de dados Neo4J(2023-04-27) Dias Neto, José Bartolomeu Alheiros; Melo, Jeane Cecília Bezerra de; Freitas, Nara Suzy Aguiar de; http://lattes.cnpq.br/6891650997818766; http://lattes.cnpq.br/8499459630583005; http://lattes.cnpq.br/5415193488789338Research carried out in recent decades indicates the need to investigate infection processes by multiple pathogens, called co-infection processes. Some coinfections have a worldwide reach, involving diseases such as: HIV, malaria, hepatitis, dengue and, more recently, COVID-19. In a study carried out with 500 volunteers carrying the HIV virus (Human Immunodeficiency Virus), it was observed that the coinfection between the HIV virus and MTB (Mycobacterium tuberculosis), the bacterium that causes tuberculosis, produced an increase in the chance of death by 4.07 times when compared to other types of co-infection. The panorama presented indicates the need for studies to identify occurrences, map their incidence in geographic terms, and even include aspects that favor the understanding of the biological mechanisms involved in co-infection processes, whether for prevention, diagnosis or treatment. In Brazil, an instrument that helps in health planning, defining and evaluating the impact of interventions, is the Information System for Notifiable Diseases – SINAN, made available by the Department of Informatics of the SUS (DATASUS). The effective use of these databases makes it possible to identify the epidemiological reality of a given geographic area. Free access to all health professionals corroborates the democratization of access to information, allowing it to be made available to the community. In this work, an exploratory analysis was carried out on data relating to TB and HIV co-infection processes, coming from SINAN, with the objective of proposing methods that facilitate the use of data from this system by health professionals who do not have technical training in computing. Considering that such an application is strongly based on data relationships, it was decided to propose a mapping of data in unconventional databases, oriented to graphs, such as Neo4J. Thus, in addition to simplifying modeling, applications of this type tend to be faster when compared to traditional applications (using relational databases). Therefore, the mapping of data available at SINAN to Neo4J allowed a more perceptible visualization of correlations, enabling an analysis of multiple factors and characteristics of co-infection processes, enhancing the information obtained from the bases of SINAN and the Tabulation System of Data made available by the agency, TABNET.Item Análise de desempenho e de disponibilidade do Ambiente Virtual de Aprendizagem na Nuvem Privada Apache CloudStack(2019) Silva, Alison Vinicius Gomes da; Callou, Gustavo Rau de Almeida; http://lattes.cnpq.br/3146558967986940; http://lattes.cnpq.br/8010059314855618Item Análise de envelhecimento de software em uma plataforma de Blockchain(2022-05-04) Silva, Douglas Dias da; Andrade, Ermeson Carneiro de; http://lattes.cnpq.br/2466077615273972; http://lattes.cnpq.br/5082801636483279Software aging is a phenomenon that plagues many long-running complex computer systems, which exhibit performance degradation or an increasing failure rate. Such a phenomenon may also be present in blockchain platforms. However, there are still no works focused on analyzing this phenomenon on these platforms. Thus, we adopted the Cardano blockchain to analyze software aging due to the presence of this technology in critical projects, its open-source nature and for being a sustainable solution. Considering the analysis of running a Cardano node on two computers with different configurations, we found evidence of software aging through memory degradation that was confirmed by the Mann-Kendall test. By analyzing the running processes, we confirmed that cardanonode (the main process of the platform) is the process possibly responsible for such degradation.Item Análise de sentimentos de tweets relacionados a vacinas antes e durante a pandemia da COVID-19 no Brasil(2023-03-01) Silva, Íkaro Alef de Lima; Andrade, Ermeson Carneiro de; http://lattes.cnpq.br/2466077615273972; http://lattes.cnpq.br/7938306473921402In early 2020, the COVID-19 disease spread rapidly around the world and one of the ways to fight it is the vaccine. Governments faced problems with fake news and anti-vaccination groups. Thus, it is necessary to understand the feelings of the population in order to propose efficient public policies. This article describes a sentiment analysis on vaccine-related tweets in Brazil from June 2020 to June 2021. The results revealed peaks in total tweets in January and May 2021, the predominance of positive tweets, and feelings of confidence, fear, submission and sadness. They are also associated with former President Jair Bolsonaro. The negative polarity was the least common, showing that the Brazilian population was receptive to vaccines.Item Análise de um sistema de recomendação de restaurantes sensível ao contexto sobre o grau de satisfação dos usuários(2023-09-01) Melo Filho, Carlos Olimpio Rodrigues de; Silva, Douglas Véras e; http://lattes.cnpq.br/2969243668455081; http://lattes.cnpq.br/6986499479035317Popular applications of recommender systems can be found in many areas. In the food business, platforms such as TripAdvisor stand out for suggesting specialized restaurant recommendations based on various types of relevant information, such as reviews from other users for the menu, atmosphere and recommendations for the closest restaurants are some of the specialties of these platforms. With the possibility of using new data sensitive to the user’s context, the main objective of this work is to evaluate the usage of the reason of going to the restaurant to reorganize the final restaurants recommendation through a context-based post-filtering. To achieve the goal, a mobile application was developed, the SR Recife Restaurants, to assess the degree of satisfaction of real users to the recommended restaurants, an online evaluation approach, using questionnaires, was used. When carrying out the experiment with 15 users, it was possible to notice an increase of 26.67% in the degree of satisfaction of the top-5 first recommendations when using the trip type to the restaurant as context data for the post-filtering phase.Item Uma análise do impacto da experiência prévia com pensamento computacional no desempenho de estudantes em programação no ensino superior(2019) Silva, Emanuel Leite Oliveira da; Falcão, Taciana Pontual da Rocha; http://lattes.cnpq.br/5706959249737319; http://lattes.cnpq.br/5886730483799524This paper aims to study the effect of previous contact with Computational Thinking instudents of higher education courses. Computational Thinking is a skill that aims to de-velop logical thinking and algorithmic thinking on an ongoing and lifelong basis, helpingthem to solve personal and professional life problems using the techniques of computer science. According to research, more than 50% of students in computer courses willdrop out of the course and one of the main reasons is the difficulty in learning and as-similating the basic and advanced concepts of programming, becoming unmotivated.Thus, this work investigated the feasibility of using computational thinking to help thosestudents with programming learning difficulties. Therefore, two student profiles wereidentified, who had contact with Computational Thinking before and after attending Pro-gramming, and questionnaires were applied to evaluate the perspectives they had onthedisciplineanditsbenefit,whethertheuseofComputationalThinkingwasproductiveor not. Two teachers from the UFRPE Computer Degree course were also interviewedto examine their perspective on Computational Thinking on student performance, com-paring students who had contact before and after attending Programming. From thestudents’ perspective, the use of Computational Thinking assists them in cognitive de-velopment, improving logical thinking and algorithmic thinking, and programming learn-ing. Teachers believe that Computational Thinking cognitively prepares students forProgramming, reducing the effort to assimilate the basics and seeing this approach asan improvement for students.Item Uma análise do impacto das linguagens de programação nos custos de execução no AWS Lambda em cenários de cold start e warm start(2023-04-24) Andrade Júnior, Edilson Alves de; Medeiros, Robson Wagner Albuquerque de; http://lattes.cnpq.br/3169193612606500; http://lattes.cnpq.br/5131828050788518Public cloud computing solutions have gained visibility on the market for offering great advantages over on-premises systems. However, cloud-based management workflows also brings concerns. As well as problems related to information security and lack of skilled professionals, cost management is one of the main challenges faced by users and organizations that migrate or already have their operations on cloud. Cloud providers define variables that directly affect cost behaviors, in addition, factors such as key characteristics of programming languages can also contribute to change those behaviors. This work aimed to understand how programming languages behave in cloud services such as AWS Lambda, so that cost management is carried out more assertively and efficiently, directly contributing to the reduction of costs and financial waste when using this kind of service. The results showed that the characteristics of programming languages significantly interfere in the financial costs of execution, elucidating that the choice of a certain programming language should be considered when cost is a requirement to be met when using AWS Lambda.Item Análise e predição nas votações de leis federais na Câmara dos Deputados(2022-05-27) Brito, Ranniery Dias de; Brito, Kellyton dos Santos; http://lattes.cnpq.br/8750956715158540; http://lattes.cnpq.br/1061900830319137This study aims to analyze machine learning algorithms and deep learning for the task of predictability of approval of bills. It follows a post-positivist approach, adopting the quali-quantitative paradigm as a methodology. In the search for results, experiments were carried out using the available data on the Portal of the Chamber of Deputies, following the steps of bibliographic review, definition of experimentation environment, descriptive analysis and prediction. It was also sought to do a descriptive analysis and to predict possible outcomes in the voting process of legislative proposals focusing on bills that have been voted.Item Aplicação de métodos ágeis em desenvolvimento global de software(2021-07-22) Alves, Annelyelthon Ferreira; Marinho, Marcelo Luiz Monteiro; http://lattes.cnpq.br/3362360567612060; http://lattes.cnpq.br/8410367808658970Global Software Development (GSD) continues to grow and is rapidly becoming a standard, fundamentally different from local Software Engineering development. Withal, agile software development (ASD) has become an appealing choice for companies attempting to improve their performance although its methods were originally designed for small and individual teams. The current literature does not provide a cohesive picture of how the agile practices are taken into account in the distributed nature of software development: how to do it, who, and what works in practice. This study aims to highlight how ASD practices are applied in the context of GSD in order to develop a set of techniques that can be relevant in both research and practice. To answer the research question, ”how are agile practices adopted in agile global software development teams?” We conducted a systematic literature review and a survey with practitioners of the ASD and GSD literature. A synthesis of solutions found in seventysix studies provided 48 distinct practices that organizations can implement, including ”collaboration among teams”, ”agile architecture”, ”coaching”, ”system demo” and ”test automation”. These implementable practices go some way towards providing solutions to manage GSD teams, and thus to embrace agility.Item Aplicação do processo de design no desenvolvimento de um produto de software para suporte à inovação social(2018) Santos, Juliana Ferreira dos; Souza, Ricardo André Cavalcante de; http://lattes.cnpq.br/7101881357139219; http://lattes.cnpq.br/8780029383567585Innovation can be described as a good Idea of solving a relevant problem implemented. Social Innovation is na innovation that at the same time meets a social need and creates new relationships or social collaborations. Social innovations of high impact and high scalability are generally aided by ICT(InformationandCommunicationTechnology).In thiscontext,this work presents the application of the Design Process for the inception, design and implementation of a software product to support Social Innovation. To do so, it was necessary to align the Design Process with a Social Innovation Model. The social innovation treated in this work consists in fomenting a social network of rainfall (Rainwater measurement) to support several áreas (agriculture, livestock, mobility, etc.) that use climatologic information in decision making. The developed software product maintains the Record and visualization of the pluviometric information shared by the people and consists of the first implemented capacity of a Time and Weather Collaboration Network.Item Aplicativo móvel de suporte ao investidor iniciante baseado em análise fundamentalista de dados(2021-12-13) Ferreira Júnior, Marcos Eduardo; Burégio, Vanilson André de Arruda; http://lattes.cnpq.br/3518416272921878; http://lattes.cnpq.br/4966069849715181Brazil is currently undergoing an attempt to recover from a recession that began in 2020 with the onset of the COVID-19 pandemic. Adding to the economic problems generated by the pandemic, Brazil has a long history of alternating between recovery and recession of its economy. The Brazilian economic roller coaster generates for its population, mainly the poorest, the challenge of not only paying their bills, but also being able to save or invest. Today there are numerous ways to save and allocate money in places that can generate a profit during the time invested, one of them is the stock market. Compared to other investments, the stock market, investment risk is relatively higher. The functioning of the stock market is seen by many as something complex, being this a great barrier to the entry of new investors. Investments in the stock market can be made following two strands of analysis: fundamental and technical. Through fundamental analysis, the investor checks the company’s latest balance sheets, and its assets, studies its products and the market in which it operates. After this analysis, the investor has the basis to decide if he wants to invest in the company and be a partner in it for a medium to long term period. Thinking about the challenges generated by the Brazilian economy and the difficulty of Brazilians to earn an income beyond their profession, the objective of this work is to bring a mobile application that is easy to use and simple in language, using formulas that combine different fundamentalist indicators. The construction of this app is based on the fundamentals of Nielsen’s Heuristics. To keep the language simple, the Plain Language technique was used, which aims to improve the process of communication and understanding, so that texts and documents can be understood the first time the target audience reads or listens. In the stage of finalizing and verifying the quality of the created product, a survey using a form was used to compare the quality of the created product and its competitor.Item Aprendizado profundo com capacidade computacional reduzida: uma aplicação à quebra de CAPTCHAs(2018-08-16) Melo, Diogo Felipe Félix de; Sampaio, Pablo Azevedo; http://lattes.cnpq.br/8865836949700771; http://lattes.cnpq.br/2213650736070295During the last decade, Deep Neural Networks has been shown to be a powerfull machine learn technique. Generally, to obtain relevant results, these techniques require high computacional power and large volumes of data, which can be a limiting factor on some cases. Neverthless, a careful project of trainig and archtecture may help to reduce these requirements. In the this work we present a comparative approach to the application of deep neural networks to text based CAPTCHAs as a way to cope with these limitations. We studied models that are capable of learn to segment and identify the text content of images, only based on examples. By experimentation of different hiper-parameters and architectures, we were capable to obtain a final model with 96.06% of token prediction accuracy in approximately 3 hours of training in a simple personal computer.