Bacharelado em Sistemas de Informação (Sede)

URI permanente desta comunidadehttps://arandu.ufrpe.br/handle/123456789/12

Siglas das Coleções:

APP - Artigo Publicado em Periódico
TAE - Trabalho Apresentado em Evento
TCC - Trabalho de Conclusão de Curso

Navegar

Agora exibindo 1 - 16 de 16

Um algoritmo para geração de Navigation Meshes em mapas bidimensionais homogêneos: uma aplicação no jogo Dragon Age: Origins
(2019) Costa, Ingrid Danielle Vilela; Bocanegra, Silvana; http://lattes.cnpq.br/4596111202208863; http://lattes.cnpq.br/6113606913639280
In the field of electronic gaming and more recently in robotics, autonomous agent soften need to repeatedly solve the problem of searching for the smallest path. This need can eventually consume a lot of resources and demands optimizations to make these searches more efficient. Such optimizations may include improvements in search algorithms, map representation, data structures used. This work presents an optimization for search algorithms based on the reduction of the search space by means of an automatic Navigation Meshes generation algorithm which are networks of walka blemap areas implying in a reduction of the search space and consequently improving the search processing time. The generation of Navigation Meshes is a problem with no consolidated solution. To prove the heuristic, path finding problems were solved on 156 benchmark maps. The path findings were performmed by the A* algorithm and the solutions were compared between the original maps and the optimized ones. An average search space reduction of 97.42% was achieved, with a standard deviation of 0.026and the search had an average marginal reduction in execution time of 46.76%.
Análise das dinâmicas de transmissão da Mpox em Pernambuco através do uso de Modelo SEIQR com otimização de parâmetros
(2022-11-23) Pessoa, Wagner Palacio; Bocanegra, Silvana; http://lattes.cnpq.br/4596111202208863; http://lattes.cnpq.br/0525335441263931
In recent years, as a result of the COVID-19 pandemic, the importance of the accuracy of the results of studies related to the evolution and propagation of diseases has become evident, so that scientific authorities have enough inputs to make quick decisions in the containment and prevention of epidemics and mitigate their effects on society and the economy as soon as possible. At the end of July 2022, the Mpox (Monkeypox) outbreak was declared a global health emergency by the WHO, accelerating a possible return to the state of alert for a new pandemic. This work aims to analyze the transmission dynamics of this virus in Pernambuco using the SEIQR compartmental epidemiological model (Susceptible, Exposed, Infected, Quarantineed and Recovered), with data available from July 12 to November 3, 2022. The simulations were performed with the Wolfram Language. Experiments were performed with manual adjustment of the model parameters by a graphical interface and also considering the dynamic adjustment over time intervals, using a non-linear optimization function. The results suggest a possible regression in the spread of the virus in the state between mid-December 2022 and January 2023.
Aspect term extraction in aspect-based sentiment analysis
(2019) Francisco, Alesson Delmiro; Lima, Rinaldo José de; http://lattes.cnpq.br/7645118086647340
The increasing use of the Internet in many directions has created a necessity to analyze alarge quantity of data. A large amount of data is presented as Natural Language Text,which is unstructured, with many ways to express the same information. It is an importanttask to extract information and meaning from those unstructured content, such as opinionson products or services. The need to extract and analyze the large amount of data createdevery day on the Internet surpassed the capabilities of human ability, as a result, manytext mining applications that extract and analyze textual data produced by humans areavailable today, one of such kind of applications is Sentiment Analysis, viewed as a vitaltask both to the academic and commercial fields, so that companies and service providerscan use that knowledge extracted from textual documents to better understand how theircustomers think about them or to know how their products and services are appreciated ornot by their customers. However, the task of analysing unstructured text is a difficult one,that is why it is necessary to provide coherent information and concise summaries to thoserevisions. Sentiment Analysis is the process of computationally identifying and categorizingopinions expressed in a piece of text, especially in order to determine the writer’s attitudetowards a particular topic or product. Aspect-Based Sentiment Analysis is a sub-field ofSentiment Analysis that aims to extract more refined and exact opinions, by breakingdown text into aspects. Most of the current work in the literature does not take profitof either semantic-based resources or NLP-based analysis in the preprocessing stage. Tocountermeasure these limitations, a study on these resources is done aiming to extract thefeatures needed to execute the task, and to make the best combination for ATE. This workhas the main goal of implementing and analysing a method of Aspect Term Extraction(ATE) of users reviews (restaurants and laptops). The proposed method is based on asupervised approach called Conditional Random Fields (CRF) which is able to optimizethe use of features for classification, this choice was justified by previous related work thatdemonstrate the effectiveness of CRF for ATE. Also, we are investigating the existingmethods and features for ABSA, as well as proposing new features and experimentingwith feature combinations in order to find the best features combinations, that are not yetcovered in the state of art. The detailed study is done by experimenting with word features,n-grams and custom made features using an CRF supervised algorithm to accomplish thetask of Aspect Term Extraction with results in terms of Precision, Recall and F-measure,the standard evaluation metrics adopted in the field. Finally, a comparative assessmentbetween the proposal method for ATE against other related work presented in the literaturehas shown that the method presented by this work is competitive.
Detecção de anomalias em dados meteorológicos do sertão de Pernambuco utilizando Isolation Forest e DBSCAN
(2022-06-02) Cavalcante, Anderson Rodrigues; Medeiros, Victor Wanderley Costa de; http://lattes.cnpq.br/7159595141911505; http://lattes.cnpq.br/0155290293799371
Anomalous values are one of the problems present in the Big Data age. Robust techniques are required to manipulate correct and incorrect information that is generated at each time. Using non-supervised machine learning algorithms gives the confidence of good performance in the final results. This research will use meteorological data on air temperature and relative humidity from the Instituto Nacional de Meteorologia, of Petrolina, with DBSCAN (Density Based Spatial Clustering of Application with Noise) and IF (Isolation Forest) implemented to detect anomalies present in the data, since weathering meteorological anomalies may appear through defects, bad sensor configuration and even extreme climate effects.
Estudo de técnicas preditivas para o auxílio a gestores na pandemia de COVID-19
(2022-05-27) França, Eliana Maria Silva de; Soares, Rodrigo Gabriel Ferreira; http://lattes.cnpq.br/2526739219416964; http://lattes.cnpq.br/2782168150783950
The main objective of this work is to propose an alternative to exploratory statistical surveys, to support the decision-making of managers, during the confrontation of the COVID-19 pandemic. To this end, a methodology was created, using machine learning to provide a new tool for predicting deaths caused by COVID-19, from open data that contain sanitary, demographic and population characteristics. In such a way that, from this study, an artificial intelligence model can be developed capable of helping to face the COVID-19 pandemic. Of the 3 artificial intelligence algorithms used (Decision Tree, Support Vector Machine and Multilayer Perceptron), the model based on Support Vector Machine showed the best performance, because it has the lowest Mean Absolute Error, a metric used to measure the quality of regression-based artificial intelligence models.
Explainable Artificial Intelligence - uma análise dos trade-offs entre desempenho e explicabilidade
(2023-08-18) Assis, André Carlos Santos de; Andrade, Ermeson Carneiro de; Silva, Douglas Véras e; http://lattes.cnpq.br/2969243668455081; http://lattes.cnpq.br/2466077615273972; http://lattes.cnpq.br/3963132175829207
Explainability is essential for users to efficiently understand, trust, and manage computer systems that use artificial intelligence. Thus, as well as assertiveness, understanding how the decision-making process of the models occurred is fundamental. While there are studies that focus on the explainability of artificial intelligence algorithms, it is important to highlight that, as far as we know, none of them have comprehensively analyzed the trade-offs between performance and explainability. In this sense, this research aims to fill this gap by investigating both transparent algorithms, such as Decision Tree and Logistic Regression, and opaque algorithms, such as Random Forest and Support Vector Machine, in order to evaluate the trade-offs between performance and explainability. The results reveal that opaque algorithms have a low explanability and do not perform well regarding response time due to their complexity, but are more assertive. On the other hand, transparent algorithms have a more effective explainability and better performance regarding response time, but in our experiments, we observed that accuracy obtained was lower than the accuracy of opaque models.
Implementação WebGIS para análise de mercado e processo de compra e venda
(2020-11-05) Alves, Allan do Amaral; Gouveia, Roberta Macêdo Marques; Batista, Maria da Conceição Moraes; http://lattes.cnpq.br/8167265341219263; http://lattes.cnpq.br/2024317361355224; http://lattes.cnpq.br/8469386114225610
With the growing use of e-commerce platforms in the country and the various economic crises affecting the number of establishments sales since 2014, small and large retail companies are faced with the need to carry out an increasingly careful analysis of the environment in which they are located, in order to identify potential buyers of products in profile, geographic location and other attributes to optimize the direction of your services, anticipating possible changes in demand and obtaining a lower risk in association to the investments made. With the current technology, geographic information systems have become allies for the study of large databases, generating results that help the decision making of these companies. This work aims to implement a WEBGIS application for data analysis and rescue of significant geographical information, using a clustering algorithm to calculate and simulate improvement scenarios, identify regions with more buyers and indicate the best locations for selling classified products in different sectors of the market. metropolitan region of Recife using data from electronic invoices.
Método para Estimativa de Trajeto Baseado em Dados de Unidades de Medição Inercial
(2019) Silva, Lucas Filipe Vieira da; Medeiros, Victor Wanderley Costa de; Gonçalves, Glauco Estácio; http://lattes.cnpq.br/6157118581200722; http://lattes.cnpq.br/7159595141911505; http://lattes.cnpq.br/1223833449629855
The Internet of Things (IoT) has emerged as a new vision for the Internet, where awide range of devices can connect to the network. This concept is directly related tothe technological advances experienced in the development of semiconductors andintegrated circuits. These devices became cheaper, smaller, and more power efficient.These advances also enable the emergence of new applications, like real-time localiza-tion. Precise location through orientation plays a critical role in estimating the tracking ofa sensor attached to an object. The main objective of this work is to evaluate, through ex-perimentation, a trajectory estimation method based on the gradient descent algorithmand acceleration and rotation data activated by a low-cost Inertial Measurement Unit(IMU). The experiment was performed by collecting data in a straight walk, performed30 times, at a frequency of 100Hz and 50Hz. The equipment used was an MPU-6050sensor coupled to a TTGO T-Beam development board. The localization estimationswere calculated by an algorithm written in Python language. The results have shownthat it is possible to use an IMU to estimate a trajectory performed by a person withreasonable accuracy, adopting a sample rate of 50Hz.
Modelo e algoritmos para seleção de sensores como serviço
(2019) Verçosa, Nichene Joslin; Gonçalves, Glauco Estácio; Medeiros, Victor Wanderley Costa de; http://lattes.cnpq.br/7159595141911505; http://lattes.cnpq.br/6157118581200722; http://lattes.cnpq.br/3645909376039196
The Internet of Things (IoT) plays a key role in the future of the Internet, as it will inte-grate billions of smart devices which will present sensing, actuation and data processingcapabilities. Thus, each integrated device may have one or more built-in sensors thatwill potentially generate huge amounts of data. This scenario raises the challenge ofefficiently searching and selecting the most appropriate sensors within a set that canpresent similar functionalities and capabilities. In this context, this work presents a math-ematical model for sensor selection able to maximize the attendance to user input re-quirements, such as accuracy, robustness, and availability for different types of sensors(such as temperature, pressure, humidity, wind speed, and so on) in a limited budget.This model was tested through two algorithms, the first being an optimization algorithmand the second a greedy heuristic. These solutions were evaluated and compared interms of three criteria: the optimization time, the amount of budget being utilized, andthe optimal value. The best solutions were found by the optimization algorithm but, thegreedy heuristic found close results. In some cases, the greedy heuristic found solu-tions more than 10x faster when compared to the Optimal Algorithm.
Processo de Renovação Generalizado baseado na distribuição Gumbel como modelo de estimativas de ocorrências de ondas de calor para auxiliar no processo de tomada de decisão do cultivo de manga no Sertão de Pernambuco
(2023-05-08) Ferraz, Kimbelly Emanuelle Avelino; Cristino, Cláudio Tadeu; http://lattes.cnpq.br/0295290151219369; http://lattes.cnpq.br/2320958356149704
Several types of events can harm the planting, harvesting or handling of plants and fruits in agricultural areas, one of them including the event called heat waves, which is characterized as a prolonged and relatively uncommon meteorological phenomenon with extremely high temperatures for the region and persistent for several days or even weeks. Given the importance of agriculture, this work seeks, through the analysis of the maximum temperature data in the Petrolina region, the study of the mango plantation, the Heat Wave event through the 90th percentile, optimization algorithms and the processes of generalized renewal and Gumbel, estimating this event contributing to the farmer’s decision making and optimization of Mango production. The proposed model uses the generalized renewal process based on the Gumbel distribution (GuGRP) to model the time intervals between heat waves, considering that consecutive events are conditionally independent. This model proved to be adherent to model events with a significance level of 0.05 and a P −V alue of 0.28 through the Kolmogorov-Smirnov adherence test on the adequacy data adapted to the GuGRP. The model parameters were estimated by Log-Likelihood using optimization algorithms, also specifically testing the Particle Swarm algorithm.
Recomendação de psicólogos por meio de algoritmos de filtragem colaborativa, conteúdo e híbrida
(2023-09-14) Gomes Júnior, Augusto Rosário; Bocanegra, Silvana; http://lattes.cnpq.br/4596111202208863
There is a rising number of people diagnosed with mental health disorders such as depression and anxiety, disorders that have been long neglected by science and society. Even so, more and more advances are being made in the ways of treating these people, such as platforms that offer psychological care remotely. However, choosing a psychologist or therapist is not always an easy task, given the large amount of information involved in the choosing process. Based on that, the goal of this article was to develop a psychologist recommender system based on a hybrid model, which should be able to recommend psychologists with expertise that meet the needs of different types of patients. The model showed promising results, where the similarity between the recommended psychologists was consistent and good results were achieved in the evaluation metrics MAE (<0.5) and RMSE (<0.75). It was also possible to mitigate weaknesses from both content and collaborative recommendations.
Sistema de aprendizado de máquina para predição do tempo de esforço de tarefas de desenvolvimento de software
(2021-12-14) Sitonio, Tiago Pedro da Silva; Monteiro, Cleviton Vinicius Fonsêca; http://lattes.cnpq.br/9362573782715504; http://lattes.cnpq.br/0915757895643807
Sistema de recomendação de restaurantes, baseado em três tipos diferentes de filtragem de dados, nos bairros do Recife-PE
(2021-12-20) Silveira Filho, Daniel Guilherme da; Cysneiros Filho, Gilberto Amado de Azevedo; http://lattes.cnpq.br/0534822491953359
Considering that the city of Recife is in third place for gastronomic centers in Brazil, and that currently the amount of information present on the internet is bordering on infinity, tourists and even the local population go to the most popular restaurants. A consequence of this is that small accessories, which do not have a strong publicity for their brand, end up going out of business in the first five years of existence. Therefore, a research was carried out on recommendation systems, an analysis purpose for the development of a restaurant recommendation system, based on three different types of data filtering techniques, in the neighborhoods of the city of Recife. Therefore, it is necessary to explain the fundamentals of the filtering techniques that will be used in the development of the system, in addition to identifying how to define, collect, treat and analyze the data provided for the construction of the system, analyze the development of a recommendation-based system in the content, analyze the development of a recommendation system, based on the user, analyze the development of a hybrid recommendation system and finally identify which recommendation technique best results. A study is then carried out on the database, selection, collection and processing of data provided for the construction of the system, in addition to modeling a sample of people and results to be recommended, a study was also carried out on recommendation systems, definition, emergence and main filtering techniques, used in similar works, thus it was necessary to define which attributes and parameters to be collected, in addition to a modeling of the data capture form and development of the three selected collaborative filtering techniques, and finally, system tests are carried out to prove its functioning and analysis of collected data. Therefore, it appears that although the content-based filtering technique stands out in the results, the difference between this type of filtering and collaborative filtering was not significant, which imposes the observation that the recommendation system, based on neighborhoods , brings ease and convenience to users, in addition to promoting the brand of neighborhood restaurants and expanding tourism in the city of Recife, but it requires more interaction and information from registered users, to become more precise in their recommendations.
Sugestão de livros baseada em algoritmo híbrido de recomendação e grau de interesse recente
(2023-05-26) Tavares, Eduardo Brandão; Bocanegra, Silvana; http://lattes.cnpq.br/4596111202208863
With a vast and growing range of books available, choose your next reading can become a complex job amid so many options. In the context of Brazil, where most readers have to choose well which book to buy, due to the low purchasing power of our population, an assertive recommendation has become more valuable. This article presents a book recommendation algorithm based on a hybrid model, which consists of using both techniques related to association rules and techniques that are based on the content of books, aiming to present unknown books that follow the recent interest of the reader. The model managed to reach an accuracy comparable to other models in the RMSE and MAE metrics and delivers recommendations closely related to the last readings of each reader.
Utilização de filtragem colaborativa no auxílio de recomendação personalizada para leitores de mangá
(2024-03-04) Brochardt, Rodrigo Nativo do Brasil; Garrozi, Cícero; http://lattes.cnpq.br/0488054917286587
This study investigated, developed, and compared two approaches for generating manga recommendations: the Singular Value Decomposition (SVD) model and the Pearson Correlation Coefficient. The methodology involved data preparation through the development and execution of a web scraper to extract manga information and reviews from a highly active internet forum. Challenges arising in the applicability of these data extraction methods were addressed, along with alternatives for handling source blocking situations, model training, and performance evaluation, focusing on collaborative filtering and personalized recommendations for user profiles and manga works. In the implementation of SVD, latent patterns in user review data were identified, enabling personalized recommendations based on individual preferences through the sharing of experiences with similar profiles. However, metrics such as Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE) revealed the need for model refinement to improve its accuracy, as well as alternative implementations for conducting comparisons and metrics related to the specific data mass used in the study. Conversely, the approach based on the Pearson Correlation Coefficient prioritized similarity between manga reviews to generate item-focused recommendations, although it significantly relied on the number of available reviews. This methodology offered a direct and valid logic for personalized recommendations based on relationships derived from reviews. The conclusion highlighted the future possibility of exploring hybrid methods combining the advantages of SVD and the Pearson Correlation Coefficient to achieve more precise and comprehensive recommendations, as well as validating techniques that bring different recommendation approaches for tangible comparison. The utilization of additional data gathered in the generated data mass to enrich the quality of recommendations was suggested, aiming to use more detailed parameters in recommendations, along with the employment of indirect approaches, such as using LLMs to aid in the recommendation process. Finally, the study emphasizes the importance of advancing these recommendation technologies to facilitate readers' lives by assisting in filtering the vast content offered by the industry and the internet.
Vinculando perfis de engajamento ao desempenho acadêmico por meio de análise de redes sociais e análise de agrupamento nos dados de fóruns de discussão
(2021-11-18) Oliveira, Pamella Letícia Silva de; Rodrigues, Rodrigo Lins; http://lattes.cnpq.br/5512849006877767; http://lattes.cnpq.br/8863320225621574