Mestrado em Ciência da Computação (INF)

URI Permanente para esta coleção

http://200.137.215.59/tede/handle/tde/225

Navegar

Agora exibindo 1 - 20 de 290

A comparative study of text classification techniques for hate speech detection
(Universidade Federal de Goiás, 2022-01-27) Silva, Rodolfo Costa Cezar da; Rosa, Thierson Couto; http://lattes.cnpq.br/4414718560764818; Rosa, Thierson Couto; Moura, Edleno Silva de; Silva, Nádia Félix Felipe da
The dissemination of hate speech on the Internet, specially on social media platforms, has been a serious and recurrent problem. In the present study, we compare eleven methods for classifying hate speech, including traditional machine learning methods, neural network-based approaches and transformers, as well as their combination with eight techniques to address the class imbalance problem, which is a recurrent issue in hate speech classification. The data transformation techniques we investigated include data resampling techniques and a modification of a technique based on compound features (c_features).All models have been tested on seven datasets with varying specificity, following a rigorous experimentation protocol that includes cross-validation and the use of appropriate evaluation metrics, as well as validation of the results through appropriate statistical tests for multiple comparisons. To our knowledge, there is no broader comparative study in data enhancing techniques for hate speech detection, nor any work that combine data resampling techniques with transformers. Our extensive experimentation, based on over 2,900measurements, reveal that most data resampling techniques are ineffective to enhance the effectiveness of classifiers, with the exception of ROS which improves most classification methods, including the transformers. For the smallest dataset, ROS provided gains of 60.43% and 33.47% for BERT and RoBERTa, respectively. The experiments revealed that c_features improved all classification methods that they could be combined with. The compound features technique provided satisfactory gains of up to 7.8% for SVM. Finally,we investigate cost-effectiveness for a few of the best classification methods. This analysis provided confirmation that the traditional method Logistic Regression (LR) combined with the use of c_features can provide great effectiveness with low overhead in all datasets considered
Implementação de princípios de gamificação adaptativa em uma aplicação mHealth
(Universidade Federal de Goiás, 2023-08-25) Anjos, Filipe Maciel de Souza dos; Carvalho, Sergio Teixeira de; http://lattes.cnpq.br/2721053239592051; Carvalho, Sergio Teixeira de; Mata, Luciana Regina Ferreira da; Berretta, Luciana de Oliveira
This work describes the implementation of a gamified mHealth application called IUProst for the treatment of urinary incontinence through the performance of pelvic exercises for men who have undergone prostate removal surgery. The development of the application followed the guidelines of Framework L, designed to guide the creation of gamified mHealth applications. The initial version of IUProst was exclusively focused on the self-care dimension of Framework L and was released in November 2022. It was used by hundreds of users seeking the treatment provided by the application. Subsequently, the Gamification dimension of Framework L was employed to gamify IUProst. During the process of implementing game elements, it was noted that there were no clear definitions of how to implement the components to allow for gamification adaptation based on user profiles. To address this gap, an implementation model for gamification components was developed to guide developers in creating gamification that could adapt to the user profile dynamics proposed by the adaptive gamification of Framework L. Therefore, the contributions of this research include delivering a gamified mHealth application, analyzing usage data generated by the gamified application, and providing an implementation model for game components that were incorporated into Framework L, enabling the use of components in the context of adaptive gamification. The gamified version of IUProst was published in July 2023 and was used for 30 days until the writing of this dissertation. The results obtained demonstrate that during the gamified month, patients performed approximately 2/3 more exercises compared to the previous two months, reaching 61% of the total exercises performed during the three months analyzed. The data confirmed the hypothesis that game components indeed contribute to patient engagement with the application and also highlighted areas for improvement in the mHealth application.
Uma arquitetura para integração de dispositivos e coleta de dados em jogos sérios multimodais
(Universidade Federal de Goiás, 2023-08-25) Zacca, Flavio Augusto Glapinski; Carvalho, Sérgio Teixeira de; http://lattes.cnpq.br/2721053239592051; Carvalho, Sérgio Teixeira De; Silvestre, Bruno Oliveira; Copetti, Alessandro; Zacca
This dissertation addresses the development of an architecture for integrating devices and collecting data in multimodal serious games. However, integrating devices and collecting data in multimodal serious games present technical and scientific challenges to overcome. The research problem consists of identifying and analyzing difficulties in sharing information among heterogeneous devices, the absence of common communication protocols, limitations in utilizing data in other applications, and the need for an architecture enabling the collection, filtering, processing, and provisioning of treated data for serious games. The general objective of the research is to develop a solution allowing the integration of devices and data collection in multimodal serious games, aiming for efficient and transparent provisioning of treated data. The research is grounded in theoretical studies, analysis of related works, requirements gathering, and the implementation of this architecture. The research includes theoretical studies, analysis of related works, requirements gathering, and the implementation of this architecture. Practical studies and experiments were conducted to assess the efficiency and viability of the proposed architecture, using multimodal games developed by the research group, such as Salus Cyber Ludens and Cicloexergame, as use cases. The obtained results demonstrated the effectiveness of the architecture in handling and leveraging data from devices, contributing to the advancement of the field of multimodal serious games. In conclusion, the proposed architecture represents a promising solution for integrating devices and collecting data in multimodal serious games. Its application can benefit areas such as health, education, and industry, expanding interaction possibilities and promoting advancements in the field of multimodal serious games.
Estudo comparativo de comitês de sub-redes neurais para o problema de aprender a ranquear
(Universidade Federal de Goiás, 2023-09-01) Ribeiro, Diogo de Freitas; Sousa, Daniel Xavier de; http://lattes.cnpq.br/4603724338719739; Rosa, Thierson Couto; http://lattes.cnpq.br/4414718560764818; Rosa, Thierson Couto; Sousa, Daniel Xavier de; Canuto, Sérgio Daniel Carvalho; Martins, Wellington Santos
Learning to Rank (L2R) is a sub-area of Information Retrieval that aims to use machine learning to optimize the positioning of the most relevant documents in the answer ranking to a specific query. Until recently, the LambdaMART method, which corresponds to an ensemble of regression trees, was considered state-of-the-art in L2R. However, the introduction of AllRank, a deep learning method that incorporates self-attention mechanisms, has overtaken LambdaMART as the most effective approach for L2R tasks. This study, at issued, explored the effectiveness and efficiency of sub-networks ensemble as a complementary method to an already excellent idea, which is the self-attention used in AllRank, thus establishing a new level of innovation and effectiveness in the field of ranking. Different methods for forming sub-networks ensemble, such as MultiSample Dropout, Multi-Sample Dropout (Training and Testing), BatchEnsemble and Masksembles, were implemented and tested on two standard data collections: MSLRWEB10K and YAHOO!. The results of the experiments indicated that some of these ensemble approaches, specifically Masksembles and BatchEnsemble, outperformed the original AllRank in metrics such as NDCG@1, NDCG@5 and NDCG@10, although they were more costly in terms of training and testing time. In conclusion, the research reveals that the application of sub-networks ensemble in L2R models is a promising strategy, especially in scenarios where latency time is not critical. Thus, this work not only advances the state of the art in L2R, but also opens up new possibilities for improvements in effectiveness and efficiency, inspiring future research into the use of sub-networks ensemble in L2R.
Interpretabilidade de modelos de aprendizado de máquina: uma abordagem baseada em árvores de decisão
(Universidade Federal de Goiás, 2023-09-22) Silva, Jurandir Junior de Deus da; Salvini, Rogerio Lopes; http://lattes.cnpq.br/5009392667450875; Salvini, Rogerio Lopes; Silva, Nadia Félix Felipe da; Alonso, Eduardo José Aguilar
Interpretability is defined as the ability of a human to understand why an AI model makes certain decisions. Interpretability can be achieved through the use of interpretable models, such as linear regression and decision trees, and through model-agnostic interpretation methods, which treat any predictive model as a "black box". Another concept related to interpretability is that of Counterfactual Explanations, which show the minimal changes in inputs that would lead to different results, providing a deeper understanding of the model’s decisions. The approach proposed in this work exploits the explanatory power of Decision Trees to create a method that offers more concise explanations and counterfactual explanations. The results of the study indicate that Decision Trees not only explain the “why” of model decisions, but also show how different attribute values could result in alternative outputs.
Uma estratégia de pós-processamento para seleção de regras de associação para descoberta de conhecimento
(Universidade Federal de Goiás, 2023-08-22) Cintra, Luiz Fernando da Cunha; Salvini, Rogerio Lopes; http://lattes.cnpq.br/5009392667450875; Salvini, Rogerio Lopes; Rosa, Thierson Couto; Aguilar Alonso, Eduardo José
Association rule mining (ARM) is a traditional data mining method that provides information about associations between items in transactional databases. A known problem of ARM is the large amount of rules generated, thus requiring approaches to post-process these rules so that a human expert is able to analyze the associations found. In some contexts the domain expert is interested in investigating only one item of interest, in these cases a search guided by the item of interest can help to mitigate the problem. For an exploratory analysis, this implies looking for associations in which the item of interest appears in any part of the rule. Few methods focus on post-processing the generated rules targeting an item of interest. The present work seeks to highlight the relevant associations of a given item in order to bring knowledge about its role through its interactions and relationships in common with the other items. For this, this work proposes a post-processing strategy of association rules, which selects and groups rules oriented to a certain item of interest provided by an expert of a domain of knowledge. In addition, a graphical form is also presented so that the associations between rules and groupings of rules found are more easily visualized and interpreted. Four case studies show that the proposed method is admissible and manages to reduce the number of relevant rules to a manageable amount, allowing analysis by domain experts. Graphs showing the relationships between the groups were generated in all case studies and facilitate their analysis.
Secure D2Dcaching framework based on trust management and blockchain for mobile edge caching - a multi domain approach
(Universidade Federal de Goiás, 2023-08-18) Rocha, Acquila Santos; Pinheiro, Billy Anderson; http://lattes.cnpq.br/1882589984835011; Borges, Vinicius da Cunha Martins; http://lattes.cnpq.br/6904676677900593; Borges, Vinicius da Cunha Martins; Pinheiro, Billy Anderson; Cordeiro, Weverton Luis da Costa; Carvalho, Sérgio Teixeira de
Device–to-Device communication (D2D), combined with edge caching and mobile edge computing, is a promising approach that allows offloading data from the wireless mobile network. However, user security is still an open issue in D2D communication. Security vulnerabilities remain possible owing to easy, direct and spontaneous interactions between untrustworthy users and different degrees of mobility. This dissertation encompasses the designing of a multi-layer framework that combines diverse technologies inspired in blockchain to come up with a secure multi domain D2D caching framework. Regarding the intra-domain aspect we establish Secure D2D Caching framework inspired on trUst management and Blockchain (SeCDUB) to improve the security of D2D communication in video caching, through the combination of direct and indirect observations. In addition, blockchain concepts were adapted to the dynamic and restricted scenario of D2D networks to prevent data interception and alteration of indirect observations. This adaptation considered the development of a Clustering Approach (CA) that enables scalable and lightweight blockchain for D2D networks. Two different uncertainty mathematical models were used to infer direct and indirect trust values: Bayesian inference and the Theory Of Dempster Shafer (TDS) respectively. Regarding the inter-domain approach we developed Trust in Multiple Domains (TrustMD) framework. This approach combines edge trust storage with blockchain for distributed storage management in a multi layer architecture, designed to efficiently store trust control data in edge across different domains. Regarding the collected results, we performed simulations to test SecDUB’s intra-domain approach. The proposed clustering approach plays a key role to mitigate the SecDuB overhead as well as the consensus time. TrustMD results demonstrated a significant enhancement in goodput, reaching at best, 95% of the total network throughput, whicle SecDUB achieved approximately 80%. Even though there was a 7% increase in D2D overhead, TrustMD effectively keep control of latency levels, resulting in a slight decrease of 1.3 seconds. Hence, the achieved results indicates that TrustMD efficiently manages securitywithout compromising network performance reducing false negative rate up to 31% on the best case scenario. Actually, the combination of SecDUB and TrustMD offers a scalable and effective security solution that boosts network performance and ensures robust protection.
Classificação das despesas com pessoal no contexto dos Tribunais de Contas
(Universidade Federal de Goiás, 2023-08-22) Teixeira, Pedro Henrique; Silva, Nadia Félix Felipe da; http://lattes.cnpq.br/7864834001694765; Salvini, Rogerio Lopes; http://lattes.cnpq.br/5009392667450875; Salvini, Rogerio Lopes; Silva, Nadia Félix Felipe da; Fernandes, Deborah Silva Alves; Costa, Nattane Luíza da
The Court of Accounts of the Municipalities of the State of Goiás (TCMGO) uses the expenditure data received monthly from the municipalities of Goiás to check the expenditure related to personnel expenses, as determined by LRF. However, there are indications that the classification of expenses sent by the municipal manager may contain inconsistencies arising from fiscal tricks, creative accounting or material errors, leading TCMGO to make decisions based on incorrect reports, resulting in serious consequences for the inspection process. As a way of dealing with this problem, this work used text classification techniques to identify, based on the description of the expense and instead of the code provided by the municipality, the class of a personnel expense. For this, a corpus was built with 17,116 expense records labeled by domain experts, using binary and multi-class approaches. Data processing procedures were applied to extract attributes from the textual description, as well as assign numerical values to each instance of the data set with the TF-IDF algorithm. In the modeling stage, the algorithms Multinomial Naïve Bayes, Logistic Regression and Support Vector Machine (SVM) were used in supervised classification. SVM proved to be the best algorithm, with F-Score of 0.92 and 0.97, respectively, on the multi-class and binary corpus. However, it was found that the labeling process carried out by human experts is complex, time-consuming and expensive. Therefore, this work developed a method to classify personnel expenses using only 235 labeled samples, improved by unlabeled instances, based on the adaptation of the Self-Training algorithm, producing very promising results, with an average F-Score between 0.86 and 0.89.
Junções por similaridade aproximadas em espaços vetoriais densos
(Universidade Federal de Goiás, 2023-08-24) Santana , Douglas Rolins de; Santana; Ribeiro, Leonardo Andrade; http://lattes.cnpq.br/4036932351063584; Ribeiro, Leonardo Andrade; Bedo, Marcos Vinicius Naves; Martins, Wellington Santos
Similarity Join is an operation that returns pairs of objects whose similarity is greater than or equal to a specified threshold, and is essential for tasks such as cleaning, mining, and data integration. A common approach is to use data vector representations, such as the TFIDF method, and measure the similarity between vectors using the cosine function. However, computing the similarity for all pairs of vectors can be computationally prohibitive on large data sets. Traditional algorithms exploit the sparsity of vectors and apply filters to reduce the comparison space. Recently, advances in natural language processing have produced in semantically richer vectors, improving the results quality. However, these vectors have different characteristics from those generated by traditional methods, being dense and of high dimensionality. Preliminary experiments demonstrated that L2AP, the best known algorithm for similarity join, is not efficient for dense vector spaces. Due to the intrinsic characteristics of such vectors, approximate solutions based on specialized indices are predominant for dealing with large datasets. In this context, we investigate how to perform similarity joins using the Hierarchical Navigable Small World (HNSW), a state-of-the-art graph-based index designed for approximate k-nearest neighbor (kNN) queries. We explored the design space of possible solutions, ranging from top-end alternatives to HNSW to deeper integration of similarity join processing into this framework. The experiments carried out demonstrated accelerations of up to 2.48 and 3.47 orders of magnitude in relation to the exact method and the baseline approach, respectively, maintaining recovery rates close to 100%.
Alocação de recursos e posicionamento de funções virtualizadas em redes de acesso por rádio desagregadas
(Universidade Federal de Goiás, 2023-08-30) Almeida, Gabriel Matheus Faria de; Pinto, Leizer de Lima; http://lattes.cnpq.br/0611031507120144; Cardoso, Kleber Vieira; http://lattes.cnpq.br/0268732896111424; Cardoso, Kleber Vieira; Pinto, Leizer de Lima; Klautau Júnior, Aldebaro Barreto da Rocha; Silva, Luiz Antonio Pereira da
Jointly choosing a functional split of the protocol stack and placement of network functions in a virtualized RAN is critical to efficiently using the access network resources. This problem represents a current research topic in 5G and Post-5G networks, which involves the challenge of simultaneously choosing the placement of virtualized functions, the routes for traffic and the management of available computing resources. In this work, we present three approaches to solve this problem considering the planning scenario and two approaches considering the network operation scenario. The first result is a Mixed Integer Linear Programming (MILP) model, considering a generic set of processing nodes and multipath routing. The second approach uses artificial intelligence and machine learning concepts, in which we formulate a deep reinforcement learning agent. The third approach used is based on search meta-heuristics, through a genetic algorithm. The last two approaches are Markov Decision Process (MDP) formulations that consider dynamic demand on radio units. In all formulations, the objective is to maximize the network function’s centralization while minimizing positioning cost. Analysis of the solutions and comparison of their results show that exact approaches such as MILP naturally provide the best solution. However, in terms of efficiency, the genetic algorithm has the best search time, finding a high quality solution in a few seconds. The deep reinforcement learning agent presents a high convergence, finding high quality solutions for the problem and showing problem generalization capacity with different topologies. Finally, the formulations considering the network operation scenario with dynamic demand are highly complex due to the size of the action space
Requisitos em ação: uma arquitetura pedagógica para o ensino de engenharia de requisitos
(Universidade Federal de Goiás, 2023-06-12) Santana, Thalia Santos de; Kudo, Taciana Novo; http://lattes.cnpq.br/7044035224784132; Bulcão Neto, Renato de Freitas; http://lattes.cnpq.br/5627556088346425; Bulcão Neto, Renato de Freitas; Santos, Davi Viana dos; Ferreira, Deller James
Requirements Engineering Education (REE) is a knowledge area that raises discussions regarding the teaching of Requirements Engineering (RE) topics, aiming to provide quality training for future requirements analysts. [Problem] Despite this concern, the literature describes that the teaching of RE in undergraduate courses often lacks synergy with market demands, which is corroborated by the lack of pedagogical frameworks that permeate the REE on what and how to teach such content, causing training failures understood in academia and industry. [Objective] Thus, this work aimed to collaborate with the teaching-learning of requirements through the design of a pedagogical architecture (PA) focused on teaching specification and validation activities, in order to favor the development of hard and soft skills. [Methods] The PA was developed contemplating lesson plans, teaching materials and practical activities, and was subsequently instantiated in four editions of ER courses with undergraduate Computing students. [Results] The results of the quantitative and qualitative evaluations indicate that the techniques of user stories and acceptance test scenarios have their learning potential enhanced, being perceived by students as useful in professional practice. In addition, the teachers mention that the PA collaborates with the EER ensuring greater student participation, also highlighting the collaboration of the class scripts for a correct execution of the proposed practices. [Conclusions] Therefore, the present AP contributes to ER education by demonstrating a pedagogical framework that can promote alignment between software requirements knowledge and the hard and soft skills desired in industry.
Reconhecimento de entidades nomeadas em textos informais no domínio legislativo
(Universidade Federal de Goiás, 2023-04-19) Costa, Rosimeire Pereira da; Souza, Ellen Polliana Ramos; http://lattes.cnpq.br/6593918610781356; Silva, Nádia Félix Felipe da; http://lattes.cnpq.br/7864834001694765; Silva, Nádia Félix Felipe da; Souza, Ellen Polliana Ramos; Silva, Sérgio Francisco da; Fernandes, Deborah Silva Alves
Named Entity Recognition (NER) is a challenging task in Natural Language Processing (NLP) for a language as rich as Portuguese. When applied in a scenario appropriate to informal language and short texts, the task acquires a new layer of complexity, manipulating a lexicon specific to the domain in question. In this work, we expand the UlyssesNER-Br corpus for the NER task with Brazilian Portuguese comments on bill projects. Additionally, we enriched the annotated set with a formal corpus in order to analyze whether the combination of formal and informal texts from the same domain could improve the performance of NER models. Finally, we conducted experiments with a Conditional Random Fields (CRF) model, a Bidirectional LSTM-CRF model (BiLSTM-CRF), and subsequently fine-tuned a BERT and RoBERTa language model on the NER task with our dataset. We conclude that formal texts aided in identifying entities in informal texts. The best model was the fine-tuning of BERT which achieved an F1- score of 74.63%, surpassing the benchmark of related works.
Supporting public health policy decisions through live birth predictions for health regions of Goiás with machine learning
(Universidade Federal de Goiás, 2023-04-11) Vitória, Arthur Ricardo de Sousa; Galvão Filho, Arlindo Rodrigues; http://lattes.cnpq.br/7744765287200890; Galvão Filho, Arlindo Rodrigues; Coelho, Clarimar José; Soares, Anderson da Silva
The use of forecasting models is becoming even more common in healthcare and administration applications because they can be reliable decision support tools. The live birth rate is a health index that is directly linked with maternal and newborn health, and its prediction can assist health managers to anticipate resources destined for obstetric and pediatric services. Thus, the objective of this work is to forecast the number of live births in the state of Goiás (Brazil) for a 24-month horizon, providing useful information to support the planning and implementation of public policies. This study investigates two distinct approaches: univariate and multivariate, allowing a better understanding and management of the Brazilian territorial hierarchy. Both approaches are evaluated with data provided by the information system on live births of the information department of the single health system (SINASC-DATASUS). The dataset is composed of 252 monthly records of the number of live births for the 18 health regions of Goiás. The results were measured in prediction ability by Mean Absolute Percentual Error (MAPE) and Mean Absolute Error (MAE). For the univariate approach using a LMU, the average MAPE and MAE achieved were 6.4614 and 19.9136, respectively. The multivariate approach was combined with the K-means method for clustering similar time series using a dynamic time warping measure, generating an average result of 5.5985 and 18.1360 for MAPE and MAE, respectively.
Ensino do pensamento computacional por meio de uma abordagem transversal apoiada por padrões de programação, jogos desconectados e Scratch
(Universidade Federal de Goiás, 2021-03-04) Carlos, Cássio Martins; Ferreira, Deller James; http://lattes.cnpq.br/1646629818203057; Ferreira, Deller James; Brandão, Leônidas de Oliveira; Berretta, Luciana de Oliveira
The concept of Computational Thinking (PC) has beeing to be widely addressed in research in the past ten years. These researches look for ways to use this concept in formal education. However, it is common to find difficulties in learning the PC, because of this there is a need for teaching approaches capable of stimulating the learning of the concept. Games emerge as tools capable of expanding PC teaching results, improving student engagement and motivation. There are also programming patterns, which can be understood as a common solution to a recurring problem, which allows inexperienced students to accelerate the development of fundamental skills for PC learning. There is also software for visual programming, such as Scratch, which has an intuitive block programming interface, allowing the visualization of the command blocks and their execution. The PC is a skill that is not restricted only to information technology, in fact it can and should be applied in other areas, so it must be linked to transversal approaches. For the development of a transversal approach to teaching PC using the aforementioned tools, a design-based research methodology (Design Based Research) was applied. This methodology involves the participation of teachers in the process of developing a set of teaching practices, so that this set is contextualized in a real world of education and at the same time refined by specialists in each area of knowledge. The interactions with the teachers presented satisfactory data and produced an efficient and robust set of practices for teaching the PC in a transversal way in a context of elementary school.
Controle de estilo na síntese de voz em português brasileiro usando redes neurais profundas
(Universidade Federal de Goiás, 2021-08-26) Tunnermann, Daniel; Soares, Anderson da Silva; http://lattes.cnpq.br/1096941114079527; Soares, Anderson da Silva; Galvão Filho, Arlindo Rodrigues; Gonçalves, Cristhiane
The popularization of computer programs capable of emulating a dialogue between machines and people, known as chatbots, has driven the development of human-computer interface solutions. In this context, there is a relevant demand in the development of conversational voice interfaces that include at least the ability of the machine to understand words and synthesize voice. The use of Neural Networks has led to a new state of the art for speech synthesis. Mean Opinion Score(MOS) tests show that the speech synthesized by this method has a quality similar to speech recorded in studio by humans. Even with this quality, these methods have difficulty to reproduce the various ways of speaking the same text, to convey information that goes beyond the content, such as emotion, intensity, speed and emphasis. Therefore, new models have been developed to control the style of the generated speech and to transfer style from one audio segment to others. Despite these recent advances, the studies carried out are concentrated on the synthesis of texts in English or Mandarin. The application of style control methods to produce variations in Brazilian Portuguese is also scarce or non-existent. The research presented here developed a neural network architecture for speech synthesis in Brazilian Portuguese capable of controlling the style of synthesized speech. This control allows pitch and velocity changes. In MOS evaluation, the constructed model obtained 4.1 on a scale from 1(Poor) to 5(Excellent), validating the subjective evaluation of good quality in synthesized audios. Examples of audio generated by the developed models can be seen at shorturl.at/etFJP and https://mrfalante.com.br/sobre. Real-time synthesis using models resulting from this research can be performed at https://cybervox.ai.
Alianças defensivas em grafos
(Universidade Federal de Goiás, 2010-03-26) Dias, Elisângela Silva; Barbosa, Rommel Melgaço; http://lattes.cnpq.br/6228227125338610; Barbosa, Rommel Melgaço; Martins, Wellington Santos; Tronto, Íris Fabiana de Barcelos
A defensive alliance in graph G = (V,E) is a set of vertices S ⊆V satisfying the condition that every vertex v ∈ S has at most one more neighbor in V − S than S. Due to this type of alliance, the vertices in S together defend themselves to the vertices in V − S. This dissertation introduces the basic concepts for the understanding of alliances in graphs, along with a variety of alliances and their numbers and provides some mathematical properties for these alliances, focusing mainly on defensive alliances in graphs. It shows theorems, corollaries, lemmas, propositions and observations with appropriate proofs with respect to the minimum degree of a graph G δ(G), the maximum degree ∆(G), the algebraic connectivity µ, the total dominanting set γt(G), the eccentricity, the edge connectivity λ(G), the chromatic number χ(G), the (vertex) independence number β0(G), the vertex connectivity κ(G), the order of the largest clique ω(G) and the domination number γ(G). It also shows a generalization of defensive alliances, called defensive k alliance, and the definition and properties of a security set in G. A secure set S ⊆ V of graph G = (V,E) is a set whose every nonempty subset can be successfully defended of an attack, under appropriate definitions of “attack” and “defence”.
Um sistema WebGIS para classificação supervisionada de cobertura do solo utilizando inteligência artificial
(Universidade Federal de Goiás, 2022-10-21) Fernandes, Yuri Kuivjogi; Costa, Ronaldo Martins da; http://lattes.cnpq.br/7080590204832262; Costa, Ronaldo Martins da; Oliveira, Bruna Mendes de; Cremon, Édipo Henrique
With the advancement in data generation for Earth observation and its availability free of charge, the Remote Sensing (SR) area advanced significantly. Over the years, it has been observed the migration of RS applications to the internet environment, facilitating searches of different uses. This work proposes a new approach for collecting and manipulating spatial data for spectral classification based on pixels. A web application was built integrating Google Earth Engine, Google Maps and Auto Machine Learning services for performance analysis. Experiments using samples from land cover regions in Goiás, Brazil, justifying the gain in time, processing and data storage. Such contributions are related to the large amount of information from satellite images collected in a conventional way, which are later not used. As a final result, there is an image classified through the classification process representing the different land cover classes. Model training achieved an accuracy of 99.85% using the Light Gradient Boosting Machine (LightGBM) model. In addition to these benefits, the optimization of processes allows the inclusion of research from other major areas, thus for the greater dissemination of knowledge in the area of SR and pattern recognition applications.
Uso de rotas elementares no CVRP
(Universidade Federal de Goiás, 2010-02-23) Pecin, Diego Galindo; Longo, Humberto José; http://lattes.cnpq.br/0188685041571480; Longo, Humberto José; Meneses, Cláudio Nogueira de; Aragão, Marcus Vinicius Soledade Poggi de
This dissertation addresses the optimization of the Elementary Shortest Path Problem with a Capacity Constraint (ESPPCC) and describes algorithms for its resolution that make use of concepts such as Label-Setting, Bidirectional Dynamic Programming and Decremental State Space Relaxation. These algorithms were used in a robust CVRP’s Branch-and Cut-and-Price framework as the column generation mechanism. The resulting BCP was used to obtain results (lower bounds, processing time and the number of branching nodes generated) to several CVRP’s test instances. These results are compared with previous ones obtained with the original BCP, which is based on k-cycle elimination. Elementary routes are also explored in a route enumeration context, which allows the enumeration of all possible relevant elementary routes, i.e., all routes that have a chance of being part of an optimal CVRP’s solution. If the number of relevant routes is not too large (say, in the range of tenths of thousands), the overall problem may be solved by feeding a general MIP solver with a set-partition formulation containing only those routes. If this set-partition can be solved, the optimal solution will be found and no branch will be necessary. Sometimes this leads to very significant speedups when compared to traditional branch strategies.
Aprendizado de máquina automático aplicado à predição da evasão no ensino superior
(Universidade Federal de Goiás, 2022-10-20) Barros, Bruno de Mattos; Nascimento, Hugo Alexandre Dantas do Nascimento; http://lattes.cnpq.br/2920005922426876; Nascimento, Hugo Alexandre Dantas do; Ferreira, Deller James; Mello, Rafael Ferreira Leite de
Academic dropout is a problem that affects many public and private university students in Brazil and around the world. Machine learning techniques have been used to mitigate the problem, but still require a lot of manual adjustments. We present in this work, a proposal of an automatic machine learning framework to predict academic dropout, with the goal of obtaining good results without the need for human intervention. This data processing framework includes the following stages: pre-processing, feature vector creation, data splitting into testing and training sets, clustering of data from different degrees for training, model selection, model parameter tunning and explainability. Additionally, we formalize temporal data splitting approaches for train and test datasets, as this task is not adequately addressed in most of the previous works.
Localização evolucionária de defeitos em software baseada na singularidade de escores de suspeita
(Universidade Federal de Goiás, 2022-10-13) Ferreira, Willian de Jesus; Leitão Júnior, Plinio de Sá; http://lattes.cnpq.br/4480334653242457; Leitão Júnior, Plinio de Sá; Bulcão Neto, Renato De Freitas; Chaim, Marcos Lordello
Context. Software is subject to the presence of faults, which impacts its quality as well as production and maintenance costs. Evolutionary fault localization has used data from the test activity (test spectra) as a source of information about defects, and its automation aims to obtain better accuracy and lower software repair cost. Motivation. Our analysis identified that test spectra commonly used in the research field have a high ratio of sample repetition, which impairs the training and evolution of models (heuristics). Problem. We investigate whether the uniqueness of suspiciousness scores can boost the ability to find software faults, aiming to deal with samples repetition, that is, if an exploration based on how distinguishable program elements are about being defective can generate competitive models. Methodology. The investigation formalized hypotheses, introduced three training strategies to guide the proposal and carried out an experimental evaluation, aiming to reach conclusions regarding the assessment of research questions and hypotheses. Analysis. The results have shown the competitiveness of all the proposed training strategies through evaluation metrics commonly used in the research field. Conclusion. Statistical analyses confirmed that the uniqueness of suspiciousness scores guides the generation of superior heuristics for fault localization.

Navegar

Submissões Recentes