Defesa de Dissertação de Mestrado do aluno Marcelo Costalonga Cardoso

Título da dissertação: Can Machine Learning Replace a Reviewer in the Selection of Studies for Systematic Literature Review Updates?

Resumo: The importance of systematic literature reviews (SLRs) to find and synthesize new evidence for Software Engineering (SE) is well known, yet performing and keeping SLRs up-to-date is still a big challenge. One of the most exhaustive activities during an SLR is the study selection because of the large number of studies to be analyzed. Furthermore, to avoid bias, study selection should be conducted by more than one reviewer. [Objective] This dissertation aims to evaluate the use of machine learning (ML) text classification models to support the study selection in SLR updates and verify if such models can replace an additional reviewer. [Method] We reproduce the study selection of an SLR update performed by three experienced researchers, applying the ML models to the same dataset they used. We used two supervised ML algorithms with different configurations (Random Forest and Support Vector Machines) to train the models based on the original SLR. We calculated the study selection effectiveness of the ML models in terms of precision, recall, and fmeasure. We also compared the level of agreement between the studies selected by the ML models and the original reviewers by performing a Kappa Analysis. [Results] In our investigation, the ML models achieved an f-score of 0.33 for study selection, which is insufficient for conducting the task in an automated way. However, we found that such models could reduce the study selection effort by 33.9% without loss of evidence (keeping a 100% recall), discarding studies with a low probability of being included. In addition, the ML models achieved a moderate average kappa level of agreement of 0.42 with the reviewers. [Conclusion] The results indicate that ML is not ready to replace study selection by human reviewers and may also not be used to replace the need for an additional reviewer. However, there is potential for reducing the study selection effort of SLR updates.

Orientador: Prof. Dr. Marcos Kalinowski

Banca: Prof. Dr. Helio Côrtes Vieira Lopes | Profª. Dra. Maria Teresa Baldassarre | Prof. Dr. Markus Endler

Assista a defesa pelo link: https://puc-rio.zoom.us/j/4666190940?pwd=eUdNaDNSbnhEY3VWWU1DMGF0SkRjZz09

Autor: Djalma Lúcio Soares da Silva

Orientador: Alberto Barbosa Raposo

Data e Hora: 02/05/2024 às 12:30

Local: Videoconferência

Autor: Rodrigo Leite da Silva

Orientador: Edward Hermann Haeusler

Data e Hora: 30/04/2024 às 13:00

Local: RDC 415

Defesa de Tese de Doutorado do aluno Fernando Antonio Dantas Gomes Pinto.

Título da tese: Compliance Reasoning on Legal Norms: a logic-based approach

Resumo: Ensuring that a knowledge base with public administration acts contains only facts in accordance with its legislation becomes a challenge for any public manager. To achieve this, given the large volume of data generated by public companies, it is necessary to apply technological resources that assist in the process of analyzing the compliance of these acts. This work presents a computational architecture capable of extracting information published in official gazettes and then serializing it into two knowledge bases, RDF/XML triples of facts and RDF/XML triples of rules formalized in iALC logic, an intuitionistic description logic. To ensure the consistency of this knowledge base, an SAT solver for iALC was developed in the form of an intuitionistic semantic tableau. An extension of the first-order intuitionist tableau presented by Fetting (1960). This SAT solver is part of a module that, in addition to generating models and counter-examples for the compliance rules formalized in iALC, also generates a preliminary query code in SPARQL. This approach allows you to infer and certify the quality of the data available in the RDF/XML knowledge base of facts. To guarantee the quality of our SAT Solver, we carry out the soundness proof. of its rules. To ensure the quality of our logical approach, we built a set of 20 Competency Questions and applied our tool. The results showed the effectiveness and efficiency of our approach.

Orientador: Prof. Dr. Edward Hermann Haeusler

Banca: Prof. Dr. Sergio Lifschitz | Prof. Dr. Altigran Soares da Silva | Profª. Drª. Fernanda Araujo Baião | Prof. Dr. Bruno Lopes Vieira | Profª. Drª. Cecilia Reis Englander Lustosa | Prof. Dr. Bruno Cuconato Claro

Assista a defesa presencialmente na sala 511 do RDC

Autor: Gabriel de Andrade Busquim

Orientador: Marcos Kalinowski

Data e Hora: 30/04/2024 às 09:00

Local: Videoconferência

Autor: Robinson Callou de M Brasil Filho

Orientador: Edward Hermann Haeusler

Data e Hora: 30/04/2024 às 16:00

Local: RDC 511 – Hibrida

Autor: Marcelo Costalonga Cardoso

Orientador: Marcos Kalinowski

Data e Hora: 29/04/2024 às 10:00

Local: Videoconferência

Autor: Fernando Antonio Dantas Gomes Pinto

Orientador: Edward Hermann Haeusler

Data e Hora: 26/04/2024 às 09:30

Local: RDC 511

Autor: Pedro Thiago Cutrim dos Santos

Orientador: Sérgio Colcher

Data e Hora: 29/04/2024 às 09:00

Local: Videoconferência

Defesa de Dissertação de Mestrado do aluno Daniel Luca Alves.

Título da dissertação: Graph-Based Clustering In Deep Feature Space for Shape Matching

Resumo: Engineering projects rely on complex 3D CAD models throughout their life cycle. These 3D models consist of millions of geometries that impose challenges in storage, transmission, and rendering. Previous works have successfully employed shape matching techniques based on deep learning to reduce the memory required by these 3D models. In this work, we propose a graph-based algorithm that improves unsupervised clustering in deep feature space. This approach greatly improves shape matching accuracy and results in even lower memory requirements for the 3D models. In a labeled dataset, our method achieves a 95% model reduction, outperforming previous unsupervised techniques that achieved 87% and almost reaching the 97% reduction from a fully supervised approach. In an unlabeled dataset, our method achieves an average model reduction of 87% versus an average reduction of 77% from previous unsupervised techniques.

Orientador: Prof. Dr. Waldemar Celes Filho

Co-orientador: Prof. Dr Paulo Ivson Netto Santos

Banca: Prof. Dr. Alberto Barbosa Raposo | Prof. Dr. Anselmo Cardoso de Paiva | Prof. Dr. Lucas Caracas de Figueiredo

Assista a defesa pelo link: https://puc-rio.zoom.us/j/94119149852?pwd=dFpZTkR2Rll1NHZoM3pORmVicXRoZz09