Efficient public transportation management is essential for the development of large urban centers, providing several benefits such as comprehensive coverage of population mobility, reduction of transport costs, better control of traffic congestion, and significant reduction of environmental impact limiting gas emissions and pollution. Realizing these benefits requires a deeply understanding the population and transit patterns and the adoption of approaches to model multiple relations and characteristics efficiently. This work addresses these challenges by providing a novel dataset that includes various public transportation components from three different systems: regular buses, subway, and BRT (Bus Rapid Transit). Our dataset comprises daily information from about 700,000 passengers in Salvador, one of Brazil’s largest cities, and local public transportation data with approximately 2,000 vehicles operating across nearly 400 lines, connecting almost 3,000 stops and stations. With data collected from March 2024 to March 2025 at a frequency lower than one minute, SUNT stands as one of the largest, most comprehensive, and openly available urban datasets in the literature.

Abstract Video surveillance has benefited greatly from advances in artificial intelligence, particularly in computer vision, and the number of monitored environments has consequently increased, creating new challenges in extracting relevant information. When multiple cameras cover adjacent areas, overlapping fields of view can cause the same subject to be detected across cameras, introducing duplicate counts. Although the literature offers established solutions, many rely on high-quality recordings and complex, computationally intensive methods, limiting their use on resource-constrained devices. In this work, we address these challenges with a solution that leverages minimal information about target subjects and uses a transductive strategy to detect duplicates based on interactions within overlapping fields of view. Experiments in real-world settings show that our approach suppresses duplicates effectively, making it suitable for deployment on resource-limited hardware. We evaluate state-of-the-art lightweight models with high inference speed, as well as classical re-identification methods, in scenarios with low-quality video and constrained devices. The results underscore the effectiveness of the proposed approach and motivate exploration of re-ID with domain adaptation, as well as anchor-free methods with weak or semi-supervised learning.

Hemophilia is a genetic disorder characterized by mutations in coagulation factor proteins, resulting in impaired blood coagulation. Despite recent advances in diagnosing and treating Hemophilia, the precise function of each residue within such proteins remains unclear. In this work, aiming to provide a crucial step to addressing this complex problem, we present a systematic approach that organizes the coagulation factor proteins into graphs to be later modeled by novel Graph Neural Networks (GNN). In our graphs, nodes represent amino acids, which can be connected by proximity in the three-dimensional structure. Our experiments on FVIII (coagulation factor VIII) proteins, responsible for causing Hemophilia A, presented significant results in predicting severe and mild forms of the disease. Moreover, focused on supporting the advance of novel recombinant therapeutic FVIII proteins, we adapted our study to predict the activity and expression of more than 300 in vitro alanine mutations. Besides innovating the form in which hemophilia is organized and modeled, this work presents a GNN architecture specifically designed to optimize the classification of FVIII proteins. Our results emphasize how graph-based approaches support a deeper understanding of Hemophilia A, thus providing a solid scientific basis for further research in this field.

The Intergovernmental Panel on Climate Change and the Intergovernmental Science-Policy Platform on Biodiversity and Ecosystem Services have emphasised unequivocal evidences about the impact of human actions on climate and biodiversity at alarming rates. In Brazilian terms, 2019 has been marked by controversial discussions among politicians and environmentalists, leading to misinformation and misinterpretations that clearly motivate the continuous collection and scientific analysis of data to support sustainable solutions. Aiming at dealing with this issue, this manuscript brings two contributions: (i) the creation of the Brazilian Forest Dataset, including Brazilian seed plants, Fraction of Absorbed Photosynthetically Active Radiation, meteorological and geographical data composing 8,482 attributes to model and predict 20 vegetation types; and (ii) the feasibility analysis on modelling this dataset in light of supervised machine learning algorithms, so we devise confident results on the Brazilian biodiversity. Experimental results confirm Random Forest and Support Vector Machines successfully adjust models, enabling researchers to predict the occurrence of specific types of vegetation in different regions of Brazil as well as analyse how the prediction accuracy changes along time after the collection of new data. Our contributions bring important tools to support the study on the evolution of the Brazilian biodiversity.

Source code quality plays a key role in software quality mainly due to its impact on software maintainability. Software engineers have been using source code metrics to support them to assess source code quality. Source code metrics quantify different source code characteristics. However, source code metric analysis still involves subjectivity. For instance, it is not trivial to decide whether a metric value is high or low. To reduce the eventual subjectivity of source code metrics analysis, several researchers are using Machine Learning algorithms. Therefore, in this paper, we designed a Fuzzy-based approach to extract characteristics and patterns present in source code versioning repositories in order to: i) assist the specialist in the interpretation of releases, especially when working with large volumes of source code; ii) from the release interpretation, specialists can improve the quality of the source code; and iii) monitor the evolution of the software as new releases are submitted to the repositories. We evaluated the proposed approach with the Linux Test Project repository, emphasizing the interpretability of large source code versioning repositories.

The performance of Fuzzy Rule-Based Classification Systems (FRBCSs) is highly affected by the increasing number of instances and attributes present in Big Data. Previously proposed approaches try to adapt FRBCSs to Big Data by distributing data processing with the MapReduce paradigm, by which the data is processed in two stages: Map and Reduce. In the Map stage, the data is divided into multiple blocks and distributed among processing nodes that process each block of data independently. In the Reduce stage, the results coming from every node in the Map stage are aggregated and a final result is returned. This methodology tackles vertical high dimensionality (high number of instances), but it does not approach datasets with simultaneous vertical and horizontal high dimensionality (high number of attributes), as it is the case of text datasets. In this work, we deal with the aforementioned drawbacks by proposing Summarizer, an approach for building reduced feature spaces for horizontally high dimensional data. To this end, we carry out an empirical study that compares a well-known classifier proposed for vertical high dimensionality datasets with and without the horizontal dimensionality reduction process proposed by Summarizer. Our findings show that existing classifiers that tackles vertical Big Data problems can be improved by adding the Summarizer approach to the learning process, which suggests that an unified learning algorithm for datasets with a high number of instances as well as a high number of attributes might be possible.

In this manuscript, we performed a scrutiny on hepatitis records collected in Brazil using statistical and computational tools aiming at analyzing the evolution of this disease during the period of 2007 and 2014. The study was performed in three phases. Initially, we used statistical tests to assess whether or not the notification cases were increasing. Then, we created a measure to quantify trends, without being affected by scale, thus allowing to compare the occurrence of hepatitis in different regions in Brazil. Finally, we used concept drift to detect the changing point when the notification behavior has changed over time. As a consequence of this study, public policies can be developed to deal with the increasing number of cases, specially by considering sexual transmissions.

A powerful and flexible organization of documents can be obtained by mixing fuzzy and possibilistic clustering. In such organization, documents can belong to more than one cluster simultaneously with different compatibility degrees. Clusters represent topics, which are identified by one or more descriptors extracted by a proposed method. In this manuscript, we investigated whether or not the descriptors extracted after applying possibilistic fuzzy clustering improve the flexible organization of documents. Experiments were carried out on real-world document collections and we evaluated the ability of descriptors to capture the essential information in every dataset. Results have shown the effectiveness of extracting possibilistic fuzzy cluster descriptors, improving the flexible organization of documents.

System flexibility means the ability of a system to manage imprecise and/or uncertain information. A lot of commercially available Information Retrieval Systems (IRS) address this issue at the level of query formulation. Another way to make the flexibility of an IRS possible is by means of the flexible organization of documents. Such organization can be carried out using clustering algorithms by which documents can be automatically organized in multiple clusters simultaneously. Fuzzy and possibilistic clustering algorithms are examples of methods by which documents can belong to more than one cluster simultaneously with different membership degrees. The interpretation of these membership degrees can be used to quantify the compatibility of a document with a particular topic. The topics are represented by clusters and the clusters are identified by one or more descriptors extracted by a proposed method. We aim to investigate if the performance of each clustering algorithm can affect the extraction of meaningful overlapping cluster descriptors. Experiments were carried using well-known collections of documents and the predictive power of the descriptors extracted from both fuzzy and possibilistic document clustering was evaluated. The results prove that descriptors extracted after both fuzzy and possibilistic clustering are effective and can improve the flexible organization of documents.

System flexibility means the ability of a system to manage imprecise and/or uncertain information. There are two ways to address the Information Retrieval Systems (IRS) flexibility: through methods that improve the query formulation and through methods that improve the document organization. Since the query formulation has obtained more attention in retrieval process, we aim to investigate the flexibility in document organization. When a document organization is carried out using fuzzy clustering, the documents can belong to more than one cluster simultaneously with different membership degrees, allowing the management of imprecise and/or uncertain information in the collection organization. Clusters represent topics and are identified by one or more descriptors. In this work we use an unsupervised method to extract cluster descriptors for a specific database and investigate whether the quality of the fuzzy cluster descriptors improves the flexible organization of documents.

Ontologies have been employed in applications that require semantic information representation and processing. However, traditional ontologies are not suitable to express fuzzy or vague information, which often occurs in human vocabulary as well as in several application domains. To deal with this limitation, concepts from the Fuzzy Set Theory can be incorporated into ontologies making it possible to represent and reason over fuzzy or vague knowledge. In this context, this paper proposes Fuzz-Onto, a meta-ontology for representing fuzzy ontologies which, so far, models fuzzy concepts, fuzzy relationships and fuzzy properties. In particular, the representation of fuzzy properties and linguistic terms makes it possible to combine fuzzy modeling in ontologies with existing fuzzy rule-based classification methods. The paper also presents a case study in the knowledge domain of scientific documents as an instantiation of the modeling-inference articulation.

The text mining process and its set of techniques have been widely used in order to look for new knowledge in textual documents, which can be recovered by information retrieval systems. There is a variety of methods developed to automatically organize documents based on the knowledge extracted from their content. The management of imprecision and uncertainty is very important to improve these methods. Therefore, this work proposes a method to manage imprecision and uncertainty in document organization, by clustering the documents in fuzzy clusters and extracting cluster descriptors. The proposed method was evaluated and the obtained results showed that this is a promising approach to deal with the problem of imprecision and uncertainty when organizing textual documents.

This work presents the integration of a fuzzy method and text mining to obtain an approach that enables the text documents classification to be closer to the user needs. The aim of this work is to develop a mechanism to reduce the high dimensionality of the attribute-value matrix obtained from the documents and, with this, to manage the imprecision and uncertainty using fuzzy rules to classify text documents. Some experiments have been run using different domains in order to validate the proposed approach and to compare the results with the ones obtained with the Ibk, J48, Naive Bayes and OneR classification methods. The advantages of the method, the experiments and the results obtained are discussed.

This work presents a hybrid fuzzy modeling approach based on the conditional fuzzy clustering algorithm, that aims to provide new means to handle the issue of interpretability of the rule base. The balance between interpretability and accuracy of fuzzy rules is addressed by means of the definition of contexts formed with a small number of input variables and the generation of clusters conditioned by the context defined. The rules are generated in a different format which have linguistic variables with their values as well as groups. Some experiments have been run using different domains in order to validate the proposed approach and to compare the results with the ones obtained with the Wang&Mendell and FCMeans methods. The advantages of the method, the experiments and the results obtained are discussed.