Fabricio Breve

São Paulo State University | Unesp · Departamento de Estatistica, Matemática Aplicada e Computação DEMAC

This paper investigates video game identification through single screenshots, utilizing five convolutional neural network (CNN) architectures (MobileNet, DenseNet, EfficientNetB0, EfficientNetB2, and EfficientNetB3) across 22 home console systems, spanning from Atari 2600 to PlayStation 5, totalling 8,796 games and 170,881 screenshots. Confirming t...

Time series data is of crucial importance in different domains, such as financial and medical applications. However, obtaining a large amount of labeled time series data is an expensive and time-consuming task, which becomes the process of building an effective machine learning model a challenge. In these scenarios, algorithms that can deal with re...

Recent surveys show that smartphone-based computer vision tools for visually impaired individuals often rely on outdated computer vision algorithms. Deep-learning approaches have been explored, but many require high-end or specialized hardware that is not practical for users. Therefore, developing deep learning systems that can make inferences usin...

More and more, nowadays, better performance and quality of current classifiers are required when the topic is fraud detection. In this context, processes such as feature selection help to increase the quality of the results obtained by the existing classifiers in the literature, since the high dimensionality of current datasets and redundant inform...

Semi-supervised learning (SSL) has become an interesting research area due to its capacity for learning in scenarios where both labeled and unlabeled data are available. In this work, we focus on the task of transduction—when the objective is to label all data presented to the learner—with a mean-field approximation to the Potts model. Aiming at th...

COVID-19 quickly became a global pandemic after only four months of its first detection. It is crucial to detect this disease as soon as possible to decrease its spread. The use of chest X-ray (CXR) images became an effective screening strategy, complementary to the reverse transcription-polymerase chain reaction (RT-PCR). Convolutional neural netw...

Semi-supervised learning (SSL) has become an interesting research area due to its capacity for learning in scenarios where both labeled and unlabeled data are available. In this work, we focus on the task of transduction - when the objective is to label all data presented to the learner - with a mean-field approximation to the Potts model. Aiming a...

COVID-19 quickly became a global pandemic after only four months of its first detection. It is crucial to detect this disease as soon as possible to decrease its spread. The use of chest X-ray (CXR) images became an effective screening strategy, complementary to the reverse transcription-polymerase chain reaction (RT-PCR). Convolutional neural netw...

Interpretation of machine learning models has become one of the most important topics of research due to the necessity of maintaining control and avoid bias in these algorithms. Since many machine learning algorithms are published every day, there is a need for novel model-agnostic interpretation approaches that could be used to interpret a great v...

The present work deals with the analysis of the synchronization possibility in chaotic oscillators, either completely or per phase, using a coupling force among them, so they can be used in attention systems. The neural models used were Hodgkin-Huxley, Hindmarsh-Rose, Integrate-and-Fire, and Spike-Response-Model. Discrete models such as Aihara, Rul...

In the interactive image segmentation task, the Particle Competition and Cooperation (PCC) model is fed with a complex network, which is built from the input image. In the network construction phase, a weight vector is needed to define the importance of each element in the feature set, which consists of color and location information of the corresp...

In the interactive image segmentation task, the Particle Competition and Cooperation (PCC) model is fed with a complex network, which is built from the input image. In the network construction phase, a weight vector is needed to define the importance of each element in the feature set, which consists of color and location information of the corresp...

Navigation and mobility are some of the major problems faced by visually impaired people in their daily lives. Advances in computer vision led to the proposal of some navigation systems. However, most of them require expensive and/or heavy hardware. In this paper we propose the use of convolutional neural networks (CNN), transfer learning, and semi...

In the interactive image segmentation task, the Particle Competition and Cooperation (PCC) model is fed with a complex network, which is built from the input image. In the network construction phase, a weight vector is needed to define the importance of each element in the feature set, which consists of color and location information of the corresp...

Restricted Boltzmann Machines (RBM) are stochastic neural networks mainly used for image reconstruction and unsupervised feature learning. An enhanced version, the temperature-based RBM (T-RBM), considers a new temperature parameter during the learning process that influences the neu-rons' activation. Nevertheless, the major vulnerability of such m...

Particle competition and cooperation (PCC) is a graph-based semi-supervised learning approach. When PCC is applied to interactive image segmentation tasks, pixels are converted into network nodes, and each node is connected to its k-nearest neighbors, according to the distance between a set of features extracted from the image. Building a proper ne...

Many interactive image segmentation techniques are based on semi-supervised learning. The user may label some pixels from each object and the SSL algorithm will propagate the labels from the labeled to the unlabeled pixels, finding object boundaries. This paper proposes a new SSL graph-based interactive image segmentation approach, using undirected...

Object selection refers to the mechanism of extracting objects of interest while ignoring other objects and background in a given visual scene. It is a fundamental issue for many computer vision and image analysis techniques and it is still a challenging task to artificial visual systems. Chaotic phase synchronization takes place in cases involving...

Semi-supervised learning methods are usually employed in the classification of data sets where only a small subset of the data items is labeled. In these scenarios, label noise is a crucial issue, since the noise may easily spread to a large portion or even the entire data set, leading to major degradation in classification accuracy. Therefore, the...

This paper presents an extension proposal of the semi-supervised learning method known as Particle Competition and Cooperation for carrying out tasks of image segmentation. Preliminary results show that this is a promising approach. Este artigo apresenta uma proposta de extens\~ao do modelo de aprendizado semi-supervisionado conhecido como Competi\...

Interactive image segmentation is a topic of many studies in image processing. In a conventional approach, a user marks some pixels of the object(s) of interest and background, and an algorithm propagates these labels to the rest of the image. This paper presents a new graph-based method for interactive segmentation with two stages. In the first st...

Interactive image segmentation is a topic of many studies in image processing. In a conventional approach, a user marks some pixels of the object(s) of interest and background, and an algorithm propagates these labels to the rest of the image. This paper presents a new graph-based method for interactive segmentation with two stages. In the first st...

Machine Learning is an increasing area over the last few years and it is one of the highlights in Artificial Intelligence area. Nowadays, one of the most studied areas is Semi-supervised learning, mainly due to its characteristic of lower cost in labeling sample data. The most active category in this subarea is that of graph-based models. The Parti...

Particle competition and cooperation (PCC) is a graph-based semi-supervised learning approach. When PCC is applied to interactive image segmentation tasks, pixels are converted into network nodes, and each node is connected to its k-nearest neighbors, according to the distance between a set of features extracted from the image. Building a proper ne...

In this paper, we propose a new active semi-supervised growing neural gas (GNG) model, named Active Consensus-Based Semi-Supervised GNG, or ACSSGNG. This model extends the former CSSGNG model by introducing an active mechanism for querying more representative samples in comparison to a random, or passive, selection. Moreover, as a semi-supervised m...

Semi-supervised learning methods exploit both labeled and unlabeled data items in their training process, requiring only a small subset of labeled items. Although capable of drastically reducing the costs of labeling process, such methods are directly dependent on the effectiveness of distance measures used for building the kNN graph. On the other...

Software development process requires judicious quality control, using performance indicators to support decision-making in the different processes chains. This paper recommends the use of machine learning with the semi supervised algorithms to analyze these indicators. In this context, this paper proposes the use of visualization techniques of mul...

A microblogging, such as the Twitter, is a Social Networking Service that allows the publication of short messages. Currently, Twitter has more than 270 million monthly active users, and it is widely used to discuss the most variety of topics. Due to the large amount of information circulating on Twitter, and the facility to publish and read messag...

Semi-supervised learning methods employ both labeled and unlabeled data in their training process. Therefore, they are commonly applied to interactive image processing tasks, where a human specialist may label a few pixels from the image and the algorithm would automatically propagate them to the remaining pixels, classifying the entire image. The...

Semi-supervised learning methods are usually employed in the classification of data sets where only a small subset of the data items is labeled. In these scenarios, label noise is a crucial issue, since the noise may easily spread to a large portion or even the entire data set, leading to major degradation in classification accuracy. Therefore, the...

Concept drift, which refers to non stationary learning problems over time, has increasing importance in machine learning and data mining. Many concept drift applications require fast response, which means an algorithm must always be (re)trained with the latest available data. But the process of data labeling is usually expensive and/or time consumi...

Both Semi-Supervised Leaning and Active Learning are techniques used when unlabeled data is abundant, but the process of labeling them is expensive and/or time consuming. In this paper, those two machine learning techniques are combined into a single nature-inspired method. It features particles walking on a network built from the data set, using a...

Both Active Learning and Semi-Supervised Learning are important techniques when labeled data are scarce and unlabeled data are abundant. In this paper, these two machine learning techniques are combined into a new nature-inspired method, which employs particles walking in networks generated from the data. It uses combined competitive and cooperativ...

Semi-supervised learning is applied to classification problems where only a small portion of the data items is labeled. In these cases, the reliability of the labels is a crucial factor, because mislabeled items may propagate wrong labels to a large portion or even the entire data set. This paper aims to address this problem by presenting a graph-b...

Semi-supervised learning is one of the important topics in machine learning, concerning with pattern classification where only a small subset of data is labeled. In this paper, a new network-based (or graph-based) semi-supervised classification model is proposed. It employs a combined random-greedy walk of particles, with competition and cooperatio...

Concept drift is a problem of increasing importance in machine learning and data mining. Data sets under analysis are no longer only static databases, but also data streams in which concepts and data distributions may not be stable over time. However, most learning algorithms produced so far are based on the assumption that data comes from a fixed...

Identification and classification of overlapping nodes in networks are important topics in data mining. In this paper, a network-based (graph-based) semi-supervised learning method is proposed. It is based on competition and cooperation among walking particles in a network to uncover overlapping nodes by generating continuous-valued outputs (soft l...

Identification and classification of overlap nodes in communities is an important topic in data mining. In this paper, a new graph-based (network-based) semi-supervised learning method is proposed. It is based on competition and cooperation among walking particles in the network to uncover overlap nodes, i.e., the algorithm can output continuous-va...

In machine learning study, semi-supervised learning has received increasing interests in the last years. It is applied to classification problems where only a small portion of the data points is labeled. In these situations, the reliability of these labels is extremely important because it is common to have mislabeled samples in a data set and thes...

Semi-Supervised Learning (SSL) is a machine learning research area aiming the development of techniques which are able to take advantage from both labeled and unlabeled samples. Additionally, most of the times where SSL techniques can be deployed, only a small portion of samples in the data set is labeled. To deal with such situations in a straight...

Identification and classification of overlap nodes in communities is an important topic in data mining. In this paper, a new clustering method to uncover overlap nodes in complex networks is proposed. It is based on particles walking and competing with each other, using random-deterministic movement. The new community detection algorithm can output...

Object selection refers to the mechanism of extracting objects of interest while ignoring other objects and background in a given visual scene. It is a fundamental issue for many computer vision and image analysis techniques and it is still a challenging task to artificial visual systems. Chaotic phase synchronization takes place in cases involving...

Chaotic phase synchronization among coupled oscillators is a phenomenon of interest in many physical and engineering systems. It has also been observed in biological systems, where groups of different functional units interact with each other in order to produce coherent behaviors in higher levels. While biological systems have facility to capture...

Biological systems have facility to capture salient object(s) in a given scene, but it is still a difficult task to be accomplished by artificial vision systems. In this paper a visual selection mechanism based on the integrate and fire neural network is proposed. The model not only can discriminate objects in a given visual scene, but also can del...

Semi-supervised learning is an important topic in machine learning. In this paper, a network-based semi-supervised classification method is proposed. Class labels are propagated by combined random-deterministic walking of particles and competition among them. Different from other graph-based methods, our model does not rely on loss function or regu...

In this paper a visual selection mechanism based on an integrate and fire neural network is proposed for selecting objects in a given visual scene. In comparison to other visual selection approaches, our model is able to capture attention of objects in complex forms, including those linearly non-separable, and also processes a combination of featur...

Synchronization and chaos play important roles in neural activities and have been applied in oscillatory correlation modeling for scene and data analysis. Although it is an extensively studied topic, there are still few results regarding synchrony in locally coupled systems. In this paper we give a rigorous proof to show that large numbers of coupl...

Classifier combination experiments using the multilayer perceptron (MLP) were carried out using noisy soil science multispectral images, which were obtained using a tomograph scanner. Using few units in the MLP hidden layer, images were classified using a single classifier. Later we used classifier combining techniques as bagging, decision template...

In this paper, a Visual Selection and a Shifting Mechanisms based on a lattice of coupled chaotic Wilson-Cowan oscillators is proposed. The oscillators representing each object in a given visual scene are synchronized to produce a chaotic trajectory. A cooperation and competition mechanisms are also introduced to accelerate oscillating frequency of...

Classifier combination experiments using neural network-based classifiers were carried out using noisy soil science multispectral images, which were obtained using a tomograph scanner. Using few units in the hidden layer images were classified by the Multilayer Perceptron (MLP) and the Radial Basis Function Network (RBF). Later we used classifier c...

In this paper we present a set of experiments in order to recognize materials in multispectral images, which were obtained with a tomograph scanner. These images were classified by a neural network based classifier (Multilayer Perceptron) and classifier combining techniques (Bagging, Decision Templates and Dempster-Shafer) were investigated. We als...

One salient feature of complex networks is the pres-ence of communities, or groups of densely connected nodes. Community detection can not only help to understand the topological structure of complex networks, but also provide new techniques for real applications, such as data mining. In this paper, we propose a new model for community detection by...

Pattern Recognition is a subject being used in a multidisciplinary scope, with different approaches. One of them is its application in computerized tomography images, commonly acquired in order to do medical diagnosis, but they have been used in several other applications as well, including Soil Science. The objective of this work is to study and t...

Redes complexas é um campo de pesquisa científica recente e bastante ativo que estuda redes de larga escala com estruturas topológicas não triviais, tais como redes de computadores, redes de telecomunicações, redes de transporte, redes sociais e redes biológicas. Muitas destas redes são naturalmente divididas em comunidades ou módulos e, portanto,...