Vaccines are an old technique, known and used for over 200 years. However, it is likely that the arrival of the COVID-19 pandemic made the public debate around this technology become polarized at a level never seen before. Thus, this work aims to determine and understand factors that lead Brazilian users on Twitter to be favorable or not to vaccines by first determining users’ stances in relation to the vaccination topic and then using Machine Learning methods to infer demographic information and determine which are the socio-demographic factors that cause the greatest impact on users’ opinions on vaccines. First, a data set composed of relevant demographic information from users who stand for or against vaccines was generated. Then, from the collected data, charts were generated showing the distributions of the obtained demographic information and Machine Learning algorithms were applied to the data set in order to generate relevant models for the research. Finally, the information collected in the previous steps was analyzed in order to draw relevant conclusions about how each demographic factor considered influences the formation of Twitter users opinions on vaccines and their use. The methodology proposed produced informative and pertinent results, and it was possible to determine that age and location are the factors that cause the most significant influence on users’ opinions. Our work proposes an efficient and agile framework that can be easily and readily implemented and extended to understand not only stances on vaccines, but also opinions on any subject of public debate.

Question classification is an important component of Question Answering Systems responsible for identifying the type of an answer a particular question requires. For instance, “Who is the prime minister of the United Kingdom?” demands a name of a PERSON, while “When was the queen of the United Kingdom born?” entails a DATE. This work makes an extensible review of the most recent methods for Question Classification, taking into consideration their applicability in low-resourced languages. First, we propose a manual classification of the current state-of-the-art methods in four distinct categories: low, medium, high, and very high level of dependency on external resources. Second, we applied this categorization in an empirical comparison in terms of the amount of data necessary for training and performance in different languages. In addition to complementing earlier works in this field, our study shows a boost on methods relying on recent language models, overcoming methods not suitable for low-resourced languages.

Financial time series forecasting is regarded as one of the most challenging applications of time series forecasting. Many researchers have been focusing on this topic due to the potential of yielding significant profits on the invested money in a short time frame. Believing in the predictability of stock markets, traders have been using Technical Analysis tools for a very long time to analyze and predict the behavior of stocks, aiming to make the best investment decisions possible with this information. In addition, applying machine learning techniques to predict stock market movements has become an area of research that has received a lot of attention in recent years. Popular algorithms such as Artificial Neural Networks and Support Vector Machines have been widely used in this area and they have been reporting satisfactory performances. As an attempt to improve the accuracy of these algorithms, researchers have been proposing techniques to combine them, forming Ensemble Systems. This work presents the design of an Ensemble System based on Genetic Algorithm for forecasting the weekly prices' trend in the Sao Paulo Stock Exchange Index (Ibovespa Index). In order to evaluate the performance of the proposed method, experiments were conducted to compare it with other popular ensemble methods (e.g., Bagging, Boosting and Random Forests). Finally, the empirical results show that the proposed model outperforms the other ensemble methods. Therefore, this implies that the proposed approach can be used by traders as a promising tool for forecasting stock market prices.

The goal in the present paper is to propose, develop and show a method for classifying the spatial cognition degree of development on different individuals. Thirty-Seven undergraduate students had their electroencephalogram (EEG) recorded while engaged in 3-D images mental rotation tasks. Their spatial cognition degree of development was assessed using a BPR-5 psychological test. The Largest Lyapunov Exponent (LLE) was calculated from each of the 8 electrodes recorded. The LLEs were used as input for three different classifiers: i) multi-layer perceptron artificial neural network, ii) support vector machines, and iii) K-Nearest Neighbors. The best result was achieved by the MLP using the tansig transfer function. The proposed classification method can contribute and interact with other processes in the analysis and study of human spatial cognition, as in the understanding of the human intelligence at all. A better understanding and evaluation of the cognitive capabilities of an individual could suggest him elements of motivation, ease or natural inclinations, possibly affecting the decisions of his carrier positively.

This study proposes a new algorithm for supervised learning, based on the clonal selection principle exhibited in natural and artificial immune systems. The method, called Clonal Selection Classifier with Data Reduction (CSCDR), utilizes a fitness function based on the number of correct and incorrect pattern classifications made by each antibody. The algorithm tries to maximize this value through clonal selection processes such as mutation, affinity maturation and selection of the best individuals, transforming the training phase in an optimization problem. This leads to antibodies with more representativeness and thus decreases the amount of prototypes generated at the end of the algorithm. Experimental results on benchmark datasets of the UCI machine learning repository demonstrated the effectiveness of the CSCDR algorithm as a classification technique, combined with a considerable data reduction when compared to the results obtained by the well known Artificial Immune Recognition System (AIRS) and the original Clonal Selection Classifier Algorithm (CSCA).

In this paper an innovative software for mobile devices based on the Android operating system is presented. This tool of Information and Communication Technology (ICT) is designed to be used by brazilian health professionals in the data collection and storage tasks of general and oral health conditions, in home care in field trips to work with families in vulnerability. Its use provided more agility, precision and better outcomes in the care given to them. This article will discuss the major issues involved in the choice of the Android operating system, emphasizing how it was judged more adequate to be used in this project. innovative features that a mobile device offers. This work resulted in a valuable potential for the evolution of dental care within a program of the Ministry of Health of the Government of Brazil known as the Family Health Strategy.

This paper describes a novel solution to the rigid point pattern matching problem in Euclidean spaces of any dimension. Although we assume rigid motion, jitter is allowed. We present a noniterative, polynomial time algorithm that is guaranteed to find an optimal solution for the noiseless case. First, we model point pattern matching as a weighted graph matching problem, where weights correspond to Euclidean distances between nodes. We then formulate graph matching as a problem of finding a maximum probability configuration in a graphical model. By using graph rigidity arguments, we prove that a sparse graphical model yields equivalent results to the fully connected model in the noiseless case. This allows us to obtain an algorithm that runs in polynomial time and is provably optimal for exact matching between noiseless point sets. For inexact matching, we can still apply the same algorithm to find approximately optimal solutions. Experimental results obtained by our approach show improvements in accuracy over current methods, particularly when matching patterns of different sizes.

This article describes the implementation of a strategy that selects, destroys, and replaces some individuals of a population of six real autonomous mobile robots. This strategy was called Predation. We introduce Predation as a methodology for improving the performance of an embedded evolutionary system developed for the automatic design of robotic controllers. The paper describes how the evolutionary system controls such a small robot population in Teal time and the effects of predation in avoiding local optimum. It is able to achieve obstacle avoidance behaviour with the robot population evolving while deployed in the field, instead of just using the evolving group to develop an optimum controller for a single robot.

Reports the results obtained in a speaker identification system based on Bhattacharrya distance, which combines LP-derived cepstral coefficients, with a nonlinear dynamic feature namely fractal dimension. The nonlinear dynamic analysis starts with the phase space reconstruction, and the fractal dimension of the correspondent attractor trajectory is estimated. This analysis is performed in every speech window, providing a measure of a time-dependent fractal dimension. The corpus used in the tests is composed by 37 different speakers, and the best results are obtained when the fractal dimension is included, suggesting that the information added with this feature was not present so far.

This work aims to present the most relevant results derived from the development of a novel FPGA matrix. Nevertheless its capacity, its highlights are low cost and its ability to deal with high frequencies. This prototype matrix, named FLECHA, presents some structural novelties, as a different approach to perform the interconnections between logic cells and I/O pads and an internal controller. One of the major contributions of this work deals with the strategy of placing the logic cells in rows, allowing a drastic reduction of the number of switches without reducing interconnection capacity between logic cells and I/O pads. Following this principle, a new matrix presenting 600 equivalent gates was constructed including 40 logic cells and 40 programmable I/O pads. The FLECHA matrix is intended to implement simple logic functions as for fast "glue logic" between processors and memories, reaching an operational frequency of l45 MHz.