HOW FAR do WE GET USING MACHINE LEARNING BLACK-BOXES?

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

An Intelligent System for Petroleum Well Drilling Cutting Analysis

Cutting analysis is a important and crucial task task to detect and prevent problems during the petroleum well drilling process. Several studies have been developed for drilling inspection, but none of them takes care about analysing the generated cutting at the vibrating shale shakers. Here we proposed a system to analyse the cutting's concentration at the vibrating shale shakers, which can indicate problems during the petroleum well drilling process, such that the collapse of the well borehole walls. Cutting's images are acquired and sent to the data analysis module, which has as the main goal to extract features and to classify frames according to one of three previously classes of cutting's volume. A collection of supervised classifiers were applied in order to allow comparisons about their accuracy and efficiency. We used the Optimum-Path Forest (OPF), Artificial Neural Network using Multi layer Perceptrons (ANN-MLP), Support Vector Machines (SVM) and a Bayesian Classifier (BC) for this task. The first one outperformed all the remaining classifiers. Recall that we are also the first to introduce the OPF classifier in this field of knowledge. Very good results show the robustness of the proposed system, which can be also integrated with other commonly system (Mud-Logging) in order to improve the last one's efficiency.

Álcool e comportamento: efeitos na aprendizagem e memória

Excessive alcohol consumption is responsible for many harmful effects on individuals and society. Despite years of research, the mechanisms by which alcohol affects neurological functions and the exact causes of cognitive impairment related to long-term use are unknown. In this sense, this master study proposed to observe how different doses of alcohol affect the addiction response and the learning ability of two fish species: Betta splendens and Danio rerio, the latter a commonly model due to organizational and functional characteristics shared with mammals. For this, different concentrations of ethanol (0%, 0.1%, 0.25%, 1% and 1.5%) were used in acute, chronic and withdrawal treatments. We tested the fish in three experimental protocols: 1) alcohol addiction potential using conditioned place preference, 2) associative conditioning using light as unconditioned stimulus and food as conditioned stimulus and 3) spatial learning using a maze without cues. For the alcohol addiction potential, preference between two different places in a shuttle box was tested before and after alcohol exposure (chronic and acute). In this test, the animals intoxicated by 0.1% did not change behavior, while animals receiving 1% and 1.5% alcohol changed the initial preference to the side where they received alcohol For the associative conditioning, the results show that the groups undergoing low dose (0.1%), both in chronic and withdrawal treatment, learned the task faster than control; groups under 0.25 and 1% alcohol withdrawal learned the task after control; groups chronically intoxicated with these doses did not learn the task. For the spatial learning test, fish submitted to acute and chronic treatments decreased the time to exit the maze; there were significant differences in the animal s performance in a dose-dependent pattern. This difference was not observed for the withdrawal treatment. Given these results, we conclude that the effects of alcohol on learning are dependent on the dosage. Furthermore, low doses of alcohol seem to maximize animal performance on learning tasks and do not alter their seeking behavior, while higher doses induced addition and hinder learning

HIGH STRENGTH CONCRETE: THE REINFORCED CONCRETE OF THE CENTURY 21(ST)

This work is about the 21st century reinforced concrete analysis under the point of view of its constituent materials. First of all it is described the theoretical approach of the bending elements calculated based on the Norms BAEL 91 standarts. After that, numerical load-displacement are presented from reinforced concrete beams and plates validated by experimental data. The numerical modellings has been carried on in the program CASTEM 2000. In this program a elastoplastic model of Drucker-Prager defines the rupture surface of the concrete in non associative plasticity. The crack is smeared on the Gauss points of the finite elements with formation criterion starting from the definition of the rupture surface in the branch traction-traction of the Rankine model. The reinforcements were modeled in a discrete approach with perfect bond. Finally, a comparative analysis is made between the numerical results and calculated criteria showing the future of high performance reinforced concrete in this beginning of 21st century.

Crianças no pátio escolar :a utilização dos espaços e o comportamento infantil no recreio

The interest for understanding the relationship of the child with its environment has increased in the whole world during the last few years. Several researchers, using Environmental Psychology as basis, have analyzed the implications of this relation for the child development and the organization of playful spaces. Being a place where children spend a great part of their time and develop many intellectual and social abilities, the school becomes one of the main focus of this research. This study investigated different sectors of the outdoor area of NEI -UFRN, during the recreation time, in which the use of space and the interaction between children were analyzed, through the observation of the child behavior (place-centered and individual-centered mapping). The results had disclosed that the school s outdoor area and its equipments presents a great range of choices possible to the children, however its occupation is not uniform: there are areas very used and others almost without use. Generally, this heterogeneity happens again in relation to the distribution of the interaction states in the sectors, the friendly associative behavior being the most present. The observation of children behaviors favored a better understanding of the use of the spaces, and contributed for discussion about the environment what these users really need for a healthy development, including differences in related to gender, age and daytime. In spite of the studied outdoor areas being vast, pleasant and varied, it needs a better distribution of its equipments and a plan that allows greater children participation in the place organization

Obtenção de polímeros graftizados de quitosana e estudo das propriedades físico-químicas para aplicação na indústria do petróleo

Chitosan is a biopolymer derived from the shells of crustaceans, biodegradable, inexpensive and renewable with important physical and chemical properties. Moreover, the different modifications possible in its chemical structure generate new properties, making it an attractive polysaccharide owing to its range of potential applications. Polymers have been used in oil production operations. However, growing concern over environmental constraints has prompted oil industry to search for environmentally sustainable materials. As such, this study sought to obtain chitosan derivatives grafted with hydrophilic (poly(ethylene glycol), mPEG) and/or hydrophobic groups (n-dodecyl) via a simple (one-pot) method and evaluate their physicochemical properties as a function of varying pH using rheology, small-angle Xray scattering (SAXS), dynamic light scattering (DLS) and zeta potential. The chitosan derivatives were prepared using reductive alkylation under mild reaction conditions and the chemical structure of the polymers was characterized by nuclear magnetic resonance (1H NMR) and CHN elemental analysis. Considering a constant mPEG/Chitosan molar ratio on modification of chitosan, the solubility of the polymer across a wide pH range (acidic, neutral and basic) could only be improved when some of the amino groups were submitted to reacetylation using the one-pot method. Under these conditions, solubility is maintained even with the simultaneous insertion of n-dodecyl. On the other hand, the solubility of derivatives obtained only through mPEG incorporation using the traditional methodology, or with the ndodecyl group, was similar to that of its precursor. The hydrophilic group promoted decreased viscosity of the polymer solutions at 10 g/L in acid medium. However, at basic pH, both viscosity and thermal stability increased, as well as exhibited a pronounced pseudoplastic behavior, suggesting strong intermolecular associations in the alkaline medium. The SAXS results showed a polyelectrolyte behavior with the decrease in pH for the polymer systems. DLS analyses revealed that although the dilute polymer solutions at 1 g/L and pH 3 exhibited a high density of protonated amino groups along the polymer chain, the high degree of charge contributed significantly to aggregation, promoting increased particle size with the decrease in pH. Furthermore, the hydrophobic group also contributed to increasing the size of aggregates in solution at pH 3, whereas the hydrophilic group helped reduce their size across the entire pH range. Nevertheless, the nature of aggregation was dependent on the pH of the medium. Zeta potential results indicated that its values do not depend solely on the surface charge of the particle, but are also dependent on the net charge of the medium. In this study, water soluble associative polymers exhibit properties that can be of great interest in the petroleum industry

Utilizando Pesos estáticos e dinâmicos em sistemas multi-classificadores com diferentes níveis de diversidade

Although some individual techniques of supervised Machine Learning (ML), also known as classifiers, or algorithms of classification, to supply solutions that, most of the time, are considered efficient, have experimental results gotten with the use of large sets of pattern and/or that they have a expressive amount of irrelevant data or incomplete characteristic, that show a decrease in the efficiency of the precision of these techniques. In other words, such techniques can t do an recognition of patterns of an efficient form in complex problems. With the intention to get better performance and efficiency of these ML techniques, were thought about the idea to using some types of LM algorithms work jointly, thus origin to the term Multi-Classifier System (MCS). The MCS s presents, as component, different of LM algorithms, called of base classifiers, and realized a combination of results gotten for these algorithms to reach the final result. So that the MCS has a better performance that the base classifiers, the results gotten for each base classifier must present an certain diversity, in other words, a difference between the results gotten for each classifier that compose the system. It can be said that it does not make signification to have MCS s whose base classifiers have identical answers to the sames patterns. Although the MCS s present better results that the individually systems, has always the search to improve the results gotten for this type of system. Aim at this improvement and a better consistency in the results, as well as a larger diversity of the classifiers of a MCS, comes being recently searched methodologies that present as characteristic the use of weights, or confidence values. These weights can describe the importance that certain classifier supplied when associating with each pattern to a determined class. These weights still are used, in associate with the exits of the classifiers, during the process of recognition (use) of the MCS s. Exist different ways of calculating these weights and can be divided in two categories: the static weights and the dynamic weights. The first category of weights is characterizes for not having the modification of its values during the classification process, different it occurs with the second category, where the values suffers modifications during the classification process. In this work an analysis will be made to verify if the use of the weights, statics as much as dynamics, they can increase the perfomance of the MCS s in comparison with the individually systems. Moreover, will be made an analysis in the diversity gotten for the MCS s, for this mode verify if it has some relation between the use of the weights in the MCS s with different levels of diversity

Uma Análise Comparativa entre Sistemas de Combinação de Classificadores com Distribuição Vertical dos Dados

In systems that combine the outputs of classification methods (combination systems), such as ensembles and multi-agent systems, one of the main constraints is that the base components (classifiers or agents) should be diverse among themselves. In other words, there is clearly no accuracy gain in a system that is composed of a set of identical base components. One way of increasing diversity is through the use of feature selection or data distribution methods in combination systems. In this work, an investigation of the impact of using data distribution methods among the components of combination systems will be performed. In this investigation, different methods of data distribution will be used and an analysis of the combination systems, using several different configurations, will be performed. As a result of this analysis, it is aimed to detect which combination systems are more suitable to use feature distribution among the components

Uma análise da aplicação do modelo de Rede Neural RePART em Comitês de classificadores

RePART (Reward/Punishment ART) is a neural model that constitutes a variation of the Fuzzy Artmap model. This network was proposed in order to minimize the inherent problems in the Artmap-based model, such as the proliferation of categories and misclassification. RePART makes use of additional mechanisms, such as an instance counting parameter, a reward/punishment process and a variable vigilance parameter. The instance counting parameter, for instance, aims to minimize the misclassification problem, which is a consequence of the sensitivity to the noises, frequently presents in Artmap-based models. On the other hand, the use of the variable vigilance parameter tries to smoouth out the category proliferation problem, which is inherent of Artmap-based models, decreasing the complexity of the net. RePART was originally proposed in order to minimize the aforementioned problems and it was shown to have better performance (higer accuracy and lower complexity) than Artmap-based models. This work proposes an investigation of the performance of the RePART model in classifier ensembles. Different sizes, learning strategies and structures will be used in this investigation. As a result of this investigation, it is aimed to define the main advantages and drawbacks of this model, when used as a component in classifier ensembles. This can provide a broader foundation for the use of RePART in other pattern recognition applications

Aplicação de ontologias para métodos de negociação de um sistema multiagente para o reconhecimento de padrões

The use of intelligent agents in multi-classifier systems appeared in order to making the centralized decision process of a multi-classifier system into a distributed, flexible and incremental one. Based on this, the NeurAge (Neural Agents) system (Abreu et al 2004) was proposed. This system has a superior performance to some combination-centered methods (Abreu, Canuto, and Santana 2005). The negotiation is important to the multiagent system performance, but most of negotiations are defined informaly. A way to formalize the negotiation process is using an ontology. In the context of classification tasks, the ontology provides an approach to formalize the concepts and rules that manage the relations between these concepts. This work aims at using ontologies to make a formal description of the negotiation methods of a multi-agent system for classification tasks, more specifically the NeurAge system. Through ontologies, we intend to make the NeurAge system more formal and open, allowing that new agents can be part of such system during the negotiation. In this sense, the NeurAge System will be studied on the basis of its functioning and reaching, mainly, the negotiation methods used by the same ones. After that, some negotiation ontologies found in literature will be studied, and then those that were chosen for this work will be adapted to the negotiation methods used in the NeurAge.

Dilema da diversidade-acurácia: um estudo empírico no contexto de multiclassificadores

Multi-classifier systems, also known as ensembles, have been widely used to solve several problems, because they, often, present better performance than the individual classifiers that form these systems. But, in order to do so, it s necessary that the base classifiers to be as accurate as diverse among themselves this is also known as diversity/accuracy dilemma. Given its importance, some works have investigate the ensembles behavior in context of this dilemma. However, the majority of them address homogenous ensemble, i.e., ensembles composed only of the same type of classifiers. Thus, motivated by this limitation, this thesis, using genetic algorithms, performs a detailed study on the dilemma diversity/accuracy for heterogeneous ensembles

Seleção de atributos em comitês de classificadores utilizando algoritmos genéticos

Classifier ensembles are systems composed of a set of individual classifiers and a combination module, which is responsible for providing the final output of the system. In the design of these systems, diversity is considered as one of the main aspects to be taken into account since there is no gain in combining identical classification methods. The ideal situation is a set of individual classifiers with uncorrelated errors. In other words, the individual classifiers should be diverse among themselves. One way of increasing diversity is to provide different datasets (patterns and/or attributes) for the individual classifiers. The diversity is increased because the individual classifiers will perform the same task (classification of the same input patterns) but they will be built using different subsets of patterns and/or attributes. The majority of the papers using feature selection for ensembles address the homogenous structures of ensemble, i.e., ensembles composed only of the same type of classifiers. In this investigation, two approaches of genetic algorithms (single and multi-objective) will be used to guide the distribution of the features among the classifiers in the context of homogenous and heterogeneous ensembles. The experiments will be divided into two phases that use a filter approach of feature selection guided by genetic algorithm

Abordagem de construção de arquitetura homogênea para comitês via meta-aprendizagem

In the world we are constantly performing everyday actions. Two of these actions are frequent and of great importance: classify (sort by classes) and take decision. When we encounter problems with a relatively high degree of complexity, we tend to seek other opinions, usually from people who have some knowledge or even to the extent possible, are experts in the problem domain in question in order to help us in the decision-making process. Both the classification process as the process of decision making, we are guided by consideration of the characteristics involved in the specific problem. The characterization of a set of objects is part of the decision making process in general. In Machine Learning this classification happens through a learning algorithm and the characterization is applied to databases. The classification algorithms can be employed individually or by machine committees. The choice of the best methods to be used in the construction of a committee is a very arduous task. In this work, it will be investigated meta-learning techniques in selecting the best configuration parameters of homogeneous committees for applications in various classification problems. These parameters are: the base classifier, the architecture and the size of this architecture. We investigated nine types of inductors candidates for based classifier, two methods of generation of architecture and nine medium-sized groups for architecture. Dimensionality reduction techniques have been applied to metabases looking for improvement. Five classifiers methods are investigated as meta-learners in the process of choosing the best parameters of a homogeneous committee.

Análise das medidas de boa e má diversidade na construção de comitês de classificadores através de metaheurísticas de otimização multiobjetivo

Committees of classifiers may be used to improve the accuracy of classification systems, in other words, different classifiers used to solve the same problem can be combined for creating a system of greater accuracy, called committees of classifiers. To that this to succeed is necessary that the classifiers make mistakes on different objects of the problem so that the errors of a classifier are ignored by the others correct classifiers when applying the method of combination of the committee. The characteristic of classifiers of err on different objects is called diversity. However, most measures of diversity could not describe this importance. Recently, were proposed two measures of the diversity (good and bad diversity) with the aim of helping to generate more accurate committees. This paper performs an experimental analysis of these measures applied directly on the building of the committees of classifiers. The method of construction adopted is modeled as a search problem by the set of characteristics of the databases of the problem and the best set of committee members in order to find the committee of classifiers to produce the most accurate classification. This problem is solved by metaheuristic optimization techniques, in their mono and multi-objective versions. Analyzes are performed to verify if use or add the measures of good diversity and bad diversity in the optimization objectives creates more accurate committees. Thus, the contribution of this study is to determine whether the measures of good diversity and bad diversity can be used in mono-objective and multi-objective optimization techniques as optimization objectives for building committees of classifiers more accurate than those built by the same process, but using only the accuracy classification as objective of optimization

Diagnóstico da degradação ambiental no município de Areia Branca-RN por geotecnologias

The municipality of Areia Branca is within the mesoregion of West Potiguar and within the microregion of Mossoró, covering an area of 357,58 km2. Covering an area of weakness in terms of environmental, housing, together with the municipality of Grossos-RN, the estuary of River Apodi-Mossoró. The municipality of Areia Branca has historically suffered from a lack of planning regarding the use and occupation of land as some economic activities, attracted by the extremely favorable natural conditions, have exploited their natural resources improperly. The aim of this study is to quantify and analyze the environmental degradation in the municipality. Thus initially was performed a characterization of land use using remote sensing, geoprocessing and geographic information system GIS in order to generate data and information on the municipal scale, which may serve as input to the environmental planning and land use planning in the region. From this perspective, were used a Landsat 5 image TM sensor for the year 2010. In the processing of this image was used SPRING 5.2 and applied a supervised classification using the classifier regions, which was employed Bhattacharya Distance method with a threshold at 30%. Thus was obtained the land use map that was analyzed the spatial distribution of different types of the use that is occurring in the city, identifying areas that are being used incorrectly and the main types of environmental degradation. And further, were applied the methodology proposed by Beltrame (1994), Physical Diagnosis Conservationist under some adaptations for quantifying the level of degradation or conservation study area. As results, the indexes were obtained for the parameters in the proposed methodology, allowing quantitatively analyze the degradation potential of each sector. From this perspective, considering a scale of 0 to 100, sector A and sector B had value 31.20 units of risk of physical deterioration. And the C sector, has shown its value - 34.64 units degradation risk and should be considered a priority in relation to the achievement of conservation actions