Novas abordagens para configurações automáticas dos parâmetros de controle em comitês de classificadores

Significant advances have emerged in research related to the topic of Classifier Committees. The models that receive the most attention in the literature are those of the static nature, also known as ensembles. The algorithms that are part of this class, we highlight the methods that using techniques of resampling of the training data: Bagging, Boosting and Multiboosting. The choice of the architecture and base components to be recruited is not a trivial task and has motivated new proposals in an attempt to build such models automatically, and many of them are based on optimization methods. Many of these contributions have not shown satisfactory results when applied to more complex problems with different nature. In contrast, the thesis presented here, proposes three new hybrid approaches for automatic construction for ensembles: Increment of Diversity, Adaptive-fitness Function and Meta-learning for the development of systems for automatic configuration of parameters for models of ensemble. In the first one approach, we propose a solution that combines different diversity techniques in a single conceptual framework, in attempt to achieve higher levels of diversity in ensembles, and with it, the better the performance of such systems. In the second one approach, using a genetic algorithm for automatic design of ensembles. The contribution is to combine the techniques of filter and wrapper adaptively to evolve a better distribution of the feature space to be presented for the components of ensemble. Finally, the last one approach, which proposes new techniques for recommendation of architecture and based components on ensemble, by techniques of traditional meta-learning and multi-label meta-learning. In general, the results are encouraging and corroborate with the thesis that hybrid tools are a powerful solution in building effective ensembles for pattern classification problems.

Uso de confiabilidade na rotulação de exemplos em problemas de classificação multirrótulo com aprendizado semissupervisionado

The techniques of Machine Learning are applied in classification tasks to acquire knowledge through a set of data or information. Some learning methods proposed in literature are methods based on semissupervised learning; this is represented by small percentage of labeled data (supervised learning) combined with a quantity of label and non-labeled examples (unsupervised learning) during the training phase, which reduces, therefore, the need for a large quantity of labeled instances when only small dataset of labeled instances is available for training. A commom problem in semi-supervised learning is as random selection of instances, since most of paper use a random selection technique which can cause a negative impact. Much of machine learning methods treat single-label problems, in other words, problems where a given set of data are associated with a single class; however, through the requirement existent to classify data in a lot of domain, or more than one class, this classification as called multi-label classification. This work presents an experimental analysis of the results obtained using semissupervised learning in troubles of multi-label classification using reliability parameter as an aid in the classification data. Thus, the use of techniques of semissupervised learning and besides methods of multi-label classification, were essential to show the results

Investigando a combinação de técnicas de aprendizado semissupervisionado e classificação hierárquica multirrótulo

Data classification is a task with high applicability in a lot of areas. Most methods for treating classification problems found in the literature dealing with single-label or traditional problems. In recent years has been identified a series of classification tasks in which the samples can be labeled at more than one class simultaneously (multi-label classification). Additionally, these classes can be hierarchically organized (hierarchical classification and hierarchical multi-label classification). On the other hand, we have also studied a new category of learning, called semi-supervised learning, combining labeled data (supervised learning) and non-labeled data (unsupervised learning) during the training phase, thus reducing the need for a large amount of labeled data when only a small set of labeled samples is available. Thus, since both the techniques of multi-label and hierarchical multi-label classification as semi-supervised learning has shown favorable results with its use, this work is proposed and used to apply semi-supervised learning in hierarchical multi-label classication tasks, so eciently take advantage of the main advantages of the two areas. An experimental analysis of the proposed methods found that the use of semi-supervised learning in hierarchical multi-label methods presented satisfactory results, since the two approaches were statistically similar results

Redes de aprendizado em sistemas complexos de produção

Procura-se demonstrar neste artigo que o arranjo inter-organizacional típico dos Sistemas Complexos de Produção é o de rede de firmas, marcada por uma forte especialização dos agentes que a compõem e uma intensa complementaridade entre eles. Nesse tipo de arranjo, a empresa que exerce a governança da rede busca estimular o processo de eficiência coletiva. Essa busca, por sua vez, dada a freqüente heterogeneidade dos agentes, termina por induzir a rede de firmas a transformar-se em uma rede de aprendizado. Apesar do conhecimento sobre essas redes ser ainda muito precário, podem-se levantar, com base na literatura revisada e no exame de uma rede de aprendizado em implantação no Brasil, os seguintes aspectos: ela precisa ter um propósito claro, traduzível em uma meta a ser atingida por intermédio do processo de aprendizado; é necessário criar uma estrutura, que pode tender ao virtual, e definir recursos e mecanismos a serem utilizados em sua implantação e sustentação; e deve-se tentar prever, a partir de outras experiências, as inevitáveis dificuldades que surgirão no planejamento e operacionalização dessas redes.

A avaliação de desempenho como processo essencialmente humano: a meta-avaliação da empresa X

A Avaliação de Desempenho geralmente é vista como uma ferramenta na qual a subjetividade é um viés a ser controlado. O presente trabalho traça uma trajetória da Avaliação, desde o seu surgimento até os dias atuais. Este levantamento histórico apresenta o tratamento dado às questões do Humano até o momento, a partir da revisão de vários autores. Utilizando um referencial quantitativo e qualitativo, unindo a Abordagem Fenomenológica e a Matriz de Correlações, foi realizada a Meta-Avaliação do processo de uma empresa na qual a prática da Avaliação ocorre há alguns anos, sendo considerada ponto importante para o seu sucesso. O presente estudo demonstra que o Humano é parte indissociável da Avaliação, a qual não pode mais ser considerada como ferramenta, mas como processo. Ao invés do controle da subjetividade, vista anteriormente mais como fonte de problemas e distorções, propõe-se o reconhecimento mais amplo de sua presença: tanto em seus aspectos complexos e problemáticos como em seu enorme potencial de desenvolvimento e aprendizado. Ao invés do controle, propõe-se o engajamento; ao invés de retirar o máximo possível a subjetividade, tê-la como aliada; ao invés de uma ferramenta minuciosamente estruturada, um processo flexível que acompanhe o dinamismo inerente ao Humano. Ou seja, ter o Humano da Avaliação atuando a favor do processo, cujo grande fim é o aprendizado.

Aplicação de técnicas de aprendizado de máquina no reconhecimento de classes estruturais de proteínas

Nowadays, classifying proteins in structural classes, which concerns the inference of patterns in their 3D conformation, is one of the most important open problems in Molecular Biology. The main reason for this is that the function of a protein is intrinsically related to its spatial conformation. However, such conformations are very difficult to be obtained experimentally in laboratory. Thus, this problem has drawn the attention of many researchers in Bioinformatics. Considering the great difference between the number of protein sequences already known and the number of three-dimensional structures determined experimentally, the demand of automated techniques for structural classification of proteins is very high. In this context, computational tools, especially Machine Learning (ML) techniques, have become essential to deal with this problem. In this work, ML techniques are used in the recognition of protein structural classes: Decision Trees, k-Nearest Neighbor, Naive Bayes, Support Vector Machine and Neural Networks. These methods have been chosen because they represent different paradigms of learning and have been widely used in the Bioinfornmatics literature. Aiming to obtain an improvment in the performance of these techniques (individual classifiers), homogeneous (Bagging and Boosting) and heterogeneous (Voting, Stacking and StackingC) multiclassification systems are used. Moreover, since the protein database used in this work presents the problem of imbalanced classes, artificial techniques for class balance (Undersampling Random, Tomek Links, CNN, NCL and OSS) are used to minimize such a problem. In order to evaluate the ML methods, a cross-validation procedure is applied, where the accuracy of the classifiers is measured using the mean of classification error rate, on independent test sets. These means are compared, two by two, by the hypothesis test aiming to evaluate if there is, statistically, a significant difference between them. With respect to the results obtained with the individual classifiers, Support Vector Machine presented the best accuracy. In terms of the multi-classification systems (homogeneous and heterogeneous), they showed, in general, a superior or similar performance when compared to the one achieved by the individual classifiers used - especially Boosting with Decision Tree and the StackingC with Linear Regression as meta classifier. The Voting method, despite of its simplicity, has shown to be adequate for solving the problem presented in this work. The techniques for class balance, on the other hand, have not produced a significant improvement in the global classification error. Nevertheless, the use of such techniques did improve the classification error for the minority class. In this context, the NCL technique has shown to be more appropriated

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.

Ecosystem Engineering Effects On Species Diversity Across Ecosystems: A Meta-analysis.

Ecosystem engineering is increasingly recognized as a relevant ecological driver of diversity and community composition. Although engineering impacts on the biota can vary from negative to positive, and from trivial to enormous, patterns and causes of variation in the magnitude of engineering effects across ecosystems and engineer types remain largely unknown. To elucidate the above patterns, we conducted a meta-analysis of 122 studies which explored effects of animal ecosystem engineers on species richness of other organisms in the community. The analysis revealed that the overall effect of ecosystem engineers on diversity is positive and corresponds to a 25% increase in species richness, indicating that ecosystem engineering is a facilitative process globally. Engineering effects were stronger in the tropics than at higher latitudes, likely because new or modified habitats provided by engineers in the tropics may help minimize competition and predation pressures on resident species. Within aquatic environments, engineering impacts were stronger in marine ecosystems (rocky shores) than in streams. In terrestrial ecosystems, engineers displayed stronger positive effects in arid environments (e.g. deserts). Ecosystem engineers that create new habitats or microhabitats had stronger effects than those that modify habitats or cause bioturbation. Invertebrate engineers and those with lower engineering persistence (<1 year) affected species richness more than vertebrate engineers which persisted for >1 year. Invertebrate species richness was particularly responsive to engineering impacts. This study is the first attempt to build an integrative framework of engineering effects on species diversity; it highlights the importance of considering latitude, habitat, engineering functional group, taxon and persistence of their effects in future theoretical and empirical studies.

Anxiety-like Effects Of Meta-chlorophenylpiperazine In Paradoxically Sleep-deprived Mice.

Chlorophenylpiperazines (CPP) are psychotropic drugs used in nightclub parties and are frequently used in a state of sleep deprivation, a condition which can potentiate the effects of psychoactive drugs. This study aimed to investigate the effects of sleep deprivation and sleep rebound (RB) on anxiety-like measures in mCPP-treated mice using the open field test. We first optimized our procedure by performing dose-effect curves and examining different pretreatment times in naïve male Swiss mice. Subsequently, a separate cohort of mice underwent paradoxical sleep deprivation (PSD) for 24 or 48h. In the last experiment, immediately after the 24h-PSD period, mice received an injection of saline or mCPP, but their general activity was quantified in the open field only after the RB period (24 or 48h). The dose of 5mgmL(-1) of mCPP was the most effective at decreasing rearing behavior, with peak effects 15min after injection. PSD decreased locomotion and rearing behaviors, thereby inhibiting a further impairment induced by mCPP. Plasma concentrations of mCPP were significantly higher in PSD 48h animals compared to the non-PSD control group. Twenty-four hours of RB combined with mCPP administration produced a slight reduction in locomotion. Our results show that mCPP was able to significantly change the behavior of naïve, PSD, and RB mice. When combined with sleep deprivation, there was a higher availability of drug in plasma levels. Taken together, our results suggest that sleep loss can enhance the behavioral effects of the potent psychoactive drug, mCPP, even after a period of rebound sleep.

Modeling The Effects Of Temperature And Ph On The Resistance Of Alicyclobacillus Acidoterrestris In Conventional Heat-treated Fruit Beverages Through A Meta-analysis Approach.

In this work, all publicly-accessible published findings on Alicyclobacillus acidoterrestris heat resistance in fruit beverages as affected by temperature and pH were compiled. Then, study characteristics (protocols, fruit and variety, °Brix, pH, temperature, heating medium, culture medium, inactivation method, strains, etc.) were extracted from the primary studies, and some of them incorporated to a meta-analysis mixed-effects linear model based on the basic Bigelow equation describing the heat resistance parameters of this bacterium. The model estimated mean D* values (time needed for one log reduction at a temperature of 95 °C and a pH of 3.5) of Alicyclobacillus in beverages of different fruits, two different concentration types, with and without bacteriocins, and with and without clarification. The zT (temperature change needed to cause one log reduction in D-values) estimated by the meta-analysis model were compared to those ('observed' zT values) reported in the primary studies, and in all cases they were within the confidence intervals of the model. The model was capable of predicting the heat resistance parameters of Alicyclobacillus in fruit beverages beyond the types available in the meta-analytical data. It is expected that the compilation of the thermal resistance of Alicyclobacillus in fruit beverages, carried out in this study, will be of utility to food quality managers in the determination or validation of the lethality of their current heat treatment processes.

Association Between Unilateral Tonsillar Enlargement And Lymphoma In Children: A Systematic Review And Meta-analysis.

Lymphoma is the most common head and neck malignancy in children, and palatine tonsils asymmetry is the most frequent clinical manifestation of tonsillar lymphoma. However, several studies with children with tonsillar asymmetry found no case of lymphoma, showing that the relationship of tonsillar asymmetry with lymphoma is unclear. In this review, we aimed to identify the association between tonsillar asymmetry and tonsillar lymphoma in children by conducting systematic reviews of the literature on children with palatine tonsil lymphoma and tonsillar asymmetry. Articles comprising the paediatric age group (up to 18 years) with information concerning clinical manifestations of tonsillar lymphoma or the diagnosis of the tonsillar asymmetry were included. The main cause of asymmetry of palatine tonsils was lymphoid hyperplasia, followed by lymphoma and nonspecific benign changes. The asymmetry of tonsils was present in 73.2% of cases of lymphoma. There was an association between asymmetric palatine tonsils and lymphoma, with a likelihood ratio of 43.5 for children with asymmetry of palatine tonsils and 8938.4 for children with asymmetry of tonsils and other signs of suspicion for malignancy. We also provide recommendations on the management of suspicious cases of palatine tonsil lymphoma.

Tradução & aprendizado de língua estrangeira: o ponto de vista do aluno

This paper reports some exemplary data related to a research project on the role of translation in foreign language teaching-learning. The data were collected through a questionnaire administered to 47 Brazilian ESL learners. Specifically, the points of the analysis are: how the translation process is conceived by the students; why and when the translation is used by the learners in classroom situations; mother tongue/foreign language relationships in this specific context, among other aspects. The findings reveal that translation, when used a mediating resource for foreign language teaching-learning, can promote target language management.

Curva de aprendizado e flutuações a curto e longo prazos com perimetria de freqüência dupla (FDT)

OBJECTIVE: To evaluate the learning effect, short-term fluctuation and long-term fluctuation in healthy subjects undergoing frequency doubling perimetry (FDP). METHODS: Twenty healthy young subjects underwent FDT (program N30, full threshold) in one eye (right). Each subject was tested once in the first three sessions and three times in the fourth session. Both short- and long-term fluctuations were studied as the average fluctuation of all the tested points or as a point-to-point fluctuation. To study the learning effect, the MDs values of the first session were compared to the second, third and fourth sessions. RESULTS: In the short-term analysis (3 examination done in the last session), the total mean sensitivity was 31.91 ± 1.20 dB and the mean MD and PSD were 0.84 ± 1.85 and 3.73 ± 1.55 dB, respectively. The average short-term fluctuation was 1.72 ± 0.38 dB. When the four examination, performed at different visits, were compared, the average mean sensitivity of all sessions and the average long-term fluctuation were 31.75 ± 1.11 and 2.16 ± 0.26 dB, respectively. The MD averages of the first, second, third and fourth tests were 0.11 ± 2.14 dB, 0.47 ± 1.64 dB, 1.16 ± 1.62 dB and 0.98 ± 1.92 dB respectively. The MD difference between the first and the third and between the first and the fourth examinations were statistically significant (p<0.05). CONCLUSION: The threshold sensitivity detected by FDP is influenced by both short- and long-term fluctuations. We observed a mild learning effect that shoud be taken into account whenever a patient undergoes this test for the first time.

Correlation of meta 1 expression with culture stage, cell morphology and infectivity in Leishmania (Leishmania) amazonensis promastigotes

The parasitic protozoan Leishmania (Leishmania) amazonensis alternates between mammalian and insect hosts. In the insect host, the parasites proliferate as procyclic promastigotes andthen differentiate into metacyclic infective forms. The meta 1 gene is preferentially expressed during metacyclogenesis. Meta 1 expression profile determination along parasite growth curves revealed that the meta 1 mRNA level peaked at the early stationary phase then decreased to an intermediate level. No correlation was observed between meta 1 expression and infectivity. Conversely, infectivity correlated with the increase of apoptotic cells in the late stationary phase.

A systematic review with procedural assessments and meta-analysis of Low Level Laser Therapy in lateral elbow tendinopathy (tennis elbow)

Background: Recent reviews have indicated that low level level laser therapy (LLLT) is ineffective in lateral elbow tendinopathy (LET) without assessing validity of treatment procedures and doses or the influence of prior steroid injections. Methods: Systematic review with meta-analysis, with primary outcome measures of pain relief and/or global improvement and subgroup analyses of methodological quality, wavelengths and treatment procedures. Results: 18 randomised placebo-controlled trials (RCTs) were identified with 13 RCTs (730 patients) meeting the criteria for meta-analysis. 12 RCTs satisfied half or more of the methodological criteria. Publication bias was detected by Egger's graphical test, which showed a negative direction of bias. Ten of the trials included patients with poor prognosis caused by failed steroid injections or other treatment failures, or long symptom duration or severe baseline pain. The weighted mean difference (WMD) for pain relief was 10.2 mm [95% CI: 3.0 to 17.5] and the RR for global improvement was 1.36 [1.16 to 1.60]. Trials which targeted acupuncture points reported negative results, as did trials with wavelengths 820, 830 and 1064 nm. In a subgroup of five trials with 904 nm lasers and one trial with 632 nm wavelength where the lateral elbow tendon insertions were directly irradiated, WMD for pain relief was 17.2 mm [95% CI: 8.5 to 25.9] and 14.0 mm [95% CI: 7.4 to 20.6] respectively, while RR for global pain improvement was only reported for 904 nm at 1.53 [95% CI: 1.28 to 1.83]. LLLT doses in this subgroup ranged between 0.5 and 7.2 Joules. Secondary outcome measures of painfree grip strength, pain pressure threshold, sick leave and follow-up data from 3 to 8 weeks after the end of treatment, showed consistently significant results in favour of the same LLLT subgroup (p < 0.02). No serious side-effects were reported. Conclusion: LLLT administered with optimal doses of 904 nm and possibly 632 nm wavelengths directly to the lateral elbow tendon insertions, seem to offer short-term pain relief and less disability in LET, both alone and in conjunction with an exercise regimen. This finding contradicts the conclusions of previous reviews which failed to assess treatment procedures, wavelengths and optimal doses.