Comportamento do camarão de água doce macrobrachium rosenbergii (De Man, 1879) em cultivos misto e monossexo

Understanding the behavioral activities of freshwater shrimp in captivity is of paramount importance for the appropriate management of the species. In Brazil, the shrimp Macrobrachium rosenbergii is currently the most widely used species in the freshwater shrimp culture due to its high potential for cultivation and good market acceptance. Thus, the present study aimed to describe and characterize the behavioral activities of M. rosenbergii in monosex and in mixed (male and female) (manuscript 1, 2 and 3) populations and the growth performance of this species in restrictive feeding conditions and in different feeding management (manuscript 4 and 5, respectively) . Juvenile and adult shrimps were collected from ponds of the Aquaculture Station - Unidade Especializada em Ciências Agrárias - Universidade Federal do Rio Grande do Norte (UFRN), Macaíba/RN and then transferred to the Laboratório de Estudos do Comportamento do Camarão LECC (Laboratory for Shrimp Behavioral Studies) of the Universidade Federal do Rio Grande do Norte (UFRN). For each treatment , eight aquaria of 250 L (50 cm x 50 cm x 100 cm) were used in a closed recirculating water system with artificial lighting, constant aeration , continuous filtration through a biochemical and biological filter (canister filter), and fine sand as substrate . The water quality was monitored daily. The lab consisted of two rooms with artificial lighting system , controlled by a timer with dark / light cycle of 12:12 h . In manuscript 1, the behavioral categories of the species were presented through an ethogram, which described 31 behaviors, subdivided into general and agonistic behaviors. Manuscript 2 compared the behavioral profile of shrimps in male and in female monosex and mixed populations over 24 hours in laboratory. In three types (mixed, male monosex and female monosex) of populations during the light and dark phases of the 24 hour cycle, the shrimps showed higher occurrence of cleaning behavior. Manuscript 3 examined the influence of the color of the shelter on the frequency of its use and behavioral activities of shrimp in mixed, in male monosex and in female monosex populations over 24 hours. We observed that the shrimp M. rosenbergii burrow more frequently during the light phase in male monosex and mixed populations; they also tend to choose the black shelters. Female monosex populations tend to use red and orange shelters. In manuscript 4, we evaluated in laboratory the behavioral activities and growth performance of juvenile shrimps under food restriction. We observed that a mild food restriction may be used since there is no loss concerning the growth of the animals; feeding management on alternate days , compared to daily management can be financially productive both reducing labor costs and reducing the amount of feed used . Manuscript 5 evaluated the behavior of shrimps in monosex and in mixed populations, as well as the latency of reach the food according to feed offer (tray or food dispersal) . Our results indicate that animals adjust to both types of feed offer food dispersal as much as tray, but they spend more time to reach the feed when it is offered in trays (feeders). Comparing culture types (mixed, male monosex and female monosex), the latency to reach the food was lower for female monosex population. The data obtained in this study demonstrate the importance of identifying different pressures and environmental stimuli on the behavioral responses of this species. This knowledge would support management improvement to optimize the levels of animals‟ welfare, resulting in a better zootecnical performance

Otimização em comitês de classificadores: uma abordagem baseada em filtro para seleção de subconjuntos de atributos

Traditional applications of feature selection in areas such as data mining, machine learning and pattern recognition aim to improve the accuracy and to reduce the computational cost of the model. It is done through the removal of redundant, irrelevant or noisy data, finding a representative subset of data that reduces its dimensionality without loss of performance. With the development of research in ensemble of classifiers and the verification that this type of model has better performance than the individual models, if the base classifiers are diverse, comes a new field of application to the research of feature selection. In this new field, it is desired to find diverse subsets of features for the construction of base classifiers for the ensemble systems. This work proposes an approach that maximizes the diversity of the ensembles by selecting subsets of features using a model independent of the learning algorithm and with low computational cost. This is done using bio-inspired metaheuristics with evaluation filter-based criteria

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

Analisando o desempenho do ClassAge: um sistema multiagentes para classificação de padrões

The use of multi-agent systems for classification tasks has been proposed in order to overcome some drawbacks of multi-classifier systems and, as a consequence, to improve performance of such systems. As a result, the NeurAge system was proposed. This system is composed by several neural agents which communicate and negotiate a common result for the testing patterns. In the NeurAge system, a negotiation method is very important to the overall performance of the system since the agents need to reach and agreement about a problem when there is a conflict among the agents. This thesis presents an extensive analysis of the NeurAge System where it is used all kind of classifiers. This systems is now named ClassAge System. It is aimed to analyze the reaction of this system to some modifications in its topology and configuration

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

Uma abordagem ergonômica para análise da qualidade do pescado, desde sua captura ao seu desembarque na praia, resultante da atividade dos jangadeiros de Ponta Negra - Natal/RN

The artisan fishing activity, which involves historical - cultural, environmental, social, political, economi c, among other factors, presents, nowadays, as an important source of income, creating jobs and food, contributing to the permanence of man in their own birthplace. However, the fish, considered one of the most perishable foods, requires a proper handling and conservation, from capture to its availability in the market, in order to slow the deterioration process. Thereby, this dissertation aims to study the effect of the manipulation practices on fish quality, from capture to its landing on the beach, resul ting from fisherman’s activity from Ponta Negra - Natal/RN. It also presents the purpose of analyzing the quality of the fish and propose recommendations for their proper handling and possible solutions to add value to the product, through the improvement of the quality and good handling practices. For this purpose, the methodology used was based on ergonomic analysis of their work through observational techniques and interactional with the focus group, the jangadeiros, to understand their activity and eval uated the freshness and quality of the fish by sensory analysis, and microbiological parameters and physicochemical from existing legislation Ordinance No. 185 of May 13, 1997 and RIISPOA - amended on December 1, 2007 and RDC No. 12, dated January 2, 2001. According to the results obtained in laboratory tests, it can be established, the acceptable quality of fish as the existing rules and regulations parameters , not getting significant deterioration caused by poor handling and improper storage of fish.

Influência do tipo de abrigo e da frequência de oferta alimentar no comportamento do camarão Macrobrachium rosenbergii (De Man 1879)

Macrobrachium rosenbergii is a freshwater prawn which presents agonistic behavior and heterogeneous growth. It is known that captive conditions can intensify agonism causing injuries and decreased survival, generating a condition of poor welfare. Based on this, we aim to investigate the behavior of M. rosenbergii in the juvenile phase according to different types of shelter and frequencies of feed offer, emphasizing their agonistic behavior. For this, juveniles were observed in the laboratory in three steps. At step I we characterized the behavioral profile; prawns were kept in eight aquariums (27 prawns/m2 ), identified and observed four times along both phases of 24 h light cycle. At step II (2 experiments), we evaluated the use of shelters (brick or polyethylene rolls) and their influence on agonism by the animals. For classification of animals in dominance rank, the method used was David's Score. At step III (3 experiments), we evaluated different frequencies of feed offer on the behavior of individuals, in particular agonism. Results showed that juveniles do not present a pattern activity/inactivity between the phases of the light cycle. We identified a dominance hierarchy among individuals taking advantage of access to food by the dominant, which showed greater weight gain although the frequency of intake did not differ between individuals. The type of shelter influenced the behavior of animals. Brick shelter generated a higher frequency of permanence and a reduction in the frequency of agonistic interactions. The distribution of food more frequently throughout the day, decreased the motivation of animals for food, as well as to fight. Prawns fed four times showed lower frequency of feed intake and agonistic interactions. Thus, we conclude the shelters which reduce animal’s detection by coespecifics and offer the food four times along the day reduce agonistic behavior. This result causes na improvement in life quality of the prawns and also in its quality as final product.

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.