Particle Competition and Cooperation in Networks for Semi-Supervised Learning

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

Particle Competition and Cooperation in Networks for Semi-Supervised Learning with Concept Drift

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 distribution, so they are not suitable to handle concept drifts. Moreover, some concept drifts applications requires fast response, which means an algorithm must always be (re) trained with the latest available data. But the process of labeling data is usually expensive and/or time consuming when compared to unlabeled data acquisition, thus only a small fraction of the incoming data may be effectively labeled. Semi-supervised learning methods may help in this scenario, as they use both labeled and unlabeled data in the training process. However, most of them are also based on the assumption that the data is static. Therefore, semi-supervised learning with concept drifts is still an open challenge in machine learning. Recently, a particle competition and cooperation approach was used to realize graph-based semi-supervised learning from static data. In this paper, we extend that approach to handle data streams and concept drift. The result is a passive algorithm using a single classifier, which naturally adapts to concept changes, without any explicit drift detection mechanism. Its built-in mechanisms provide a natural way of learning from new data, gradually forgetting older knowledge as older labeled data items became less influent on the classification of newer data items. Some computer simulation are presented, showing the effectiveness of the proposed method.

Particle competition and cooperation to prevent error propagation from mislabeled data in semi-supervised learning

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-based (network-based) semi-supervised learning method, specifically designed to handle data sets with mislabeled samples. The method uses teams of walking particles, with competitive and cooperative behavior, for label propagation in the network constructed from the input data set. The proposed model is nature-inspired and it incorporates some features to make it robust to a considerable amount of mislabeled data items. Computer simulations show the performance of the method in the presence of different percentage of mislabeled data, in networks of different sizes and average node degree. Importantly, these simulations reveals the existence of the critical points of the mislabeled subset size, below which the network is free of wrong label contamination, but above which the mislabeled samples start to propagate their labels to the rest of the network. Moreover, numerical comparisons have been made among the proposed method and other representative graph-based semi-supervised learning methods using both artificial and real-world data sets. Interestingly, the proposed method has increasing better performance than the others as the percentage of mislabeled samples is getting larger. © 2012 IEEE.

A multi-objective evaluation of the impact of the penetration of Distributed Generation

This paper proposes a methodology to consider the effects of the integration of DG on planning. Since DG has potential to defer investments in networks, the impact of DG on grid capacity is evaluated. A multi-objective optimization tool based on the meta-heuristic MEPSO is used, supporting an alternative approach to exploiting the Pareto front features. Tests were performed in distinct conditions with two well-known distribution networks: IEEE-34 and IEEE-123. The results combined minimization and maximization in order to produce different Pareto fronts and determine the extent of the impact caused by DG. The analysis provides useful information, such as the identification of futures that should be considered in planning. A future means a set of realizations of all uncertainties. MEPSO also presented a satisfactory performance in obtaining the Pareto fronts. © 2011 IEEE.

Fuzzy community structure detection by particle competition and cooperation

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 labels), corresponding to the levels of membership from the nodes to each of the communities. Moreover, the proposed method can be applied to detect overlapping data items in a data set of general form, such as a vector-based data set, once it is transformed to a network. Usually, label propagation involves risks of error amplification. In order to avoid this problem, the proposed method offers a mechanism to identify outliers among the labeled data items, and consequently prevents error propagation from such outliers. Computer simulations carried out for synthetic and real-world data sets provide a numeric quantification of the performance of the method. © 2012 Springer-Verlag.

Automação do despacho dinâmico de viaturas para o atendimento das ordens de serviços nas redes de distribuição de energia elétrica

Pós-graduação em Engenharia Elétrica - FEIS

A formação continuada de professores do ensino superior para a atuação docente on-line: desafios e possibilidades

Pós-graduação em Educação - FCT

Redes de transformação do processo de inovação: o caminho entre a descoberta e a comercialização

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Transformando Terra em Território: construção e dinâmica do sistema local territorial agroecológico em Francisco Beltrão, Paraná

Pós-graduação em Geografia - FCT

Otimização de sistemas de distribuição de energia elétrica radiais usando programação cônica de segunda ordem inteira mista

Pós-graduação em Engenharia Elétrica - FEIS

As dimensões geográficas dos Arranjos Produtivos Locais

This article aims to further discuss the Local Productive Arrangements (APLs), considering some geographical visions thinking about spatial configuration and the economic and social processes that characterize them, configuring a wide range of territorialities and productive territories that mark the landscape current Brazilian. In this sense, APLs are present today in both the figure of those who study analytical concept for regional development, and as a public policy supporting networks and supply chains in their territorial bases, especially small businesses. Thus, this arrangements can be read, geographically, as territorial productive specializations that are configured in spatial circuits of production, integrated with other regions, localities and supply chains through the morphology of networks and districts and grounded in networks of urban networks of material and immaterial flows which are bringing urban centers of different sizes. Considering the multidimensionality of the subject, the clusters have certain weaknesses in terms of their assumptions and perspectives, especially the limitations of the tool if designed just for resources and policies applied at the local level. Suggest the approach of a "geography of APLs" is to seek treat it from a territorial and socio reading.

Modelos matemáticos e computacionais para descrever a transmissão de dois sorotipos de vírus de dengue

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

A matemática contábil: das lides comerciais para os cursos secundários técnicos e sua transformação em setor acadêmico no Brasil (1808-1970)

Pós-graduação em Educação Matemática - IGCE

O papel das redes de transformação no processo de inovação: estudos de caso sobre a descoberta e a comercialização da inovação

Innovation is widely recognized as important. In addition, in this context, innovation networks have gained importance in academic studies, since an organization alone, does not always have access to all necessary resources. Gobbo Junior and Olsson (2010) proposed a model of network innovation whereby the transformation networks would be the linking structures between exploration and exploitation networks. In this context, this paper presents two case studies of innovation networks, aiming to increase the understanding on transformation networks. The objective was to understand how they interconnect exploration and exploitation networks; the main actors present in this interface; and to evaluate whether these actors can act as agents, to accelerate the innovation process. It was possible to verify how the transformation networks interconnect exploration and exploitation, and identify the practices and their main actors.

Análise de redes sociais e aspectos financeiros da produção de tilápias em tanques-rede na uhe de Ilha Solteira

Pós-graduação em Agronegócio e Desenvolvimento - Tupã