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.

Haemonchus contortus: A multiple-resistant Brazilian isolate and the costs for its characterization and maintenance for research use

The aim of this work was to determine the resistance level of Haemonchus contortus isolated from the Santa Inês flock of the Embrapa (Brazilian government's Agricultural Research Company), Southeast Livestock Unit (CPPSE), as well as to determine costs of characterizing and maintaining this isolate in host donors. Forty-two male Santa Inês lambs were experimentally infected with 4000 H. contortus infective larvae of the field isolate of CPPSE, called Embrapa2010, and divided into six treatment groups, which received triclorfon, albendazol plus cobalt sulfate, ivermectin, moxidectin, closantel and levamisole phosphate, as well as a negative control group (water). Egg per gram (EPG) counts were performed at 0, 3, 7, 10 and 14. days post treatment when the animals were slaughtered for parasite count. The data were analyzed using the RESO statistical program, considering anthelmintic resistance under 95% of efficacy. EPG and worm count presented a linear and significant relation with 94% determination coefficient. The susceptibility results obtained by RESO through both criteria (EPG and worm count) were equal, except for closantel, showing that the isolate Embrapa2010 is resistant to benzimidazoles, macrocyclic lactones and imidazothiazoles. The need of a control group did not appear to be essential since the result for susceptibility in the analyses with or without this group was the same. Suppression in egg production after treatment did not occur in the ivermectin and moxidectin groups. In the control group, the establishment percentage was just 12.5 because of the low number of third-stage larvae, resistance (innate and infection immunity) of the animals studied plus good nutrition. Drug classes presented similar efficacy between adults and immature stages. The costs for isolate characterization were calculated for 42 animals during 60. days. The total cost based on local market rates was approximately US$ 8000. The precise identification of Brazilian isolates and their establishment in host donors would be useful for laboratorial anthelmintic resistance diagnoses through in vitro tests, which has an annual cost of approximately US$ 2500 for maintenance in host donors. © 2012 Elsevier B.V.

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.