Reproductive biology of an endemic Physalaemus of the Brazilian Atlantic forest, and the trade-of between clutch and egg size in terrestrial breeders of the P. signifer group

Physalaemus crombiei is a small foam-nesting frog endemic to the Atlantic forest. It is a member of the P. signifer group known only from its type locality in Santa Teresa, State of Espírito Santo, and from another locality in the State of Bahia, Brazil. Most Physalaemus species are aquatic breeders, and species in the P. signifer group are the only ones exhibiting a tendency toward terrestrial reproduction in the genus. Here we describe the reproductive period, breeding site and reproductive modes of P. crombiei from a third population in the Atlantic forest, southeastern Brazil. We also investigated reproductive effort and size-fecundity relationships in females. Reproductive traits were compared to other species in the genus Physalaemus, especially those included in the P. signifer group. Physalaemus crombiei is a prolonged breeder, reproducing throughout the year with a peak of activity during the most rainy months (October-March). Males called from the humid forest foor and eggs embedded in foam nests were deposited in the water as well as on the humid foor amidst the leaf litter, or inside fallen leaves or tree holes containing rainwater on the forest foor. As expected, P. crombiei exhibited three alternative reproductive modes, as described for other species of the P. signifer group. The number of eggs produced per female varied from 91 to 250. Female body size is positively correlated both with ovary mass and clutch size (number of eggs per clutch). Variation in the number and size of eggs observed in Physalaemus species may be explained not only by female size, but also by the terrestrial reproductive mode exhibited by the species in the P. signifer group.

Robust and fast vowel recognition using optimum-path forest

The applications of Automatic Vowel Recognition (AVR), which is a sub-part of fundamental importance in most of the speech processing systems, vary from automatic interpretation of spoken language to biometrics. State-of-the-art systems for AVR are based on traditional machine learning models such as Artificial Neural Networks (ANNs) and Support Vector Machines (SVMs), however, such classifiers can not deal with efficiency and effectiveness at the same time, existing a gap to be explored when real-time processing is required. In this work, we present an algorithm for AVR based on the Optimum-Path Forest (OPF), which is an emergent pattern recognition technique recently introduced in literature. Adopting a supervised training procedure and using speech tags from two public datasets, we observed that OPF has outperformed ANNs, SVMs, plus other classifiers, in terms of training time and accuracy. ©2010 IEEE.

Intrusion detection system using optimum-path forest

Intrusion detection systems that make use of artificial intelligence techniques in order to improve effectiveness have been actively pursued in the last decade. Neural networks and Support Vector Machines have been also extensively applied to this task. However, their complexity to learn new attacks has become very expensive, making them inviable for a real time retraining. In this research, we introduce a new pattern classifier named Optimum-Path Forest (OPF) to this task, which has demonstrated to be similar to the state-of-the-art pattern recognition techniques, but extremely more efficient for training patterns. Experiments on public datasets showed that OPF classifier may be a suitable tool to detect intrusions on computer networks, as well as allow the algorithm to learn new attacks faster than the other techniques. © 2011 IEEE.

Diversity of social wasps on semideciduous seasonal forest fragments with different surrounding matrix in Brazil

We surveyed social wasps (Polistinae) present in forest fragments of northwest of So Paulo state with different surroundings composed of a matrix of citrus crops and sugarcane in the expectation that the former matrix would be more diverse than the latter. We collected specimens actively using attractive liquids. We obtained 20 species in Magda, 13 in Bebedouro, 13 in Mato, and 19 in Barretos. The most common genus was Agelaia in all of the areas. The greatest Shannon-Wiener index of diversity was obtained in Magda (H' = 2.12). Species such as Brachygastra moebiana, Metapolybia docilis, Mischocyttarus ignotus, M. paulistanus and M. consimilis had not been recorded on recent surveys in the state. Furthermore M. consimilis is a new record for the state. We concluded that, with our data, a relation between the occurrence of social wasps and the surrounding matrix was not detected. © 2011 Getulio Minoru Tanaka Junior and Fernando Barbosa Noll.

New trends in musical genre classification using optimum-path forest

Musical genre classification has been paramount in the last years, mainly in large multimedia datasets, in which new songs and genres can be added at every moment by anyone. In this context, we have seen the growing of musical recommendation systems, which can improve the benefits for several applications, such as social networks and collective musical libraries. In this work, we have introduced a recent machine learning technique named Optimum-Path Forest (OPF) for musical genre classification, which has been demonstrated to be similar to the state-of-the-art pattern recognition techniques, but much faster for some applications. Experiments in two public datasets were conducted against Support Vector Machines and a Bayesian classifier to show the validity of our work. In addition, we have executed an experiment using very recent hybrid feature selection techniques based on OPF to speed up feature extraction process. © 2011 International Society for Music Information Retrieval.

Automatic classification of fish germ cells through optimum-path forest

The spermatogenesis is crucial to the species reproduction, and its monitoring may shed light over some important information of such process. Thus, the germ cells quantification can provide useful tools to improve the reproduction cycle. In this paper, we present the first work that address this problem in fishes with machine learning techniques. We show here how to obtain high recognition accuracies in order to identify fish germ cells with several state-of-the-art supervised pattern recognition techniques. © 2011 IEEE.

Fast robot voice interface through optimum-path forest

Voice-based user interfaces have been actively pursued aiming to help individuals with motor impairments, providing natural interfaces to communicate with machines. In this work, we have introduced a recent machine learning technique named Optimum-Path Forest (OPF) for voice-based robot interface, which has been demonstrated to be similar to the state-of-the-art pattern recognition techniques, but much faster. Experiments were conducted against Support Vector Machines, Neural Networks and a Bayesian classifier to show the OPF robustness. The proposed architecture provides high accuracy rates allied with low computational times. © 2012 IEEE.

Automatic visual dictionary generation through Optimum-Path Forest clustering

Image categorization by means of bag of visual words has received increasing attention by the image processing and vision communities in the last years. In these approaches, each image is represented by invariant points of interest which are mapped to a Hilbert Space representing a visual dictionary which aims at comprising the most discriminative features in a set of images. Notwithstanding, the main problem of such approaches is to find a compact and representative dictionary. Finding such representative dictionary automatically with no user intervention is an even more difficult task. In this paper, we propose a method to automatically find such dictionary by employing a recent developed graph-based clustering algorithm called Optimum-Path Forest, which does not make any assumption about the visual dictionary's size and is more efficient and effective than the state-of-the-art techniques used for dictionary generation. © 2012 IEEE.

Automatic landslide recognition through Optimum-Path Forest

In this paper we shed light over the problem of landslide automatic recognition using supervised classification, and we also introduced the OPF classifier in this context. We employed two images acquired from Geoeye-MS satellite at March-2010 in the northwest (high steep areas) and north sides (pipeline area) covering the area of Duque de Caxias city, Rio de Janeiro State, Brazil. The landslide recognition rate has been assessed through a cross-validation with 10 runnings. In regard to the classifiers, we have used OPF against SVM with Radial Basis Function for kernel mapping and a Bayesian classifier. We can conclude that OPF, Bayes and SVM achieved high recognition rates, being OPF the fastest approach. © 2012 IEEE.

Intrusion detection in computer networks using optimum-path forest clustering

Nowadays, organizations face the problem of keeping their information protected, available and trustworthy. In this context, machine learning techniques have also been extensively applied to this task. Since manual labeling is very expensive, several works attempt to handle intrusion detection with traditional clustering algorithms. In this paper, we introduce a new pattern recognition technique called Optimum-Path Forest (OPF) clustering to this task. Experiments on three public datasets have showed that OPF classifier may be a suitable tool to detect intrusions on computer networks, since it outperformed some state-of-the-art unsupervised techniques. © 2012 IEEE.

Water availability determines the richness and density of fig trees within Brazilian semideciduous forest landscapes

The success of fig trees in tropical ecosystems is evidenced by the great diversity (+750 species) and wide geographic distribution of the genus. We assessed the contribution of environmental variables on the species richness and density of fig trees in fragments of seasonal semideciduous forest (SSF) in Brazil. We assessed 20 forest fragments in three regions in Sao Paulo State, Brazil. Fig tree richness and density was estimated in rectangular plots, comprising 31.4 ha sampled. Both richness and fig tree density were linearly modeled as function of variables representing (1) fragment metrics, (2) forest structure, and (3) landscape metrics expressing water drainage in the fragments. Model selection was performed by comparing the AIC values (Akaike Information Criterion) and the relative weight of each model (wAIC). Both species richness and fig tree density were better explained by the water availability in the fragment (meter of streams/ha): wAICrichness = 0.45, wAICdensity = 0.96. The remaining variables related to anthropic perturbation and forest structure were of little weight in the models. The rainfall seasonality in SSF seems to select for both establishment strategies and morphological adaptations in the hemiepiphytic fig tree species. In the studied SSF, hemiepiphytes established at lower heights in their host trees than reported for fig trees in evergreen rainforests. Some hemiepiphytic fig species evolved superficial roots extending up to 100 m from their trunks, resulting in hectare-scale root zones that allow them to efficiently forage water and soil nutrients. The community of fig trees was robust to variation in forest structure and conservation level of SSF fragments, making this group of plants an important element for the functioning of seasonal tropical forests. © 2013 Elsevier Masson SAS. All rights reserved.

Edge-interior differences in the species richness and abundance of drosophilids in a semideciduous forest fragment

Habitat fragmentation is the main cause of biodiversity loss, as remnant fragments are exposed to negative influences that include edge effects, prevention of migration, declines in effective population sizes, loss of genetic variability and invasion of exotic species. The Drosophilidae (Diptera), especially species of the genus Drosophila, which are highly sensitive to environmental variation, have been used as bioindicators. A twelve-month field study was conducted to evaluate the abundance and richness of drosophilids in an edge-interior transect in a fragment of semideciduous forest in São Paulo State, Brazil. One objective of the study was to evaluate the applied methodology with respect to its potential use in future studies addressing the monitoring and conservation of threatened areas. The species abundance along the transect showed a clear gradient, with species associated with disturbed environments, such as Drosophila simulans, Scaptodrosophila latifasciaeformis and Zaprionus indianus, being collected at the fragment edge and the species D. willistoni and D. mediostriata being found in the fragment's interior. Replacement of these species occurred at approximately 60 meters from the edge, which may be a reflection of edge effects on species abundance and richness because the species found within the habitat fragment are more sensitive to variations in temperature and humidity than those sampled near the edge. The results support the use of this methodology in studies on environmental impacts. © 2013 Penariol and Madi-Ravazzi; licensee Springer.

Soil erodibility assessment in a pasture and forest remnant using the inderbitzen device

Brazil has the largest cattle herd in the world with approximately 200 million head. An important feature of the Brazilian cattle industry is that most of its herd is raised on pasture, which constitutes one of the most economical and practical ways to produce and provide food for cattle. However, this production model is mishandled and can lead to soil degradation. Maintaining soil quality is essential for the conservation of natural ecosystems and the areas of production, thus soil quality improves the conditions for biogeochemical cycles. In this context, the objective of this study was to develop a device for testing the Inderbitzen way of assessing soil erodibility in two situations of usage and occupation. Therefore, one area was used as a sample collection occupied by grazing and the other as a forest fragment; both located in the city of Sorocaba in Sao Paulo State, Brazil. Thus, we concluded that the proposed device - the Inderbitzen - proved capable of assessing soil erodibility of the pasture and remnant forest. Accordingly, there was a tendency for a smaller loss of forest soils in the remnant when compared to the degraded pasture. The greatest resistance of the soil erosion in the forest remnant may be associated with the amount of organic matter released by the forest litter in all its diversity, influencing the quality of the structure of aggregates. © 2013 WIT Press.

Mite (Acari; Arachnida) diversity of two native plants in fragments of a semideciduous seasonal forest in Brazil

Studies to determine mite species richness in natural environments are still scarce, and have been conducted mainly in tropical ecosystems. The aim of this study was to determine the species richness of mites on two common native plants in fragments of the semideciduous seasonal forest in the Northwest of São Paulo State, Brazil. In each of eight fragments, 10 specimens of Actinostemon communis (Euphorbiaceae) and 10 of Trichilia casaretti (Meliaceae) were selected and marked. In total, 124 species of mites belonging to 21 families were found on the two plants. Tarsonemidae had the highest diversity (34 species), followed by Phytoseiidae (31), Tetranychidae (9) and Tenuipalpidae (8). Species accumulation curves for the two sampled plants did not reach an asymptote, even with the large sampling effort. Hence, it is estimated that a greater sampling effort may lead to an increase in species richness compared with what was found in this study. The richness of this mite fauna suggests that preservation of these plant species is important to maintain the mite diversity in these forest fragments. © 2013 Taylor & Francis Group, LLC.

Selecting for rust (Puccinia psidii) resistance in Eucalyptus grandis in São Paulo State, Brazil

In Brazil, Eucalyptus grandis is a key species for wood production. However, some genotypes are susceptible to rust (Puccinia psidii), mainly in São Paulo State, where climatic conditions are favorable for its development. Rust represents a high economic risk to forest companies because of the high potential of damage to commercial eucalypt plantations. The aims of the present study were (i) to select progenies of E. grandis for stability and adaptability regarding resistance to rust at different locations; (ii) compare the selections under these different climatic conditions; and (iii) compare rust severity in the field with the theoretical model. We observed that climatic conditions were extremely influential factors for rust development, but even under favorable conditions for disease development, we found rust-resistant progenies. In sites unfavorable for rust development, we detected highly susceptible progenies. We found significant correlation among the genetic material, environmental conditions and disease symptoms, however, we observed a simple genotype-environmental interaction and significant genetic variability among the progenies. The average heritability was high among the progenies in all sites, indicating substantial genetic control for rust resistance. We also observed a good relationship between rust severity in the field and the theoretical model that considered annual average temperature and leaf wetness. © 2013 Elsevier B.V.