Particle Competition and Cooperation in Networks for Semi-Supervised Learning

Semi-supervised learning is one of the important topics in machine learning, concerning with pattern classification where only a small subset of data is labeled. In this paper, a new network-based (or graph-based) semi-supervised classification model is proposed. It employs a combined random-greedy walk of particles, with competition and cooperation mechanisms, to propagate class labels to the whole network. Due to the competition mechanism, the proposed model has a local label spreading fashion, i.e., each particle only visits a portion of nodes potentially belonging to it, while it is not allowed to visit those nodes definitely occupied by particles of other classes. In this way, a "divide-and-conquer" effect is naturally embedded in the model. As a result, the proposed model can achieve a good classification rate while exhibiting low computational complexity order in comparison to other network-based semi-supervised algorithms. Computer simulations carried out for synthetic and real-world data sets provide a numeric quantification of the performance of the method.

A semi-supervised classification technique based on interacting forces

Semi-supervised learning is a classification paradigm in which just a few labeled instances are available for the training process. To overcome this small amount of initial label information, the information provided by the unlabeled instances is also considered. In this paper, we propose a nature-inspired semi-supervised learning technique based on attraction forces. Instances are represented as points in a k-dimensional space, and the movement of data points is modeled as a dynamical system. As the system runs, data items with the same label cooperate with each other, and data items with different labels compete among them to attract unlabeled points by applying a specific force function. In this way, all unlabeled data items can be classified when the system reaches its stable state. Stability analysis for the proposed dynamical system is performed and some heuristics are proposed for parameter setting. Simulation results show that the proposed technique achieves good classification results on artificial data sets and is comparable to well-known semi-supervised techniques using benchmark data sets.

VEGETATIVE PROPAGATION OF ANGICO-VERMELHO Anadenanthera macrocarpa (Benth) Brenan) HALF-SIBS BY MINI-CUTTINGS

The objective of this work is to evaluate the efficiency of the mini-cuttings technique in the vegetative propagation of half-sibs of angico-vermelho (Anadenanthera macrocarpa(Benth) Brenan) regarding to the productive capacity and survival of mini-stumps, rooting of the apical and intermediate mini-cuttings treated with different doses of IBA (0, 2000, 4000 and 6000 mg L-1) as well as to determine the speed of rooting in the greenhouse. The mini-stumps were obtained from seedlings of the six progenies of Anadenanthera macrocarpa half-sibs. The mini-stumps presented productivity from 1,2 to 3,7 mini-cuttings/mini-stump/collection and survival of 84% to 98% after six harvests. The apical mini-cuttings were higher than the intermediate, more prone to root, but the IBA had no significant effect on the rooting of the progenies. The results of the rooting speed showed variation among the progenies.

In vitro propagation of Sacha inchi

The aim of this study was to perform an in vitro evaluation of the auxin: cytokinine ratio in different segments of the epicotyl and hypocotyl of Sacha inchi (Plukenetia Volubilis Linneo) seeds germinated in vitro. The segments apical (A), median (B) and basal (C) were introduced into semi-solid MS culture medium (2.0g L-1 Phytagel), supplemented with MS vitamins, sucrose (30.0g L-1) and submitted to three doses of auxin indolebutyric acid - IBA (0; 0.1; 0.5mg L-1), associated with four doses of the cytokinine benzylaminopurine - BAP (0; 0.1; 0.5; 1.0mg L-1), totaling 36 treatments. After nine weeks of in vitro cultivation, the apical segment ( A) presented shoot formation by direct organogenesis at the concentrations of 0.5 and 1.0 of BAP associated with 0.0 and 0.1 of IBA. It is feasible to use in vitro cultivation with the apical region of seeds germinated in vitro used as explants.

A novel XML document structure comparison framework based-on sub-tree commonalities and label semantics

XML similarity evaluation has become a central issue in the database and information communities, its applications ranging over document clustering, version control, data integration and ranked retrieval. Various algorithms for comparing hierarchically structured data, XML documents in particular, have been proposed in the literature. Most of them make use of techniques for finding the edit distance between tree structures, XML documents being commonly modeled as Ordered Labeled Trees. Yet, a thorough investigation of current approaches led us to identify several similarity aspects, i.e., sub-tree related structural and semantic similarities, which are not sufficiently addressed while comparing XML documents. In this paper, we provide an integrated and fine-grained comparison framework to deal with both structural and semantic similarities in XML documents (detecting the occurrences and repetitions of structurally and semantically similar sub-trees), and to allow the end-user to adjust the comparison process according to her requirements. Our framework consists of four main modules for (i) discovering the structural commonalities between sub-trees, (ii) identifying sub-tree semantic resemblances, (iii) computing tree-based edit operations costs, and (iv) computing tree edit distance. Experimental results demonstrate higher comparison accuracy with respect to alternative methods, while timing experiments reflect the impact of semantic similarity on overall system performance.

Metronidazole Immediate Release Formulations: A Fasting Randomized Open-Label Crossover Bioequivalence Study in Healthy Volunteers

Metronidazole is a BCS (Biopharmaceutics Classification System) class 1 drug, traditionally considered the choice drug in the infections treatment caused by protozoa and anaerobic microorganisms. This study aimed to evaluate bioequivalence between 2 different marketed 250 mg metronidazole immediate release tablets. A randomized, open-label, 2 x 2 crossover study was performed in healthy Brazilian volunteers under fasting conditions with a 7-day washout period. The formulations were administered as single oral dose and blood was sampled over 48 h. Metronidazole plasma concentrations were determined by a liquid chromatography mass spectrometry (LC-MS/MS) method. The plasma concentration vs. time profile was generated for each volunteer and the pharmacokinetic parameters C-max, T-max, AUC(0-t), AUC(0-infinity), k(e), and t(1/2) were calculated using a noncompartmental model. Bioequivalence between pharmaceutical formulations was determined by calculating 90% CIs (Confidence Intervall) for the ratios of C-max, AUC(0-t), and AUC(0-infinity) values for test and reference using log-transformed data. 22 healthy volunteers (11 men, 11 women; mean (SD) age, 28 (6.5) years [range, 21-45 years]; mean (SD) weight, 66 (9.3) kg [range, 51-81 kg]; mean (SD) height, 169 (6.5) cm [range, 156-186 cm]) were enrolled in and completed the study. The 90% CIs for C-max (0.92-1.06), AUC(0-t) (0.97-1.02), and AUC(0-infinity) (0.97-1.03) values for the test and reference products fitted in the interval of 0.80-1.25 proposed by most regulatory agencies, including the Brazilian agency ANVISA. No clinically significant adverse effects were reported. After pharmacokinetics analysis, it concluded that test 250 mg metronidazole formulation is bioequivalent to the reference product according to the Brazilian agency requirements.

Signal propagation in Bayesian networks and its relationship with intrinsically multivariate predictive variables

A set of predictor variables is said to be intrinsically multivariate predictive (IMP) for a target variable if all properly contained subsets of the predictor set are poor predictors of the. target but the full set predicts the target with great accuracy. In a previous article, the main properties of IMP Boolean variables have been analytically described, including the introduction of the IMP score, a metric based on the coefficient of determination (CoD) as a measure of predictiveness with respect to the target variable. It was shown that the IMP score depends on four main properties: logic of connection, predictive power, covariance between predictors and marginal predictor probabilities (biases). This paper extends that work to a broader context, in an attempt to characterize properties of discrete Bayesian networks that contribute to the presence of variables (network nodes) with high IMP scores. We have found that there is a relationship between the IMP score of a node and its territory size, i.e., its position along a pathway with one source: nodes far from the source display larger IMP scores than those closer to the source, and longer pathways display larger maximum IMP scores. This appears to be a consequence of the fact that nodes with small territory have larger probability of having highly covariate predictors, which leads to smaller IMP scores. In addition, a larger number of XOR and NXOR predictive logic relationships has positive influence over the maximum IMP score found in the pathway. This work presents analytical results based on a simple structure network and an analysis involving random networks constructed by computational simulations. Finally, results from a real Bayesian network application are provided. (C) 2012 Elsevier Inc. All rights reserved.

Signal Transceiver Transit Times and Propagation Delay Corrections for Ranging and Georeferencing Applications

The accuracy of ranging measurements depends critically on the knowledge of time delays undergone by signals when retransmitted by a remote transponder and due to propagation effects. A new method determines these delays for every single pulsed signal transmission. It utilizes four ground-based reference stations, synchronized in time and installed at well-known geodesic coordinates and a repeater in space, carried by a satellite, balloon, aircraft, and so forth. Signal transmitted by one of the reference bases is retransmitted by the transponder, received back by the four bases, producing four ranging measurements which are processed to determine uniquely the time delays undergone in every retransmission process. A minimization function is derived comparing repeater's positions referred to at least two groups of three reference bases, providing the signal transit time at the repeater and propagation delays, providing the correct repeater position. The method is applicable to the transponder platform positioning and navigation, time synchronization of remote clocks, and location of targets. The algorithm has been demonstrated by simulations adopting a practical example with the transponder carried by an aircraft moving over bases on the ground.

Incorporating label dependency into the binary relevance framework for multi-label classification

In multi-label classification, examples can be associated with multiple labels simultaneously. The task of learning from multi-label data can be addressed by methods that transform the multi-label classification problem into several single-label classification problems. The binary relevance approach is one of these methods, where the multi-label learning task is decomposed into several independent binary classification problems, one for each label in the set of labels, and the final labels for each example are determined by aggregating the predictions from all binary classifiers. However, this approach fails to consider any dependency among the labels. Aiming to accurately predict label combinations, in this paper we propose a simple approach that enables the binary classifiers to discover existing label dependency by themselves. An experimental study using decision trees, a kernel method as well as Naive Bayes as base-learning techniques shows the potential of the proposed approach to improve the multi-label classification performance.

Hierarchical multi-label classification using local neural networks

Hierarchical multi-label classification is a complex classification task where the classes involved in the problem are hierarchically structured and each example may simultaneously belong to more than one class in each hierarchical level. In this paper, we extend our previous works, where we investigated a new local-based classification method that incrementally trains a multi-layer perceptron for each level of the classification hierarchy. Predictions made by a neural network in a given level are used as inputs to the neural network responsible for the prediction in the next level. We compare the proposed method with one state-of-the-art decision-tree induction method and two decision-tree induction methods, using several hierarchical multi-label classification datasets. We perform a thorough experimental analysis, showing that our method obtains competitive results to a robust global method regarding both precision and recall evaluation measures.