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.

Detecting an abnormality in a recovery boiler using dynamic multivariate data analysis with parallel coordinate plots

Data visualization techniques are powerful in the handling and analysis of multivariate systems. One such technique known as parallel coordinates was used to support the diagnosis of an event, detected by a neural network-based monitoring system, in a boiler at a Brazilian Kraft pulp mill. Its attractiveness is the possibility of the visualization of several variables simultaneously. The diagnostic procedure was carried out step-by-step going through exploratory, explanatory, confirmatory, and communicative goals. This tool allowed the visualization of the boiler dynamics in an easier way, compared to commonly used univariate trend plots. In addition it facilitated analysis of other aspects, namely relationships among process variables, distinct modes of operation and discrepant data. The whole analysis revealed firstly that the period involving the detected event was associated with a transition between two distinct normal modes of operation, and secondly the presence of unusual changes in process variables at this time.

GPR applied to mapping utilities along the route of the Line 4 (yellow) subway tunnel construction in Sao Paulo City, Brazil

The rapid industrial development and disorganized population growth in huge cities bring about various urban problems due to intense use of physical space on and below the surface. Subsurface problems in metropolitan areas are caused by subway line construction, which often follows the routes of utility networks, such as electric and telephone cables, water and gas pipes, storm sewers, etc. Usually, the main problems are related to damage or destruction of preexisting utilities, often putting human lives at risk. With the purpose of minimizing risks. GPR-profiling with 200 MHz antennae was done at two sites, both located in downtown Sao Paulo, Brazil. The objectives of this work were to map utilities or existing infrastructure in the subsurface in order to orient the construction of the Line 4 (yellow) subway tunnel in Sao Paulo. GPR profiles can detect water pipes, utility networks in the subsurface, and concrete foundation columns or pilings in subsoil up to 2 m depth. In addition. the GPR profiles also provided details of the target shapes in the subsurface. GPR interpretations combined with lithological information from boreholes and trenches opened in the study areas were extremely important in mapping of the correct spatial distribution of buried utilities at these two sites in Sao Paulo. This information improves and updates maps of utility placement, serves as a basis for planning of the geotechnical excavation of the Line 4 (yellow) subway tunnel in Sao Paulo, helps minimize problems related to destruction of preexisting utilities in the subsoil, and avoids risk of dangerous accidents. (C) 2012 Elsevier B.V. All rights reserved.

Collective Almost Synchronisation in Complex Networks

This work introduces the phenomenon of Collective Almost Synchronisation (CAS), which describes a universal way of how patterns can appear in complex networks for small coupling strengths. The CAS phenomenon appears due to the existence of an approximately constant local mean field and is characterised by having nodes with trajectories evolving around periodic stable orbits. Common notion based on statistical knowledge would lead one to interpret the appearance of a local constant mean field as a consequence of the fact that the behaviour of each node is not correlated to the behaviours of the others. Contrary to this common notion, we show that various well known weaker forms of synchronisation (almost, time-lag, phase synchronisation, and generalised synchronisation) appear as a result of the onset of an almost constant local mean field. If the memory is formed in a brain by minimising the coupling strength among neurons and maximising the number of possible patterns, then the CAS phenomenon is a plausible explanation for it.

Semi-supervised learning guided by the modularity measure in complex networks

Semi-supervised learning techniques have gained increasing attention in the machine learning community, as a result of two main factors: (1) the available data is exponentially increasing; (2) the task of data labeling is cumbersome and expensive, involving human experts in the process. In this paper, we propose a network-based semi-supervised learning method inspired by the modularity greedy algorithm, which was originally applied for unsupervised learning. Changes have been made in the process of modularity maximization in a way to adapt the model to propagate labels throughout the network. Furthermore, a network reduction technique is introduced, as well as an extensive analysis of its impact on the network. Computer simulations are performed for artificial and real-world databases, providing a numerical quantitative basis for the performance of the proposed method.

Genetic and environmental risk factors in congenital heart disease functionally converge in protein networks driving heart development

Congenital heart disease (CHD) occurs in similar to 1% of newborns. CHD arises from many distinct etiologies, ranging from genetic or genomic variation to exposure to teratogens, which elicit diverse cell and molecular responses during cardiac development. To systematically explore the relationships between CHD risk factors and responses, we compiled and integrated comprehensive datasets from studies of CHD in humans and model organisms. We examined two alternative models of potential functional relationships between genes in these datasets: direct convergence, in which CHD risk factors significantly and directly impact the same genes and molecules and functional convergence, in which risk factors significantly impact different molecules that participate in a discrete heart development network. We observed no evidence for direct convergence. In contrast, we show that CHD risk factors functionally converge in protein networks driving the development of specific anatomical structures (e.g., outflow tract, ventricular septum, and atrial septum) that are malformed by CHD. This integrative analysis of CHD risk factors and responses suggests a complex pattern of functional interactions between genomic variation and environmental exposures that modulate critical biological systems during heart development.

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.

Elemental composition evaluation in lichens collected in the industrial city of So Mateus Sul, Parana, Brazil

In this study, Canoparmelia texana lichenized fungi species was used as a passive biomonitor of the atmospheric pollution from the industrial city of So Mateus do Sul, PR, Brazil. Lichen samples collected from tree barks were cleaned, freeze-dried and analyzed by neutron activation analysis. Comparisons were made between the element concentrations obtained in lichens from this city and that from a clean area of Atlantic Forest in Intervales Park, SP. The high concentrations of elements As, Ca, Co, Cr, Fe, Hf, Sb, and Th found in lichens could be attributed to the emissions from a ceramic and an oil shale plants.

Analysis of the interplay between knowledge and performance management in industrial clusters

The concept of industrial clustering has been studied in-depth by policy makers and researchers from many fields, mainly due to the competitive advantages it may bring to regional economies. Companies often take part in collaborative initiatives with local partners while also taking advantage of knowledge spillovers to benefit from locating in a cluster. Thus, Knowledge Management (KM) and Performance Management (PM) have become relevant topics for policy makers and cluster associations when undertaking collaborative initiatives. Taking this into account, this paper aims to explore the interplay between both topics using a case study conducted in a collaborative network formed within a cluster. The results show that KM should be acknowledged as a formal area of cluster management so that PM practices can support knowledge-oriented initiatives and therefore make better use of the new knowledge created. Furthermore, tacit and explicit knowledge resulting from PM practices needs to be stored and disseminated throughout the cluster as a way of improving managerial practices and regional strategic direction. Knowledge Management Research & Practice (2012) 10, 368-379. doi:10.1057/kmrp.2012.23

Stochastic competitive learning in complex networks

Competitive learning is an important machine learning approach which is widely employed in artificial neural networks. In this paper, we present a rigorous definition of a new type of competitive learning scheme realized on large-scale networks. The model consists of several particles walking within the network and competing with each other to occupy as many nodes as possible, while attempting to reject intruder particles. The particle's walking rule is composed of a stochastic combination of random and preferential movements. The model has been applied to solve community detection and data clustering problems. Computer simulations reveal that the proposed technique presents high precision of community and cluster detections, as well as low computational complexity. Moreover, we have developed an efficient method for estimating the most likely number of clusters by using an evaluator index that monitors the information generated by the competition process itself. We hope this paper will provide an alternative way to the study of competitive learning.

PERFORMANCE EVALUATION OF RESOURCE-AWARE BUSINESS PROCESSES USING STOCHASTIC AUTOMATA NETWORKS

In this work, we study the performance evaluation of resource-aware business process models. We define a new framework that allows the generation of analytical models for performance evaluation from business process models annotated with resource management information. This framework is composed of a new notation that allows the specification of resource management constraints and a method to convert a business process specification and its resource constraints into Stochastic Automata Networks (SANs). We show that the analysis of the generated SAN model provides several performance indices, such as average throughput of the system, average waiting time, average queues size, and utilization rate of resources. Using the BP2SAN tool - our implementation of the proposed framework - and a SAN solver (such as the PEPS tool) we show through a simple use-case how a business specialist with no skills in stochastic modeling can easily obtain performance indices that, in turn, can help to identify bottlenecks on the model, to perform workload characterization, to define the provisioning of resources, and to study other performance related aspects of the business process.

Texture descriptor based on partially self-avoiding deterministic walker on networks

Texture image analysis is an important field of investigation that has attracted the attention from computer vision community in the last decades. In this paper, a novel approach for texture image analysis is proposed by using a combination of graph theory and partially self-avoiding deterministic walks. From the image, we build a regular graph where each vertex represents a pixel and it is connected to neighboring pixels (pixels whose spatial distance is less than a given radius). Transformations on the regular graph are applied to emphasize different image features. To characterize the transformed graphs, partially self-avoiding deterministic walks are performed to compose the feature vector. Experimental results on three databases indicate that the proposed method significantly improves correct classification rate compared to the state-of-the-art, e.g. from 89.37% (original tourist walk) to 94.32% on the Brodatz database, from 84.86% (Gabor filter) to 85.07% on the Vistex database and from 92.60% (original tourist walk) to 98.00% on the plant leaves database. In view of these results, it is expected that this method could provide good results in other applications such as texture synthesis and texture segmentation. (C) 2012 Elsevier Ltd. All rights reserved.

Synthetic biology: a novel approach for the construction of industrial microorganisms

The recent achievement of synthesising a functioning bacterial chromosome marks a coming of age for engineering living organisms. In the future this should allow the construction of novel organisms to help solve the problems facing the human race, including health care, food, energy and environmental protection. In this minireview, the current state of the field is described and the role of synthetic biology in biotechnology in the short and medium term is discussed. It is particularly aimed at the needs of food technologists, nutritionists and other biotechnologists, who might not be aware of the potential significance of synthetic biology to the research and development in their fields. The potential of synthetic biology to produce interesting new polyketide compounds is discussed in detail.