A parallel evolutionary algorithm for technical market indicators optimization

This paper deals with the optimization of parameters of technical indicators for stock market investment. Price prediction is a problem of great complexity and, usually, some technical indicators are used to predict market trends. The main difficulty in using technical indicators lies in deciding a set of parameter values. We proposed the use of Multi-Objective Evolutionary Algorithms (MOEAs) to obtain the best parameter values belonging to a collection of indicators that will help in the buying and selling of shares. The experimental results indicate that our MOEA offers a solution to the problem by obtaining results that improve those obtained through technical indicators with standard parameters. In order to reduce execution time is necessary to parallelize the executions. Parallelization results show that distributing the workload of indicators in multiple processors to improve performance is recommended. This parallelization has been performed taking advantage of the idle time in a corporate technology infrastructure. We have configured a small parallel grid using the students Labs of a Computer Science University College.     

Dealing with hardware heterogeneity: a new parallel search model

In this article we present Ethane, a parallel heterogeneous metaheuristic model specifically designed for its execution on heterogeneous hardware environments. With Ethane we propose a hybrid parallel search algorithm inspired in the structure of the chemical compound of the same name, implementing a heterogeneous island model based in the structure of the chemical bonds of the ethane compound. Here we also shape a schema for describing a complete family of parallel heterogeneous metaheuristics inspired by the structure of hydrocarbons in nature, HydroCM (HydroCarbon inspired Metaheuristics), establishing a resemblance between atoms and computers, and between chemical bonds and communication links. Our goal is to gracefully match computers of different computing power to algorithms of different behavior (genetic algorithm and simulated annealing in this study), all them collaborating to solve the same problem. In addition to the nice natural metaphor we will show that Ethane, though simple, can solve search problems in a faster and more robust way than well-known panmictic and distributed algorithms very popular in the literature, as well as can achieve a better exploration/exploitation balance during the search process.     

Hinging hyperplane based regression tree identified by fuzzy clustering and its application

Hierarchical fuzzy modeling techniques have great advantage since model accuracy and complexity can be easily controlled thanks to the transparent model structures. A novel tool for regression tree identification is proposed based on the synergistic combination of fuzzy c-regression clustering and the concept of hierarchical modeling. In a special case (c = 2), fuzzy c-regression clustering can be used for identification of hinging hyperplane models. The proposed method recursively identifies a hinging hyperplane model that contains two linear submodels by partitioning operating region of one local linear model resulting a binary regression tree. Novel measures of model performance and complexity are developed to support the analysis and building of the proposed special model structure. Effectiveness of proposed model is demonstrated by benchmark regression datasets. Examples also demonstrate that the proposed model can effectively represent nonlinear dynamical systems. Thanks to the piecewise linear model structure the resulted regression tree can be easily utilized in model predictive control. A detailed application example related to the model predictive control of a water heater demonstrate that the proposed framework can be effectively used in modeling and control of dynamical systems.     

Incremental semantic analysis for OCL compilers

In software engineering, modeling with unified modeling language and object constraint language became industry standards and are supported by many computer-aided software engineering tools. The increasing number of the modeled functionalities results in complex models that need more and more textual constraints to express the hidden restrictions applied to the systems. During the metamodel development, rebuilding all the constraints is unnecessary when only a few changes have been applied due to the iterative, incremental manner of modifications. In this paper, we present a family of algorithms that handles the changes in constraints incrementally on the expression level; thus, the required rebuilds are kept to a minimum. Incremental variable reference resolving and type checking are performed as a part of the incremental semantic analysis. Balancing between the incremental and standard compilation is also considered, heuristics are given to select the faster method of compilation at each iteration. With the achieved results the duration of metamodel development can be decreased; thus, the efficiency of the environment is improved.     

Fix-and-Relax-Coordination for a multi-period location–allocation problem under uncertainty

A multi-period discrete facility location problem is introduced for a risk neutral strategy with uncertainty in the costs and some of the requirements along the planning horizon. A compact 0–1 formulation for the Deterministic Equivalent Model of the problem under two alternative strategies for the location decisions is presented. Furthermore, a new algorithmic matheuristic, Fix-and-Relax-Coordination, is introduced. This solution scheme is based on a specialization of the Branch-and-Fix Coordination methodology, which exploits the Nonanticipativity Constraints and uses the Twin Node Family concept. The results of an extensive computational experience allow to compare the alternative modeling strategies and assess the effectiveness of the proposed approach versus the plain use of a state-of-the-art MIP solver.     

SIMULATING STRUCTURAL CHANGE IN ADAPTIVE ORGANIZATIONS

This paper presents an agent-based model of an organization. The model is made of a social network—composed of the different organization workers—and a knowledge network. Workers are assigned tasks, for which they have to use information in the knowledge network. We have modeled the quality of the information by assigning each information item a probability of being wrong. Agents can interact with other agents, who can recommend to them new information items in the knowledge network for the task to be performed. Workers are assigned different information-seeking behavior (passive, active, and learning), governing the way in which they interact with each other. Moreover, indirect interaction is also possible, as a publicly accessible knowledge base contains each agent's preferred information items.

The model was implemented in SDML, and its simulation shows that agents quickly learn to discern the better information items for the given task. However, group formation (agents' collaborating by exchanging information) takes longer to stabilize. Additionally, when the quality of items is changed, agents can quickly select the better new knowledge items, and organization performance improves again to a maximum that is only randomly disturbed.     

Development of a Real Time PCR system for detection of ochratoxin A-producing strains of the Aspergillus niger aggregate

Members of Aspergillus section Nigri are distributed worldwide, being considered as common food spoilage fungi. Some species of this section produce ochratoxin A (OTA), mainly Aspergillus carbonarius and several members of the Aspergillus niger aggregate. Detection of ochratoxigenic A. niger aggregate strains is important to prevent OTA contamination in foodstuffs. A new Real Time PCR procedure has been developed for the rapid and specific detection and quantification of ochratoxin A-producing strains of the A. niger aggregate. Two specific primers delimiting a 120 bp fragment and a probe were designed and directed to a polyketide synthase (PKS) from A. niger CBS 513.88 genome. This PKS has a strong similarity to PKS of A. ochraceus fragment involved in ochratoxin biosynthesis. Specificity was confirmed by testing primers towards purified DNA from 91 fungal strains, including reference and food isolates. The SYBR-Green and the TaqMan approaches developed allowed the specific detection only of ochratoxigenic strains of the A. niger aggregate. All other analyzed food related fungi gave negative results. This is the first report on a Real Time PCR system for the detection of OTA-producing strains of the A. niger aggregate.     

Determination of water content in Brazilian honeybee-collected pollen by Karl Fischer titration

This paper assesses the performance of a chemical method based on the Karl Fischer titration to determine the water content in samples of dehydrated honeybee-collected pollen. The following analysis parameters were investigated: extraction temperature, particle size, reaction time, and weight of a dried pollen sample. After optimization, the method was used to determine the water content of 154 samples of dried honeybee-collected pollen from different geographical regions of Brazil. The Karl Fischer titration method, performed using a solvent mixture of methanol and n-octanol (1:1 v/v) at 50 °C on pollen particles 600 μm in size produced the best results. Mean values for water content of the 154 samples of dried honeybee-collected pollen from 12 Brazilian regions ranged from 3% to 9%.