Harmony Search applied for Support Vector Machines Training Optimization

Since the beginning, some pattern recognition techniques have faced the problem of high computational burden for dataset learning. Among the most widely used techniques, we may highlight Support Vector Machines (SVM), which have obtained very promising results for data classification. However, this classifier requires an expensive training phase, which is dominated by a parameter optimization that aims to make SVM less prone to errors over the training set. In this paper, we model the problem of finding such parameters as a metaheuristic-based optimization task, which is performed through Harmony Search (HS) and some of its variants. The experimental results have showen the robustness of HS-based approaches for such task in comparison against with an exhaustive (grid) search, and also a Particle Swarm Optimization-based implementation.

Ethanol production by Zymomonas mobilis during sucrose fermentation: Optimization of culture conditions using factorial design

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

A transmission power self-optimization technique for wireless sensor networks

Wireless sensor networks (WSNs) are generally used to monitor hazardous events in inaccessible areas. Thus, on one hand, it is preferable to assure the adoption of the minimum transmission power in order to extend as much as possible the WSNs lifetime. On the other hand, it is crucial to guarantee that the transmitted data is correctly received by the other nodes. Thus, trading off power optimization and reliability insurance has become one of the most important concerns when dealing with modern systems based on WSN. In this context, we present a transmission power self-optimization (TPSO) technique for WSNs. The TPSO technique consists of an algorithm able to guarantee the connectivity as well as an equally high quality of service (QoS), concentrating on the WSNs efficiency (Ef), while optimizing the transmission power necessary for data communication. Thus, the main idea behind the proposed approach is to trade off WSNs Ef against energy consumption in an environment with inherent noise. Experimental results with different types of noise and electromagnetic interference (EMI) have been explored in order to demonstrate the effectiveness of the TPSO technique.

Production of β-(1,3)-glucanases by Trichoderma harzianum Rifai: Optimization and Application to Produce Gluco-oligosaccharides from Paramylon and Pustulan

β-(1→3)-Glucanases were produced by Trichoderma harzianum Rifai PAMB-86 cultivated on botryosphaeran in a bench-fermenter and optimised by the response surface method. Maximal enzyme titres occurred at 5 days, initial pH 5.5 and aeration of 1.5vvm. β-(1→3)-The β-glucanolytic enzyme complex produced by T. harzianum Rifai PAMB- 86 was fractionated by gel filtration into 2 fractions (F-I, F-II), and employed to produce gluco-oligosaccharides from algal paramylon ((1→3)-β-D-glucan) and lichen pustulan ((1→6)-β-D-glucan). Both enzymes attacked paramylon to the extent of ~15-20% in 30 min releasing glucose and laminaribiose as major end-products, and laminarioligosaccharides of degree of polymerization (DP) ≥3. Only F-I degraded pustulan resulting in ~2% degradation at 30 min, with glucose, gentiobiose and gentio-oligosaccharides of DP ≥4 as major products. The difference in the nature of the hydrolysis products can be explained by the substrate specificities of each enzyme fraction, and the structural differences of the β-D-glucans attacked.

Sucrose utilization by Zymomonas mobilis: Levan production optimization using submerged fermentation

Levan is an extracellular polysaccharide (EPS), constituted by linked fructose units β (2,6), obtained by transfructosilation reaction during fermentation of microorganisms in a sucrose rich culture medium. The bacterial levan production is a good alternative of fructose source, besides having certain functional characteristics in the human body, such as a hypocholesterolemic and an anticarcinogenic agent. In the food industry, the levan can be used to fix colors and flavors, as well as to thickening and stabilizing agent in foods. This work aimed to analyze the kinetic parameters for levan production by Zymomonas mobilis CCT 4494, using submerged fermentation. The response surface methodology (RSM), was utilized to predict the optimization of medium for exopolymer production and the independent variables studied were: initial pH, incubation temperature, sucrose, KCl, K2SO4, MgSO4 and CaCl2. It was observed that the bacterium Z. mobilis CCT 4494 well adapted in medium containing high concentrations of sucrose.

Saddle Point and Second Order Optimality in Nondifferentiable Nonlinear Abstract Multiobjective Optimization

This article deals with a vector optimization problem with cone constraints in a Banach space setting. By making use of a real-valued Lagrangian and the concept of generalized subconvex-like functions, weakly efficient solutions are characterized through saddle point type conditions. The results, jointly with the notion of generalized Hessian (introduced in [Cominetti, R., Correa, R.: A generalized second-order derivative in nonsmooth optimization. SIAM J. Control Optim. 28, 789–809 (1990)]), are applied to achieve second order necessary and sufficient optimality conditions (without requiring twice differentiability for the objective and constraining functions) for the particular case when the functionals involved are defined on a general Banach space into finite dimensional ones.

Parameters optimization of heat treatment for obtaining luminescent PZT powders

Low crystalline PZT powder samples were successfully synthesized using polymeric precursor method and slow decomposition steps. The polymeric resin precursor was thermal treated in a muffle type oven varying the temperature from 250 °C to 700 °C and the time from 3 to 24 hours in order to investigate the order/disorder mechanism toward the amorphous powders. Powder samples with low crystalline phases were obtained at lower temperatures and long time of thermal treatment, demonstrating a kinetic dependence for organic removal and a thermodynamic barrier for crystallization processes. Through XRD and FTIR spectroscopy characterizations the long time thermal treated samples showed to be composed of the solid solution of metal oxides in absent of organic matter, originating broad XRD peaks profiles and no carbonaceous bands in FTIR spectra. A Photoluminescence characterization showed that the peak emission is higher for disordered and homogeneous phases, which only can be reached through the long time of thermal treatment.

Construction of pediatric homogeneous phantoms for optimization of chest and skull radiographs

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Electrochemical oxidation of landfill leachate in a flow reactor: optimization using response surface methodology

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Generalized interval vector spaces and interval optimization

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

On the properness of an impulsive control extension of dynamic optimization problems

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

On the Newton method for solving fuzzy optimization problems

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Developing an optimization tool for evaluating the transmission system expansion

The transmission system is responsible for connecting the power generators to consumers safely and reliably, its constant expansion is necessary to transport increasing amounts of electricity. In order to help the power systems engineers, an optimization tool for optimize the expansion of the transmission system was developed using the modeling method of the linearized load flow and genetic. This tool was designed to simulate the impact of different scenarios on the cost of transmission expansion. The proposed tool was used to simulate the effects of the presence of distributed generation in the expansion of a fictitious transmission system, where it was found a clear downward trend in investment required for the expansion of the transmission system taking account of increasing levels of distributed generation.

Volt-VAR multiobjective optimization to peak-load relief and energy efficiency in distribution networks

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)