Hybrid Water Demand Forecasting Model Associating Artificial Neural Network with Fourier Series

This paper addressed the problem of water-demand forecasting for real-time operation of water supply systems. The present study was conducted to identify the best fit model using hourly consumption data from the water supply system of Araraquara, Sa approximate to o Paulo, Brazil. Artificial neural networks (ANNs) were used in view of their enhanced capability to match or even improve on the regression model forecasts. The ANNs used were the multilayer perceptron with the back-propagation algorithm (MLP-BP), the dynamic neural network (DAN2), and two hybrid ANNs. The hybrid models used the error produced by the Fourier series forecasting as input to the MLP-BP and DAN2, called ANN-H and DAN2-H, respectively. The tested inputs for the neural network were selected literature and correlation analysis. The results from the hybrid models were promising, DAN2 performing better than the tested MLP-BP models. DAN2-H, identified as the best model, produced a mean absolute error (MAE) of 3.3 L/s and 2.8 L/s for training and test set, respectively, for the prediction of the next hour, which represented about 12% of the average consumption. The best forecasting model for the next 24 hours was again DAN2-H, which outperformed other compared models, and produced a MAE of 3.1 L/s and 3.0 L/s for training and test set respectively, which represented about 12% of average consumption. DOI: 10.1061/(ASCE)WR.1943-5452.0000177. (C) 2012 American Society of Civil Engineers.

Combining meta-learning and search techniques to select parameters for support vector machines

Support Vector Machines (SVMs) have achieved very good performance on different learning problems. However, the success of SVMs depends on the adequate choice of the values of a number of parameters (e.g., the kernel and regularization parameters). In the current work, we propose the combination of meta-learning and search algorithms to deal with the problem of SVM parameter selection. In this combination, given a new problem to be solved, meta-learning is employed to recommend SVM parameter values based on parameter configurations that have been successfully adopted in previous similar problems. The parameter values returned by meta-learning are then used as initial search points by a search technique, which will further explore the parameter space. In this proposal, we envisioned that the initial solutions provided by meta-learning are located in good regions of the search space (i.e. they are closer to optimum solutions). Hence, the search algorithm would need to evaluate a lower number of candidate solutions when looking for an adequate solution. In this work, we investigate the combination of meta-learning with two search algorithms: Particle Swarm Optimization and Tabu Search. The implemented hybrid algorithms were used to select the values of two SVM parameters in the regression domain. These combinations were compared with the use of the search algorithms without meta-learning. The experimental results on a set of 40 regression problems showed that, on average, the proposed hybrid methods obtained lower error rates when compared to their components applied in isolation.

Comparative clinical study of the effectiveness of different dental bleaching methods - two year follow-up

This study evaluated color change, stability, and tooth sensitivity in patients submitted to different bleaching techniques. Material and methods: In this study, 48 patients were divided into five groups. A half-mouth design was conducted to compare two in-office bleaching bleaching techniques (with and without light activation): G1: 35% hydrogen peroxide (HP) (Lase Peroxide - DMC Equipments, Sao Carlos, SP, Brazil) + hybrid light (HL) (LED/Diode Laser, Whitening Lase II DMC Equipments, Sao Carlos, SP, Brazil); G2: 35% HP; G3: 38% HP (X-traBoost - Ultradent, South Jordan UT, USA) + HL; G4: 38% HP; and G5: 15% carbamide peroxide (CP) (Opalescence PF - Ultradent, South Jordan UT, USA). For G1 and G3, HP was applied on the enamel surface for 3 consecutive applications activated by HL. Each application included 3x3' HL activations with 1' between each interval; for G2 and G4, HP was applied 3x15' with 15' between intervals; and for G5, 15% CP was applied for 120'/10 days at home. A spectrophotometer was used to measure color change before the treatment and after 24 h, 1 week, 1, 6, 12, 18 and 24 months. A VAS questionnaire was used to evaluate tooth sensitivity before the treatment, immediately following treatment, 24 h after and finally 1 week after. Results: Statistical analysis did not reveal any significant differences between in-office bleaching with or without HL activation related to effectiveness; nevertheless the time required was less with HL. Statistical differences were observed between the result after 24 h, 1 week and 1, 6, 12, 18 and 24 months (integroup). Immediately, in-office bleaching increased tooth sensitivity. The groups activated with HL required less application time with gel. Conclusion: All techniques and bleaching agents used were effective and demonstrated similar behaviors.

Hybrid density functional study of small Rh-n (n=2-15) clusters

The physical properties of small rhodium clusters, Rh-n, have been in debate due to the shortcomings of density functional theory (DFT). To help in the solution of those problems, we obtained a set of putative lowest energy structures for small Rh-n (n = 2-15) clusters employing hybrid-DFT and the generalized gradient approximation (GGA). For n = 2-6, both hybrid and GGA functionals yield similar ground-state structures (compact), however, hybrid favors compact structures for n = 7-15, while GGA favors open structures based on simple cubic motifs. Thus, experimental results are crucial to indicate the correct ground-state structures, however, we found that a unique set of structures (compact or open) is unable to explain all available experimental data. For example, the GGA structures (open) yield total magnetic moments in excellent agreement with experimental data, while hybrid structures (compact) have larger magnetic moments compared with experiments due to the increased localization of the 4d states. Thus, we would conclude that GGA provides a better description of the Rh-n clusters, however, a recent experimental-theoretical study [ Harding et al., J. Chem. Phys. 133, 214304 (2010)] found that only compact structures are able to explain experimental vibrational data, while open structures cannot. Therefore, it indicates that the study of Rh-n clusters is a challenging problem and further experimental studies are required to help in the solution of this conundrum, as well as a better description of the exchange and correlation effects on the Rh n clusters using theoretical methods such as the quantum Monte Carlo method.

GENERALIZED FINITE ELEMENT METHOD ON NONCONVENTIONAL HYBRID-MIXED FORMULATION

The generalized finite element method (GFEM) is applied to a nonconventional hybrid-mixed stress formulation (HMSF) for plane analysis. In the HMSF, three approximation fields are involved: stresses and displacements in the domain and displacement fields on the static boundary. The GFEM-HMSF shape functions are then generated by the product of a partition of unity associated to each field and the polynomials enrichment functions. In principle, the enrichment can be conducted independently over each of the HMSF approximation fields. However, stability and convergence features of the resulting numerical method can be affected mainly by spurious modes generated when enrichment is arbitrarily applied to the displacement fields. With the aim to efficiently explore the enrichment possibilities, an extension to GFEM-HMSF of the conventional Zienkiewicz-Patch-Test is proposed as a necessary condition to ensure numerical stability. Finally, once the extended Patch-Test is satisfied, some numerical analyses focusing on the selective enrichment over distorted meshes formed by bilinear quadrilateral finite elements are presented, thus showing the performance of the GFEM-HMSF combination.

Glass/PDMS hybrid microfluidic device integrating vertically aligned SWCNTs to ultrasensitive electrochemical determinations

This communication reports a promising platform for rapid, simple, direct, and ultrasensitive determination of serotonin. The method is related to integration of vertically aligned single-walled carbon nanotubes (SWCNTs) in electrochemical microfluidic devices. The required microfabrication protocol is simple and fast. In addition, the nanomaterial influenced remarkably the obtained limit-of-detection (LOD) values. Our system achieved a LOD of 0.2 nmol L-1 for serotonin, to the best of our knowledge one of the lowest values reported in the literature.