Search

Many algorithms have been proposed so far for pruning and sparse approximation of feedforward neural networks with random weights in order to obtain compact networks which are fast and robust on various datasets. One drawback of the randomization process is that the resulted weight vectors might be highly correlated. It has been shown that ensemble classifiers’ error depends on the amount of error correlation between them. Thus, decrease in correlation between output vectors must lead to generation of more efficient hidden nodes. In this research a new learning algorithm called New Sparse Learning Machine (NSLM) for single-hidden layer feedforward networks is proposed for regression and classification. In the first phase, the algorithm creates hidden layer with small correlation among nodes by orthogonalizing the columns of the output matrix. Then in the second phase, using $$L_1$$ -norm minimization problem, NSLM makes the components of the solution vector become zero as many as possible. The resulted network has higher degree of sparsity while the accuracy is maintained or improved. Therefore, the method leads to a new network with a better generalization performance. Numerical comparisons on several classification and regression datasets confirm the expected improvement in comparison to the basic network.

Since carbon nanotubes (CNTs) are unstable in different polar solvents such as water, using surfactants can open a new gateway for solving the challenge by attaching non-covalent hydrophilic bonds. Here, the influence of different surfactants including gum arabic (GA), cetyl trimethylammonium bromide (CTAB) and sodium dodecyl sulfate (SDS) on stability and thermophysical properties of multi-walled carbon nanotubes (MWCNTs) in aqueous media is experimentally investigated. To reach this purpose, aqueous suspension of surfactant–MWCNT was synthesized in the ratios 0.5–1, 1–1 and 2–1. Zeta potential was used to determine stability of above-mentioned suspensions as a common method. Dynamic light scattering analysis was also employed to determine particles size distribution. The results indicated relative stability of suspensions in all ratios. It was also found that the minimum particle size was obtained in the presence of the ratio 1–1 of SDS and CTAB. Thermophysical properties of above-mentioned suspensions including viscosity, shear stress, electrical conductivity, surface tension and density were also studied at the range of 20–80 °C. The results indicated an increase in the electrical conductivity, density, viscosity, shear stress and a decrease in the surface tension (except in GA) of suspensions in all concentrations relative to pure water in constant temperature. As temperature increases, the electrical conductivity increases significantly, while the viscosity, shear stress, density and surface tension decreases more or less for all concentrations.

Bene hull contains antioxidant components. Optimum conditions for bioactive compound extraction processes from Bene hull using subcritical water with response surface methodology (RSM) were obtained. Temperature (110–200°C), processing time (30–60 min), and the water to Bene hull ratio (10:1–50:1) were the investigated factors. The optimal conditions for maximizing the antioxidant activity were 196.8°C for 52.6 min and a ratio of 43.6:1 for water to Bene hull. Under these conditions, the amount of polyphenolic compounds, the reduction power (RP) (EC50), and the DPPH free radical scavenging activity (RSA) (EC50) were predicted to be 2,284 mg of gallic acid/100 g of Bene hull, 0.2002 mg/mL, and 0.6284 mg/mL, respectively. HPLC analysis was used to identify the main phenolic compounds. The subcritical water extraction technique could be used as a beneficial method to obtain bioactive compounds from Bene hull.

Biodegradable starch/poly (vinyl alcohol)/nano-titanium dioxide (ST/PVA/nano-TiO2) nanocomposite films were prepared via a solution casting method. Their biodegradability, mechanical properties, and thermal properties were also studied in this paper. A general full factorial experimental approach was used to determine effective parameters on the mechanical properties of the prepared films. ST/PVA/TiO2 nanocomposites were characterized by scanning electron microscopy (SEM) and X-ray diffraction (XRD). The results of mechanical analysis show that ST/PVA films with higher contents of PVA have much better mechanical properties. In thermal analysis, it is found that the addition of TiO2 nanoparticles improves the thermal stability of the films. SEM micrographs, taken from the fracture surface of samples, illustrate that the addition of PVA makes the film softer and more flexible. The results of soil burial biodegradation indicate that the biodegradability of ST/PVA/TiO2 films strongly depends on the starch proportion in the film matrix. The degradation rate is increased by the addition of starch in the films.

The main objective of this research was to use Box-Behnken experimental design (BBD) and response surface methodology (RSM) for optimization of micellar-enhanced ultrafiltration (MEUF) to remove lead ions from synthetic wastewater using spiral-wound ultrafiltration membrane. The critical factors selected for the examination were surfactant concentration, molar ratio of surfactant to metal (S/M) and solution pH. A total of 17 experiments were accomplished towards the construction of a quadratic model for both target variables. The experimental results were fitted with a second-order polynomial equation by a multiple regression analysis, and more than 95%, 93% of the variation could be predicted by the models for lead rejection and permeation flux, respectively. The optimum condition was found by using the obtained mathematical models. Optimization indicated that in CSDS=2mM, pH=6.57 and S/M= 9.82 maximum flux and rejection efficiency can be achieved, simultaneously.