A comparison of artificial neural networks learning algorithms in predicting tendency for suicide

New approaches adopted by behavioral science researchers to use modern modeling and predicting tools such as artificial neural networks have necessitated the study and comparison of the efficiency of different learning algorithms of these networks for various applications. By using well-known and different learning algorithms, this study examines and compares the Perceptron artificial neural network as predicting tendency for suicide based on risk factors within 33 input parameters framework used in neural network. To find the “best” learning algorithm, the algorithms were compared in terms of train and capability. The experimental data were collected through questionnaires distributed among 800 university students. All questionnaires used in this research were standardized with appropriate validity and reliability. The study findings indicated that LM and BFG algorithms had close evaluation in terms of performance index and true acceptance rate (TAR), and they showed higher predictive accuracy than the other algorithms. Furthermore, CFG algorithm had the minimum training time.     

Dynamic Wavelet Neural Network for Nonlinear Identification of Highrise Buildings

Abstract:   Recently, the authors presented a multiparadigm dynamic time-delay fuzzy wavelet neural network (WNN) model for nonparametric identification of structures using the nonlinear autoregressive moving average with exogenous inputs. Compared with conventional neural networks, training of a dynamic neural network for system identification of large-scale structures is substantially more complicated and time consuming because both input and output of the network are not single valued but involve thousands of time steps. In this article, an adaptive Levenberg–Marquardt least-squares algorithm with a backtracking inexact linear search scheme is presented for training of the dynamic fuzzy WNN model. The approach avoids the second-order differentiation required in the Gauss–Newton algorithm and overcomes the numerical instabilities encountered in the steepest descent algorithm with improved learning convergence rate and high computational efficiency. The model is applied to two highrise moment-resisting building structures, taking into account their geometric nonlinearities. Validation results demonstrate that the new methodology provides an efficient and accurate tool for nonlinear system identification of high-rising buildings.     

A New Approach for Health Monitoring of Structures: Terrestrial Laser Scanning

Abstract:   A new approach is presented for health monitoring of structures using terrestrial laser scanning (TLS). Three-dimensional (3D) coordinates of a target structure acquired using TLS can have maximum errors of about 10 mm, which is insufficient for the purpose of health monitoring of structures. A displacement measurement model is presented to improve the accuracy of the measurement. The model is tested experimentally on a simply supported steel beam. Measurements were made using three different techniques: (1) linear variable displacement transducers (LVDTs), (2) electric strain gages, and (3) a long gage fiber optic sensor. The maximum deflections estimated by the TLS model are less than 1 mm and within 1.6% of those measured directly by LVDT. Although GPS methods allow measurement of displacements only at the GPS receiver antenna location, the proposed TLS method allows measurement of the entire building's or bridge's deformed shape, and thus a realistic solution for monitoring structures at both structure and member level. Furthermore, it can be used to create a 3D finite element model of a structural member or the entire structure at any instance of time automatically. Through periodic measurements of deformations of a structure or a structural member and performing inverse structural analyses with the measured 3D displacements, the health of the structure can be monitored continuously.     

Broiler chicken litter application timing effect on Coastal bermudagrass in southeastern U.S.

Presently, more than 85% of the broiler chicken (Gallus gallus domesticus) litter (BCL) is being applied to pasture lands year-round. This practice results in nutrient losses and potentially unfavorable environmental impacts particularly during the wet winter months. A field plot experiment was initiated in 2001 on a Ruston silt loam in Mize, MS to identify the proper BCL application timing that enhances BCL nutrient uptake by crops while minimizing undesirable nutrient buildup in soil. Seven treatments (BCL application timings) were employed on previously established “Coastal” hybrid bermudagrass [Cynodon dactylon (L.) Pers.] plots. For each treatment, the quantity of broiler chicken litter (a mixture of chicken manure plus bedding materials) needed for each plot was calculated based on the BCL total N content to provide 400 kg N ha⁻¹ for top bermudagrass yield (18 Mg ha⁻¹) and applied either as a single, two-way split, or three-way split at different dates as follow: May; May/June; April/May/June; May/June/July; June/July/August; July/August/September; and August/September/October. Bermudagrass was harvested 5 times each year for dry matter (DM) and nutrient uptake determination. Significant differences in DM yield were observed in each year among application timings. The greatest DM yield was 18.6 Mg ha⁻¹ for the single application in May and lowest at 15.0 Mg ha⁻¹ for Aug/Sep/Oct application dates in 2001 and followed by the same trend in 2002. The N and P uptake by bermudagrass ranged from 270 to 381, and 53 to 63 kg ha⁻¹ respectively, in 2001. Similar trend, but lower values for nutrient uptake were observed in 2002. Significant differences were observed among BCL application timings in regard to soil residual of total carbon (TC), total nitogen (TN), Mehlich 3 extracted P (M3-P), NO₃–N, Cu, and Fe elements at the end of the study. In general, summer and early fall BCL applications resulted in greater buildup of most of these elements. Based on the results of this study, there is a wide window (May–July) for BCL application timing on bermudagrass considering the criteria of producing high yield and low soil residual nutrient. However, the best BCL application timing should be in spring (late April–June) when minimum temperatures exceed those required (24–27°C) for bermudagrass growth.     

Simulation of Air Entrainment during Mold Filling: Comparison with Water Modeling Experiments

Metallurgical and Materials Transactions B - Oxide inclusions form during pouring of metal castings as a result of air entrainment. Recently, a model was developed by the authors to predict the...     

Synthesis and morphology of new functional polyimide/titania nano hybrid materials

The synthesis and full characterization of 3,5-diamino-N-(1-oxo-3-phenyl-1-(phenylamino)propan-2-yl)benzamide (5), as a new diamine monomer containing l-phenylalanine fractions in the structure of pendant group is presented. The stated diamine is employed as a key monomer for the in situ sol–gel fabrication of polyimide/titania nano hybrid thin films containing different titania contents. It is shown that titania particles are created in the size range of 20–80 nm, well-dispersed and enjoy the favorable spherical shapes supposing the constructive organic–inorganic interactions. The superior thermal stabilities of resulted nanocomposite films are confirmed using thermal analysis techniques. Moreover, the UV–Vis spectroscopy has shown the growing up in blocking efficiency along with the increase in titania contents. Predictably, the produced titania nanoparticles have amorphous structures.     

Effect of thermal treatments on functional properties of cress seed (Lepidium sativum) and xanthan gums: A comparative study

Foods are generally subjected to thermal treatments during processing operations, which affect on the functional properties of hydrocolloid solutions. In this paper, the effect of different thermal conditions (60 °C-30 min, 80 °C-23 min, 100 °C-18 min and 121 °C-15 min) on functional properties (rheological, emulsifying and foaming properties) of cress seed gum and xanthan gum were investigated. The results demonstrated that cress seed gum solutions had desirable rheological, emulsifying and foaming properties. When the hydrocolloid samples were heated, an irreversible increase in viscosity of cress seed gum solutions was observed and as a result, the emulsification and foaming properties improved. Whereas, xanthan gum would not have the ability to stand against heat treatment and its viscosity decreased. Nevertheless, the viscosity values of xanthan gum solutions were always higher than cress seed gum in all conditions.