Sharif Digital Repository

Purpose – The purpose of this paper is to propose a Meta modeling based on regression, neural network, and clustering to analyze the job satisfaction factors and improvement policy making. Design/methodology/approach – Since any job satisfaction evaluation supposes to improve the status by prescribing specific strategies to be performed in the organization, proposing applicable strategies is decisively important. Task demand, social structure and leader-member exchange (LMX) are general applications easily conceptualized while proposing job satisfaction improvement strategies. Findings – On the basis of these empirical findings, the authors first aim to identify relationships between LMX,... 

The aim of this study is to investigate the effect of the rock brittleness indexes on the specific ampere draw of the circular diamond saws. In this study, twelve rock types belonging to granite and carbonate rock were cut with two different types of circular diamond saws on a fully instrumented laboratory-sawing rig at different feed rate and depths of cut. Rock samples were collected from factories from Iran for laboratory tests and uniaxial compressive strength and tensile strength were determined. The brittleness of B 1 (the ratio of compressive strength to tensile strength), B 2 (the ratio of compressive strength minus tensile strength to compressive strength plus tensile strength), and... 

A new method for the robust estimation of target orientation using measured radar cross section is proposed. The method is based on a Generalized Regression Neural Network (GRNN) scheme. The network is trained by the FFT modulus of bistatic radar cross section data sampled at the receiver positions. The target value to be trained is the angle between a defined target orientation and the incident wave. Results based on actual measurements are presented  

A quantitative structure-activity relationship study based on multiple linear regression (MLR), artificial neural network (ANN), and self-training artificial neural network (STANN) techniques was carried out for the prediction of gas chromatographic relative retention times of 13 different classes of organic compounds. The five descriptors appearing in the selected MLR model are molecular density, Winer number, boiling point, polarizability and square of polarizability. A 5-6-1 ANN and a 5-4-1 STANN were generated using the five descriptors appearing in the MLR model as inputs. Comparison of the standard errors and correlation coefficients shows the superiority of ANN and STANN over the MLR... 

The prediction of production rate in ornamental stones sawing is very important in cost estimation and process planning of the rock sawing plants. The main aim of this paper is finding a mathematical correlation between production rate and rock brittleness indexes. The utilized data have been collected from several stone factories in Iran. Seventeen different granite and carbonate rocks have been experienced sawing conditions with large-diameter circular saws. The laboratory tests such as uniaxial compressive strength and tensile strength, were carried out on the rock samples which were collected from these factories. The ratio of compressive strength to tensile strength (B1), the ratio of... 

A rotated general regression neural network is presented as an enhancement to the general regression neural network. A variable kernel estimate for multivariate densities is considered. A coordinate transformation is adopted which circumvent the difficulty of predicting multimodal distribution with large variance differences between modes which is associated with the general regression neural network. The proposed technique trains the network in a way that the variance differences between modes is kept small and in the same order. Further, the technique reduces the number of indispensable training parameters to two parameters and lowers the load of the computation as well as the time for... 

Although statistical modeling is a common task in different fields of science, it is still difficult to estimate the best model that can accurately describe inherent characteristics of a system for which historical or experimental data are available. Since we may classify estimating techniques as optimizations, we can model this problem as an optimization problem and solve it by a new heuristic algorithm like neural networks, genetic algorithms, and tabu search or by classic ones such as regression and econometric models. In this paper, we propose a new type of genetic algorithm to find the best regression model among all suggested and evaluate its performances by an economical case study. ©... 

This method introduces the structural error of regression deviation, which is an effective method for the path generation of a vast type of planar and spatial mechanism. The proposed method avoids point-by-point comparison and requirement of timing and reflects the difference between the two curves very effectively in the objective function. By decreasing the number of the design variables, this method would help considerably in decreasing CPU time. The objective function that is based on regression error would converge to a global minimum by a genetic algorithm. At the end, the effectiveness of the method is shown by two numerical examples. © Sharif University of Technology  

The electrophoretic mobilities of 31 isomeric alkyl- and alkenylpyridines in capillary electrophoresis were predicted using an artificial neural network (ANN). The multiple linear regression (MLR) technique was used to select the descriptors as inputs for the artificial neural network. The neural network is a fully connected back-propagation model with a 3-6-1 architecture. The results obtained using the neural network were compared with those obtained using the MLR technique. Standard error of training and standard error of prediction were 6.28 and 5.11%, respectively, for the MLR model and 1.03 and 1.20%, respectively, for the ANN model. Two geometric parameters and one electronic... 

Feasibility investigation of a humidification dehumidification (HDH) desalination system driven by an absorption-compression heat pump cycle (ACHPC) is carried out in this paper. The proposed hybrid desalination system uses both heating capacity of the discharged brine as a waste heat for the ACHPC and mechanical power of the ACHPC for the HDH system. The system's performance is investigated under different optimal design modes, using genetic algorithm (GA) as the most robust tool for optimization. A steady-state mathematical model based on the mass, energy, exergy, and exergoeconomic balance equations for components of the proposed system is developed and the predicted results are validated... 

The application of artificial neural network to compressor performance map prediction is investigated. Different types of artificial neural network such as multilayer perceptron network, radial basis function network, general regression neural network, and a rotated general regression neural network proposed by the authors are considered. Two different models are utilized in simulating the performance map. The results indicate that while the rotated general regression neural network has the least mean error and best agreement to the experimental data, it is however limited to curve fitting application. On the other hand, if one considers a tool for curve fitting as well as for interpolation... 

Unsymmetrical dimethyl hydrazine (UDMH) is a strong propellant, which due to its very good physical properties and high power of repellency has been utilized as a liquid fuel for fighter jet engines for so many years. There are different methods for production of this material. One of the more efficient ones which results in higher yields compared to others is the catalytic hydrogenation of Nitroso Dimethylamine (NDMA). In this work hydrogenation of NDMA to UDMH on a 5% Pd/C in aqueous solution of NDMA was studied experimentally. Experiments were carried out in a Semi-batch three phase STR reactor under constant pressure and temperature in the range of 40 to 70°C, pressures of up to 15 bar... 

The relative response factors (RRFs) of a flame ionization detection (FID) system and two pulsed discharge photoionization detection (PID) systems with different discharge gases are predicted for a set of organic compounds containing various functional groups. As a first step, numerical descriptors were calculated based on the molecular structures of compounds. Then, multiple linear regression (MLR) was employed to find informative subsets of descriptors that can predict the RRFs of these compounds. The selected MLR model for the FID system includes seven descriptors and two selected MLR models for the PID systems with argon- and krypton-doped helium as the discharge gases, respectively,...