Generally, direct measurement of soil compression index (Cc) is expensive and time-consuming. To save time and effort, indirect methods to obtain Cc may be an inexpensive option. Usually, the indirect methods are based on a correlation between some easier measuring descriptive variables such as liquid limit, soil density, and natural water content. This study used the ANFIS and regression methods to obtain Cc indirectly. To achieve the aim of this investigation, 177 undisturbed samples were collected from the cohesive soil in Sulaymaniyah Governorate in Iraq. Results of this study indicated that ANFIS models over-performed the Regression method in estimating Cc with R2 of 0.66 and 0.48 for both ANFIS and Regression models, respectively. This work is an effort to practice the advantages of machine learning techniques to build a robust and cost-effective model for Cc estimation by designers, decision makers, and stakeholders.
Abstract
This paper is an experimental work to determinate the effect of welding velocity and formed arc energy for CO2-MAG fusion weld pool. The input parameters (arc voltage, wire feed speed and gas flow rate) were investigated to find their effects on the weld joint efficiency. Design of experiment with response surface methodology technique was used to build empirical mathematical models for welding velocity and arc energy in term of the input welding parameters. The predicted quadratic models were statistically checked for adequacy purpose by ANOVA analysis. Additionally, numerical optimization was conducted to obtain the optimum values for welding velocity and arc energy. A good agree
... Show MoreThe purpose of this work is to concurrently estimate the UVvisible spectra of binary combinations of piroxicam and mefenamic acid using the chemometric approach. To create the model, spectral data from 73 samples (with wavelengths between 200 and 400 nm) were employed. A two-layer artificial neural network model was created, with two neurons in the output layer and fourteen neurons in the hidden layer. The model was trained to simulate the concentrations and spectra of piroxicam and mefenamic acid. For piroxicam and mefenamic acid, respectively, the Levenberg-Marquardt algorithm with feed-forward back-propagation learning produced root mean square errors of prediction of 0.1679 μg/mL and 0.1154 μg/mL, with coefficients of determination of
... Show MoreOily wastewater is one of the most challenging streams to deal with especially if the oil exists in emulsified form. In this study, electrospinning method was used to prepare nanofiberous polyvinylidene fluoride (PVDF) membranes and study their performance in oil removal. Graphene particles were embedded in the electrospun PVDF membrane to enhance the efficiency of the membranes. The prepared membranes were characterized using a scanning electron microscopy (SEM) to verify the graphene stabilization on the surface of the membrane homogeneously; while FTIR was used to detect the functional groups on the membrane surface. The membrane wettability was assessed by measuring the contact angle. The PVDF and PVDF / Graphene membranes efficiency
... Show MoreWe prepared polythiophene (PTH) with single wall carbon nanotube (SWCNT) nanocomposite thin films for Nitrogen dioxide (NO2) gas sensing applications. Thin films were synthesized via electrochemical polymerization method onto (Indium tin oxide) ITO coated glass substrate of thiophene monomer with magnesium perchlorate and different concentration from SWCNT (0.012 and 0.016) % in the presence130mL of Acetonitrile used. X-ray diffraction (XRD), Field Emission Scanning Electron microscopy (FE-SEM), Atomic Force Microscope (AFM) and Fourier Transform Infrared Spectroscopy (FT-IR) were used to characterized these nanocomposite thin films. The response of these nanocomposite for NO2 gas was evaluated via monitoring the change
... Show MoreThis paper proposes a new structure of the hybrid neural controller based on the identification model for nonlinear systems. The goal of this work is to employ the structure of the Modified Elman Neural Network (MENN) model into the NARMA-L2 structure instead of Multi-Layer Perceptron (MLP) model in order to construct a new hybrid neural structure that can be used as an identifier model and a nonlinear controller for the SISO linear or nonlinear systems. Weight parameters of the hybrid neural structure with its serial-parallel configuration are adapted by using the Back propagation learning algorithm. The ability of the proposed hybrid neural structure for nonlinear system has achieved a fast learning with minimum number
... Show MoreThe aim of the present study was to develop theophylline (TP) inhalable sustained delivery system by preparing solid lipid microparticles using glyceryl behenate (GB) and poloxamer 188 (PX) as a lipid carrier and a surfactant respectively. The method involves loading TP nanoparticles into the lipid using high shear homogenization – ultrasonication technique followed by lyophilization. The compositional variations and interactions were evaluated using response surface methodology, a Box – Behnken design of experiment (DOE). The DOE constructed using TP (X1), GB (X2) and PX (X3) levels as independent factors. Responses measured were the entrapment efficiency (% EE) (Y1), mass median
... Show More
Concentrated research topic in addressing variable vital to the work of offices of inspectors general, construction and scale effectiveness and efficiency is the organizational structure, which are important as is obvious to any researcher in the management and organization and this variable would affect the exercise task supervision and inspection of financial and administrative corruption and combat efficiently, Thus this effect will be placed in the fold ability to achieve goals. That the creation of the organizational structure and requirements to achieve harmony between its properties is creating step towards success. This research aims to analyze the characteristics and style o
Sentiment analysis refers to the task of identifying polarity of positive and negative for particular text that yield an opinion. Arabic language has been expanded dramatically in the last decade especially with the emergence of social websites (e.g. Twitter, Facebook, etc.). Several studies addressed sentiment analysis for Arabic language using various techniques. The most efficient techniques according to the literature were the machine learning due to their capabilities to build a training model. Yet, there is still issues facing the Arabic sentiment analysis using machine learning techniques. Such issues are related to employing robust features that have the ability to discrimina
... Show More