Its well known that understanding human facial expressions is a key component in understanding emotions and finds broad applications in the field of human-computer interaction (HCI), has been a long-standing issue. In this paper, we shed light on the utilisation of a deep convolutional neural network (DCNN) for facial emotion recognition from videos using the TensorFlow machine-learning library from Google. This work was applied to ten emotions from the Amsterdam Dynamic Facial Expression Set-Bath Intensity Variations (ADFES-BIV) dataset and tested using two datasets.
Oxidation of sulfur compounds in fuel followed by an adsorption process were studied using two modes of operation, batch mode and continuous mode (fixed bed). In batch experiment oxidation process of kerosene with sulfur content 2360 ppm was achieved to study the effect of amount of hydrogen peroxide(2.5, 4, 6 and 10) ml at different temperature(40, 60 and 70)°C. Also the effect of amount acetic acid was studied at the optimal conditions of the oxidation step(4ml H2O2 and 60 °C).Besides, the role of acetic acid different temperatures(40, 60, 70) °C and 4ml H2O2, effect of reaction time(5, 30, 60, 120, 300) minutes at temperatures(40,60) °C, 4ml H2O2 and 1 mlHAC)&
... Show MoreIn many industries especially oil companies in Iraq consumed large quantities of water which will produce oil-contaminated water which can cause major pollution in agricultural lands and rivers. The aim of the present work is to enhance the efficiency of dispersed air flotation technique by using highly effective and cost-efficient coagulant to treating gas oil emulsion. The experimental work was carried out using bubble column made of Perspex glass (5cm I.D, 120cm height). A liquid was at depth of 60cm. Different dosage of sawdust +bentonite at ratio 2:1 (0.5+ 0.25; 1+ 0.5 and 2+1) gm and alum at concentration (10,20and30mg/l) at different pH ( 4 and 7) were used to determine optimum dosages of coagulant. Jar test exper
... Show MoreThe present study examines the extraction of lead (Pb), cadmium (Cd) and nickel (Ni) from a contaminated soil by washing process. Ethylenediaminetetraacetic acid disodium salt (Na2EDTA) and hydrochloric acid (HCl) solution were used as extractants. Soil washing is one of the most suitable in-situ/ ex-situ remediation method in removing heavy metals. Soil was artificially contaminated with 500 mg/kg (Pb , Cd and Ni ). A set of batch experiments were carried out at different conditions of extractant concentration , contact time, pH and agitation speed. The results showed that the maximum removal efficiencies of (Cd, Pb and Ni ) were (97, 88 and 24 )&nbs
... Show MoreThe performance of a batch undivided electrochemical reactor with a rotating cylinder electrode of woven-wire (60 mesh size), stainless steel 316, is examined for the removal of copper from synthetic solution of o.5 M sodium chloride containing 125 ppm at pH ≈ 3.5. The effect of total applied current, rotation speed on the figures of merit of the reactor is analyzed. For an applied current of 300 mA at 100 rpm, the copper concentration decreased from 125 to mg l-1 after 60 min of electrolysis with a specific energy consumption of 1.75 kWh kg-1 and a normalized space velocity of 1.62 h-1. The change in concentration was higher when the total applied currents were increased because of the turbulence
... Show MoreA particle swarm optimization algorithm and neural network like self-tuning PID controller for CSTR system is presented. The scheme of the discrete-time PID control structure is based on neural network and tuned the parameters of the PID controller by using a particle swarm optimization PSO technique as a simple and fast training algorithm. The proposed method has advantage that it is not necessary to use a combined structure of identification and decision because it used PSO. Simulation results show the effectiveness of the proposed adaptive PID neural control algorithm in terms of minimum tracking error and smoothness control signal obtained for non-linear dynamical CSTR system.
Positive and negative parity states for 114Te have been studied applying the vibration al limit U(5) of Interacting boson model (IBM- 1 ) . The present results have shown their good agreement with experimental data in addition to the determination of the spin/parity of new energy levels are not assigned experimentally as the levels 0+2 and 5+1 and the levels 3"1 and 5-1 . Then back propagation multiLayer neural network used for positive and negative parity states for 114Te and shown their membership to the Vibration limit U(5) the network implemented by MATLAB system.
The OpenStreetMap (OSM) project aims to establish a free geospatial database for the entire world which is editable by international volunteers. The OSM database contains a wide range of different types of geographical data and characteristics, including highways, buildings, and land use regions. The varying scientific backgrounds of the volunteers can affect the quality of the spatial data that is produced and shared on the internet as an OSM dataset. This study aims to compare the completeness and attribute accuracy of the OSM road networks with the data supplied by a digitizing process for areas in the Baghdad and Thi-Qar governorates. The analyses are primarily based on calculating the portion of the commission (extr
... Show MoreWellbore instability is one of the most common issues encountered during drilling operations. This problem becomes enormous when drilling deep wells that are passing through many different formations. The purpose of this study is to evaluate wellbore failure criteria by constructing a one-dimensional mechanical earth model (1D-MEM) that will help to predict a safe mud-weight window for deep wells. An integrated log measurement has been used to compute MEM components for nine formations along the studied well. Repeated formation pressure and laboratory core testing are used to validate the calculated results. The prediction of mud weight along the nine studied formations shows that for Ahmadi, Nahr Umr, Shuaiba, and Zubair formations
... Show MoreDuring COVID-19, wearing a mask was globally mandated in various workplaces, departments, and offices. New deep learning convolutional neural network (CNN) based classifications were proposed to increase the validation accuracy of face mask detection. This work introduces a face mask model that is able to recognize whether a person is wearing mask or not. The proposed model has two stages to detect and recognize the face mask; at the first stage, the Haar cascade detector is used to detect the face, while at the second stage, the proposed CNN model is used as a classification model that is built from scratch. The experiment was applied on masked faces (MAFA) dataset with images of 160x160 pixels size and RGB color. The model achieve
... Show More