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.
Background: Beta thalassemia is a typically autosomal recessive form of severe anemia which is caused by an imbalance of two types of protein (alpha and beta) subunits of hemoglobin. Oxidative stress imbalance is the equilibrium between pro-oxidant\antioxidant statuses in cellular system, which results in damaging the cells. Antioxidant is a chemical that delays the start or slows the rate of lipid oxidation reaction and it play a very important role in the body defense system against reactive oxygen species. The aims of this study were to recorded the oro-facial manifestations in beta thalassemic patients and assess the oxidative stress marker malondialdehyde in serum and salivs and their role in the pathogenesis of beta thalassemia and ev
... Show MoreBackground: The purpose of this study was to assess the relation among the ramal length and width with various cervical and cranio-facial measurements for a sample of Iraqi adults with different skeletal classes. Materials and method: The sample composed of 71 Iraqi adults (36 females and 35 males) with an age ranged between 17-30 years and had different skeletal mal-relations using SNA, SNB and ANB to differentiate between them and assorting them into CL.I, CL.II and CL.III mal-relation. Each individual was subjected to clinical examination and digital true lateral cephalometric radiograph that had been analyzed using AutoCAD 2007 software computer program to determine sixteen linear and ten angular measurements. Descriptive statistics wer
... Show MoreIn data mining, classification is a form of data analysis that can be used to extract models describing important data classes. Two of the well known algorithms used in data mining classification are Backpropagation Neural Network (BNN) and Naïve Bayesian (NB). This paper investigates the performance of these two classification methods using the Car Evaluation dataset. Two models were built for both algorithms and the results were compared. Our experimental results indicated that the BNN classifier yield higher accuracy as compared to the NB classifier but it is less efficient because it is time-consuming and difficult to analyze due to its black-box implementation.
The ability of pulverized walnut-shell to remove oil from aqueous solutions has been studied. It involves two-phase process which consists of using walnut-shell as a filtering bed for the accumulation and adsorption of oil onto its surface. Up to 96% oil removal from synthetic wastewater samples was achieved while tests results showed that 75% of oil can be removed from the actual wastewater discharged from Al- Duara refinery in the south of Baghdad.
This paper presents a hybrid energy resources (HER) system consisting of solar PV, storage, and utility grid. It is a challenge in real time to extract maximum power point (MPP) from the PV solar under variations of the irradiance strength. This work addresses challenges in identifying global MPP, dynamic algorithm behavior, tracking speed, adaptability to changing conditions, and accuracy. Shallow Neural Networks using the deep learning NARMA-L2 controller have been proposed. It is modeled to predict the reference voltage under different irradiance. The dynamic PV solar and nonlinearity have been trained to track the maximum power drawn from the PV solar systems in real time.
Moreover, the proposed controller i
... Show MorePrediction of penetration rate (ROP) is important process in optimization of drilling due to its crucial role in lowering drilling operation costs. This process has complex nature due to too many interrelated factors that affected the rate of penetration, which make difficult predicting process. This paper shows a new technique of rate of penetration prediction by using artificial neural network technique. A three layers model composed of two hidden layers and output layer has built by using drilling parameters data extracted from mud logging and wire line log for Alhalfaya oil field. These drilling parameters includes mechanical (WOB, RPM), hydraulic (HIS), and travel transit time (DT). Five data set represented five formations gathered
... Show More