Mobile-based human emotion recognition is very challenging subject, most of the approaches suggested and built in this field utilized various contexts that can be derived from the external sensors and the smartphone, but these approaches suffer from different obstacles and challenges. The proposed system integrated human speech signal and heart rate, in one system, to leverage the accuracy of the human emotion recognition. The proposed system is designed to recognize four human emotions; angry, happy, sad and normal. In this system, the smartphone is used to record user speech and send it to a server. The smartwatch, fixed on user wrist, is used to measure user heart rate while the user is speaking and send it, via Bluetooth, to the smartphone which in turn sends it to the server. At the server side, the speech features are extracted from the speech signal to be classified by neural network. To minimize the misclassification of the neural network, the user heart rate measurement is used to direct the extracted speech features to either excited (angry and happy) neural network or to the calm (sad and normal) neural network. In spite of the challenges associated with the system, the system achieved 96.49% for known speakers and 79.05% for unknown speakers
The influence of different thickness (500,750, and 1000) nm on the structure properties electrical conductivity and hall effect measurements have been investigated on the films of copper indium selenide CuInSe2 (CIS) the films were prepared by thermal evaporation technique on glass substrates at RT from compound alloy. The XRD pattern show that the film have poly crystalline structure a, the grain size increasing with as a function the thickness. Electrical conductivity (σ), the activation energies (Ea1,Ea2), hall mobility and the carrier concentration are investigated as function of thickness. All films contain two types of transport mechanisms of free carriers increase films thickness. The electrical conductivity increase with thickness
... Show MoreThe adsorption of Malonic acid, Succinic acid, Adipic acid, and Azelaic acid from their aqueous solutions on zinc oxide surface were investigated. The adsorption efficiency was investigated using various factors such as adsorbent amount, contact time, initial concentration, and temperature. Optimum conditions for acids removal from its aqueous solutions were found to be adsorbent dose (0.2 g), equilibrium contact time (40 minutes), initial acids concentration (0.005 M). Variation of temperature as a function of adsorption efficiency showed that increasing the temperature would result in decreasing the adsorption ability. Kinetic modeling by applying the pseudo-second order model can provide a better fit of the data with a greater correla
... Show MoreAbdominal fat synthesizes a variety of adipokines, including vaspin and chemerin, that affect the resistance to insulin. This research was conducted to demonstrate the effect of pioglitazone, one insulin sensitizer used to decrease insulin resistance, on these adipokines in obese patients with polycystic ovary (PCOS). Twenty-five obese women with PCOS were treated with pioglitazone 15mg/bid for 12 weeks. Modifications in fasting blood glucose (FBG), serum fasting insulin (FSI), chemerin and vaspin serum levels, follicle stimulation hormone (FSH), luteinizing hormone (LH), testosterone (T), and in baseline and post-therapy were assessed. Body mass index decreased without any substantial variance after 12 weeks of piogl
... Show MoreField experiment was conducted to test the effect of saline water 2 and7 dSm-1 potassium fertilizer rate 150,300 and 450 kg/donum on nitrogen fixation in Pisum sativum L. nodules. The experiment included anatomy study .Results water salinity ( 2,7 dSm-1) as a main plot and fertilizer rates as a sub plot. Results indicated that irrigation with saline water 7 dSm-¹ caused a significant decrease in N contents especially in the lower parts of the plants. The percentage of the N decreased in lower leaves to (0.01%) under 7dSm-¹ and 300 kg/donum fertilizer; however the percentage increased in the upper leaves to (2.80%) under with 2dSm-¹of irrigation water and 300 kg/ donum fertilizer rate. Fresh weight decreased to 6.26g under 7 dSm
... Show MoreThe present research has investigated the effect of microwave energy on improving the flow properties of heavy crude oil. The fragmentation of crude oil molecules was carried out with and without using 1 and 10 wt. % concentration of various types of H-donors like tetralin, cyclohexane, and naphtha. Microwave power of 320, 385, and 540 W and radiation time 1-9 min, and temperature were studied. The kinematic viscosity and asphaltene content were measured for evaluation the improving of heavy crude oil.
Results show that viscosity of crude oil decreased with increase H-donor concentration, a maximum percentage of viscosity reduction was10.63 % for tetralin at 6 min radiation time, while 8.67%, and 7.34% for cycl
... Show MoreThis study discusses risk management strategies caused by pandemic-related (Covid-19) suspensions in thirty-six engineering projects of different types and sizes selected from countries in the middle east and especially Iraq. The primary data collection method was a survey and questionnaire completed by selected project crew and laborers. Data were processed using Microsoft Excel to construct models to help decision-makers find solutions to the scheduling problems that may be expected to occur during a pandemic. A theoretical and practical concept for project risk management that addresses a range of global and local issues that affect schedule and cost is presented and results indicate that the most significant delays are due to a
... Show More<p>Currently, breast cancer is one of the most common cancers and a main reason of women death worldwide particularly in<strong> </strong>developing countries such as Iraq. our work aims to predict the type of tumor whether benign or malignant through models that were built using logistic regression and neural networks and we hope it will help doctors in detecting the type of breast tumor. Four models were set using binary logistic regression and two different types of artificial neural networks namely multilayer perceptron MLP and radial basis function RBF. Evaluation of validated and trained models was done using several performance metrics like accuracy, sensitivity, specificity, and AUC (area under receiver ope
... Show More