Recognizing speech emotions is an important subject in pattern recognition. This work is about studying the effect of extracting the minimum possible number of features on the speech emotion recognition (SER) system. In this paper, three experiments performed to reach the best way that gives good accuracy. The first one extracting only three features: zero crossing rate (ZCR), mean, and standard deviation (SD) from emotional speech samples, the second one extracting only the first 12 Mel frequency cepstral coefficient (MFCC) features, and the last experiment applying feature fusion between the mentioned features. In all experiments, the features are classified using five types of classification techniques, which are the Random Forest (RF), k-Nearest Neighbor (k-NN), Sequential Minimal Optimization (SMO), Naïve Bayes (NB), and Decision Tree (DT). The performance of the system validated over Surrey Audio-Visual Expressed Emotion (SAVEE) dataset for seven emotions. The results of the experiments showed given good accuracy compared with the previous studies using a fusion of a few numbers of features with the RF classifier.
Identity crisis is a dominant literary theme, especially in most Arab women writers’ works. However, it has not been given enough attention from a linguistic point of view. By so doing, the current study intends to fill this gap by analyzing the identity crisis from a pragma-stylistic perspective by examining the writer's style in three purposely selected extracts from Diana Abu-Jaber’s novel Origin (2007). The study aims to examine the identity crisis by using pragmatic and stylistic tools and to explore the effects of Abu-Jaber’s stylistic choices on the readers of her work. To conduct this study, an eclectic model comprising Searle’s speech acts (1979), Brown and Levinson's politeness theory (1987), Leech's model of figur
... Show MoreThe Covid-19 virus disease has been shown to affect numerous organs and systems including the liver. The study aimed to compare lipid profiles and liver enzyme levels in individuals who had recovered from Covid-19 infection. To achieve the study objectives, liver Aspartate Aminotransferase (AST), Alanine Aminotransferase (ALT), Alkaline phosphatase (ALP), Random Blood Sugar (RBS) and Lipid profile which include cholesterol, High-Density Lipoprotein (HDL), Triglycerides (T.G), Low-Density Lipoprotein (LDL), and Very low-density Lipoprotein (VLDL) were determined.
One hundred twenty serum samples were obtained, of which fifty samples were utilized as the control healthy persons (not affected by COVID) and seventy samples came f
... Show MoreThis paper presents the application of a framework of fast and efficient compressive sampling based on the concept of random sampling of sparse Audio signal. It provides four important features. (i) It is universal with a variety of sparse signals. (ii) The number of measurements required for exact reconstruction is nearly optimal and much less then the sampling frequency and below the Nyquist frequency. (iii) It has very low complexity and fast computation. (iv) It is developed on the provable mathematical model from which we are able to quantify trade-offs among streaming capability, computation/memory requirement and quality of reconstruction of the audio signal. Compressed sensing CS is an attractive compression scheme due to its uni
... Show MoreOptimized Link State Routing Protocol (OLSR) is an efficient routing protocol used for various Ad hoc networks. OLSR employs the Multipoint Relay (MPR) technique to reduce network overhead traffic. A mobility model's main goal is to realistically simulate the movement behaviors of actual users. However, the high mobility and mobility model is the major design issues for an efficient and effective routing protocol for real Mobile Ad hoc Networks (MANETs). Therefore, this paper aims to analyze the performance of the OLSR protocol concerning various random and group mobility models. Two simulation scenarios were conducted over four mobility models, specifically the Random Waypoint model (RWP), Random Direction model (RD), Nomadic Co
... Show MoreIn this research, the multi-period probabilistic inventory model will be applied to the stores of raw materials used in the leather industry at the General Company for Leather Industries. The raw materials are:Natural leather includes cowhide, whether imported or local, buffalo leather, lamb leather, goat skin, chamois (raw materials made from natural leather), polished leather (raw materials made from natural leather), artificial leather (skai), supplements which include: (cuffs - Clocks - hands - pockets), and threads.This model was built after testing and determining the distribution of demand during the supply period (waiting period) for each material and completely independently from the rest of the materials, as none of the above mate
... Show MoreThe biometric-based keys generation represents the utilization of the extracted features from the human anatomical (physiological) traits like a fingerprint, retina, etc. or behavioral traits like a signature. The retina biometric has inherent robustness, therefore, it is capable of generating random keys with a higher security level compared to the other biometric traits. In this paper, an effective system to generate secure, robust and unique random keys based on retina features has been proposed for cryptographic applications. The retina features are extracted by using the algorithm of glowworm swarm optimization (GSO) that provides promising results through the experiments using the standard retina databases. Additionally, in order t
... Show MoreThe aim of this study was to investigate the effectiveness of binary solvent for regeneration of spent lubricating oil by extraction-flocculation process. The regeneration was investigated by bench scale experiments by using locally provided solvents (Heavy Naphtha, n-Butanol, and iso-Butanol). Solvents to used oil, mixing time, mixing speed and temperatures were studied as operating parameters. The performance on three estimated depended key parameters, namely the percentage of base oil recovered (Yield), percent of oil loss (POL), and the percent of sludge removal (PSR) were used to evaluate the efficiency of the employed binary solvent on extraction process. The best solvent to solvent ratio for binary system were 30:70 for Heavy Naph
... Show MoreDue to the importance of the extraction process in many engineering and medical industries, in addition to great interest in medicinal plants, in this research, microwave-assisted extraction has been applied to extract some active compounds from Rosmarinus officinalis leaves. The optimal extraction conditions were then determined by calculating the ratio and extraction efficiency. The process has also been described through kinetic study by applying five kinetic models, the Hyperbolic diffusion model, Power low model, the First order reaction model, Elovich's model, and Fick's second law diffusion model and determining their compatibility with the studies operation, and determining the kinetic constants for each model. The result
... Show MoreThe extraction of Eucalyptus oil from Iraqi Eucalyptus Camadulensis leaves was studded using water distillation methods. The amount of Eucalyptus oil has been determined in a variety of extraction temperature and agitation speed. The effect of water to Eucalyptus leaves (solvent to solid) ratio and particle size of Eucalyptus leaves has been studied in order to evaluate the amount of Eucalyptus oil. The optimum experimental condition for the Eucalyptus oil extraction was established as follows: 100˚C extraction temperature, 200 rpm agitation speed; 0.5 cm leave particle size and 6:1 ml: g amount of water to eucalyptus leaves Ratio.
The chemical composition of wastes of pressed grapes and found that the main components of wastes of pressed grapes, represented by the percentage of moisture was 6.47%, and the proportions are 3.71%. Either carbohydrates amounted to 85.77 %, either in fat models using petroleum ether Petroleum ether) was the increase of 0.27%. estimated the percentage of ash in the sampls was 3.78%, either fiber reached 69.47 %,, in addition to the test extracts towards the growth of seven types of bacteria, which included Bacillus subtilis, Bacillus cereus, Bacillus stearothermophilus, Escherishia coli, Staphylococcus aureus, Salmonella typhimurium and Pseudomonas fluorescens and yeast Candida albicans and Kluyveromyces marxianus, ( diffusion method ).
... Show More