The area of character recognition has received a considerable attention by researchers all over the world during the last three decades. However, this research explores best sets of feature extraction techniques and studies the accuracy of well-known classifiers for Arabic numeral using the Statistical styles in two methods and making comparison study between them. First method Linear Discriminant function that is yield results with accuracy as high as 90% of original grouped cases correctly classified. In the second method, we proposed algorithm, The results show the efficiency of the proposed algorithms, where it is found to achieve recognition accuracy of 92.9% and 91.4%. This is providing efficiency more than the first method.
The shortage in surface water quantities led to a shift in dependence on the groundwater as an alternative water source in southern parts of Iraq. The groundwater is decreasing in quantity and water quality is degrading due to different factors. Therefore, it is important to assess the groundwater quality of the Missan Governorate of the country by analyzing the physicochemical parameters and distinguishing the probable sources of contaminants in the area. The present study used water quality diagrams and statistical methods such as factor analysis and agglomerative cluster analysis to determine the sources of chemical ions in the forty-four groundwater samples collected from wells in the study area. In addition, the Water Quality Index (WQ
... Show MoreFace Recognition Systems (FRS) are increasingly targeted by morphing attacks, where facial features of multiple individuals are blended into a synthetic image to deceive biometric verification. This paper proposes an enhanced Siamese Neural Network (SNN)-based system for robust morph detection. The methodology involves four stages. First, a dataset of real and morphed images is generated using StyleGAN, producing high-quality facial images. Second, facial regions are extracted using Faster Region-based Convolutional Neural Networks (R-CNN) to isolate relevant features and eliminate background noise. Third, a Local Binary Pattern-Convolutional Neural Network (LBP-CNN) is used to build a baseline FRS and assess its susceptibility to d
... Show MoreIn this study, the Earth's surface was studied in Razzaza Lake for 25 years, using remote sensing methods. Images of the satellites Landsat 5 (TM) and 8 (OLI) were used to study and determine the components of the land cover. The study covered the years 1995-2021 with an interval of 5 years, as this region is uninhabited, so the change in the land cover is slow. The land cover was divided into three main classes and seven subclasses and classified using the maximum likelihood classifier with the help of training sets collected to represent the classes that made up the land cover. The changes detected in the land cover were studied by considering 1995 as a reference year. It was found that there was a significant reduction in the water mass
... Show MoreThis study was aimed to isolate and identify Saccharomyces boulardii from Mangosteen fruits (Garcinia mangostana L.) by traditional and molecular identification methods To get safe and healthy foods probiotics for use, The isolates and two commercial strains were subjected to cultural, morphological and biochemical tests, The colonies of the isolates were spherical, smooth, mucoidal, dull and white to cream colour on SD agar media .The shape of cells was globose to ovoid and sometimes with budding, in a single form or clustered like a beehive. The isolates and two commercial strains were unable to metabolized galactose and lactose , Results shows that all isolates were unable to utilize potassium nitrate and not grow in the presence of (
... Show MoreThe issue of liquidity, profitability, and money employment, and capital fullness is one of the most important issues that gained high consideration by other authors and researchers in their attempts to find out the real relationship and how can balance be achieved, which is the main goal of each deposits.
For the sake of comprising the study variables, the research has formed the problem of the study which refers to the bank capability to enlarge profits without dissipation in liquidity of the bank which will negatively reflect on the bank's fame as well as the customers' trust. For all these matters, the researcher has proposed a set of aims, the important of which is the estimation of the bank profitability; liquid
... Show MoreThe research has been concerned with the modalities of foreign trade payments (foreign trade financing), and made an accounting comparison between them to choose the best way to pay for the imported goods (payment of the real values of imported goods), given the importance of the impact of this activity on the national economy of all countries of the world, especially Iraq for the adoption of a very large amount of imported goods to meet the requirements of the people, which require the flow of huge amounts of foreign currency outside Iraq to pay for these goods, and therefore dealing incorrectly with it leads to the destruction of the national economy and the spread of a number of negative social and economic phenomena of
... Show MoreThe research aims to reveal the recent trends used in providing information and to know the persuasive methods used in designing the content of the infographic as well as the nature of persuasive design methods and the topics presented by the infographic in the research sample. The researcher used the survey method, specifically the survey, by using the content analysis method to analyze the infographic material from the sample selected from the press and news sites that are the subject of the research, based on the method of what was said? How was it said? The researcher relied on the intentional sample, and this sample depends on the researcher selecting the vocabulary of the sample based on experiences and evaluating the c
... Show MoreEmotion recognition has important applications in human-computer interaction. Various sources such as facial expressions and speech have been considered for interpreting human emotions. The aim of this paper is to develop an emotion recognition system from facial expressions and speech using a hybrid of machine-learning algorithms in order to enhance the overall performance of human computer communication. For facial emotion recognition, a deep convolutional neural network is used for feature extraction and classification, whereas for speech emotion recognition, the zero-crossing rate, mean, standard deviation and mel frequency cepstral coefficient features are extracted. The extracted features are then fed to a random forest classifier. In
... Show MoreIn this paper, An application of non-additive measures for re-evaluating the degree of importance of some student failure reasons has been discussed. We apply non-additive fuzzy integral model (Sugeno, Shilkret and Choquet) integrals for some expected factors which effect student examination performance for different students' cases.
In this study, we have created a new Arabic dataset annotated according to Ekman’s basic emotions (Anger, Disgust, Fear, Happiness, Sadness and Surprise). This dataset is composed from Facebook posts written in the Iraqi dialect. We evaluated the quality of this dataset using four external judges which resulted in an average inter-annotation agreement of 0.751. Then we explored six different supervised machine learning methods to test the new dataset. We used Weka standard classifiers ZeroR, J48, Naïve Bayes, Multinomial Naïve Bayes for Text, and SMO. We also used a further compression-based classifier called PPM not included in Weka. Our study reveals that the PPM classifier significantly outperforms other classifiers such as SVM and N
... Show More