Alzheimer’s Disease (AD) is the most prevailing type of dementia. The prevalence of AD is estimated to be around 5% after 65 years old and is staggering 30% for more than 85 years old in developed countries. AD destroys brain cells causing people to lose their memory, mental functions and ability to continue daily activities. The findings of this study are likely to aid specialists in their decision-making process by using patients’ Magnetic Resonance Imaging (MRI) to distinguish patients with AD from Normal Control (NC). Performance evolution was applied to 346 Magnetic Resonance images from the Alzheimer's Neuroimaging Initiative (ADNI) collection. The Deep Belief Network (DBN) classifier was used to fulfill classification function. Weights were used to test the proposed method's recognition capacity, and the network was trained with a sample training set. As a result, this study offeres a new method for identifying Alzheimer's disease utilizing automated categorization. In tests, it performed admirably With 98.46% accuracy achieved for AD and NC studied classes when combining Gray Level Co-occurrence Matrix (GLCM) features with a DBN.
This study focusses on the effect of using ICA transform on the classification accuracy of satellite images using the maximum likelihood classifier. The study area represents an agricultural area north of the capital Baghdad - Iraq, as it was captured by the Landsat 8 satellite on 12 January 2021, where the bands of the OLI sensor were used. A field visit was made to a variety of classes that represent the landcover of the study area and the geographical location of these classes was recorded. Gaussian, Kurtosis, and LogCosh kernels were used to perform the ICA transform of the OLI Landsat 8 image. Different training sets were made for each of the ICA and Landsat 8 images separately that used in the classification phase, and used to calcula
... Show MoreInternal control system is a safety valve that preserves economic units assets and ensure the accuracy of financial data, as well as to obligation in the laws, regulations, administrative policies ,and improve the efficiency, effectiveness and economic of operation, so it has become imperative for these units attention to internal and developed control system The research problem in exposure the economic units when the exercise of their business to many of the risks to growth or hinder the achievement of its objectives and the risks (financial, operational, strategy, risk) and not it rely on risk Assessment according to modern scientific methods, as in Brown's risk Classification, Which led to the weakness of the internal control identif
... Show MoreAn eco-epidemic model is proposed in this paper. It is assumed that there is a stage structure in prey and disease in predator. Existence, uniqueness and bounded-ness of the solution for the system are studied. The existence of each possible steady state points is discussed. The local condition for stability near each steady state point is investigated. Finally, global dynamics of the proposed model is studied numerically.
A prey-predator model with Michael Mentence type of predator harvesting and infectious disease in prey is studied. The existence, uniqueness and boundedness of the solution of the model are investigated. The dynamical behavior of the system is studied locally as well as globally. The persistence conditions of the system are established. Local bifurcation near each of the equilibrium points is investigated. Finally, numerical simulations are given to show our obtained analytical results.
Introduction: A Pap test can detect pre-cancerous and cancerous cells in the vagina and uterine cervix. Cervical cancer is the easiest gynecologic cancer to be prevented and diagnosed using regular screening tests and follow-up. This study aimed to estimate the cytological changes and the precancerous lesions using Pap smear test and visual inspection of the cervices of Iraqi women, and also to determine the possible relationship of this cancer with patients’ demographic characteristics. Methods: The study included 140 women aged (18-67) years old referred to the National Cancer Research Center (NCRC), Baghdad, Iraq, during the period 2011-2016. Both visual inspections of the uterine cervix and Papanicolaou smear screening were performed
... Show MoreAbstract: non-alcoholic fatty liver disease (NAFLD) is one of the widespread chronic liver diseases; it is ranging from simple fat buildup in the liver (steatosis) to non-alcoholic steatohepatitis (NASH) presence of inflammation and hepatocyte injury. &nb
... Show MoreThe objective of this study is to evaluate the level of cytokines IL-1?, IL-10 and IL-17A in the serum of patients with Alzheimer's disease (AD), vascular dementia (VD) and down syndrome (DS). The results showed that Serum level of IL-1? was significantly increased in AD patients (3.79 ± 0.26 pg/ml) as compared with DS patients (2.78 ± 0.39 pg/ml) or controls (2.78 ± 0.22 pg/ml), while no significant difference was observed between AD and VD (3.25 ± 0.20 pg/ml) patients or between VD patients, DS patients and controls. The serum level of IL-10 was approximated in VD and DS patients and controls (3.39 ± 0.24, 2.77 ± 0.39 and 3.41 ± 0.35 pg/ml, respectively), but was significantly (P ? 0.05) increased in AD patients (5.73 ± 0.55 pg/ml
... Show MoreSupport Vector Machines (SVMs) are supervised learning models used to examine data sets in order to classify or predict dependent variables. SVM is typically used for classification by determining the best hyperplane between two classes. However, working with huge datasets can lead to a number of problems, including time-consuming and inefficient solutions. This research updates the SVM by employing a stochastic gradient descent method. The new approach, the extended stochastic gradient descent SVM (ESGD-SVM), was tested on two simulation datasets. The proposed method was compared with other classification approaches such as logistic regression, naive model, K Nearest Neighbors and Random Forest. The results show that the ESGD-SVM has a
... Show More