Information from 54 Magnetic Resonance Imaging (MRI) brain tumor images (27 benign and 27 malignant) were collected and subjected to multilayer perceptron artificial neural network available on the well know software of IBM SPSS 17 (Statistical Package for the Social Sciences). After many attempts, automatic architecture was decided to be adopted in this research work. Thirteen shape and statistical characteristics of images were considered. The neural network revealed an 89.1 % of correct classification for the training sample and 100 % of correct classification for the test sample. The normalized importance of the considered characteristics showed that kurtosis accounted for 100 % which means that this variable has a substantial effect on how the network perform when predicting cases of brain tumor, contrast accounted for 64.3 %, correlation accounted for 56.7 %, and entropy accounted for 54.8 %. All remaining characteristics accounted for 21.3-46.8 % of normalized importance. The output of the neural networks showed that sensitivity and specificity were scored remarkably high level of probability as it approached % 96.
Salivary peroxidases have biological functions of particular importance to oral health. The aim of this paper is to shed the light on saliva and serum total peroxidases activity as well as the activity of each of salivary peroxidase (SPO) and myeloperoxidase (MPO) in patients with oral tumors. The studied participants were divided into two groups: the first group included 18 oral squamous cell carcinoma patients and 20 age and gender-matched healthy controls while the second group consisted of 20 oral ossifying fibroma patients and 23 age and gender-matched healthy controls. Total peroxidases activity was determined, and its specific activity was calculated in serum and whole mixed saliva as well as in the supernatant and pellet fractions
... Show More<span lang="EN-US">Diabetes is one of the deadliest diseases in the world that can lead to stroke, blindness, organ failure, and amputation of lower limbs. Researches state that diabetes can be controlled if it is detected at an early stage. Scientists are becoming more interested in classification algorithms in diagnosing diseases. In this study, we have analyzed the performance of five classification algorithms namely naïve Bayes, support vector machine, multi layer perceptron artificial neural network, decision tree, and random forest using diabetes dataset that contains the information of 2000 female patients. Various metrics were applied in evaluating the performance of the classifiers such as precision, area under the c
... Show MoreThis work implements the face recognition system based on two stages, the first stage is feature extraction stage and the second stage is the classification stage. The feature extraction stage consists of Self-Organizing Maps (SOM) in a hierarchical format in conjunction with Gabor Filters and local image sampling. Different types of SOM’s were used and a comparison between the results from these SOM’s was given.
The next stage is the classification stage, and consists of self-organizing map neural network; the goal of this stage is to find the similar image to the input image. The proposal method algorithm implemented by using C++ packages, this work is successful classifier for a face database consist of 20
... Show MoreThe biomarker significance of three chemokines (CXCL8, CXCL10 and CXCL16) was evaluated in sera of 45 breast cancer (BC) and 28 benign breast lesion (BBL) patients, as well as 20 control women. Clinical stage and tumor expression of estrogen (ER), progesterone (PgR) and human epidermal growth factor receptor-2 (HER-2) receptors were considered in this evaluation. The results demonstrated that CXCL8, CXCL10 and CXCL16 showed a significant increased median in BC and BBL patients compared to control (CXCL8: 47.3 and 25.7 vs. 15.0; CXCL10: 37.6 and 30.7 vs. 13.1; CXCL16; 27.9 and 25.2 vs. 19.2 pg/ml, respectively). The increased levels of CXCL8 and CXCL16 were more pronounced in triple-negative and HER-2 positive p
... Show MoreBackground: The rapid evolution of Artificial Intelligence (AI) has significantly influenced Education, demonstrating substantial potential to transform traditional teaching and learning methods. AI reshapes teacher-student interactions and the relationship with knowledge. Objective: To analyze the potential benefits, ethical challenges, and limitations of AI in Education based on recent scientific literature, emphasizing the balance between technology and human interaction. Methods: A documentary research approach with a descriptive focus was employed, following the PRISMA protocol for systematic reviews. The search strategy involved analyzing evidence from 18 scientific articles published within the last six years. Results:AI o
... Show MoreThis research aims to clarify the importance of an accounting information system that uses artificial intelligence to detect earnings manipulation. The research problem stems from the widespread manipulation of earning in economic entities, especially at the local level, exacerbated by the high financial and administrative corruption rates in Iraq due to fraudulent accounting practices. Since earning manipulation involves intentional fraudulent acts, it is necessary to implement preventive measures to detect and deter such practices. The main hypothesis of the research assumes that an accounting information system based on artificial intelligence cannot effectively detect the manipulation of profits in Iraqi economic entities. The researche
... Show More